Tag Archives: ML

13 Most Common Google Cloud Reference Architectures

Posted by Priyanka Vergadia, Developer Advocate

Google Cloud is a cloud computing platform that can be used to build and deploy applications. It allows you to take advantage of the flexibility of development while scaling the infrastructure as needed.

I'm often asked by developers to provide a list of Google Cloud architectures that help to get started on the cloud journey. Last month, I decided to start a mini-series on Twitter called “#13DaysOfGCP" where I shared the most common use cases on Google Cloud. I have compiled the list of all 13 architectures in this post. Some of the topics covered are hybrid cloud, mobile app backends, microservices, serverless, CICD and more. If you were not able to catch it, or if you missed a few days, here we bring to you the summary!

Series kickoff #13DaysOfGCP

#1: How to set up hybrid architecture in Google Cloud and on-premises

Day 1

#2: How to mask sensitive data in chatbots using Data loss prevention (DLP) API?

Day 2

#3: How to build mobile app backends on Google Cloud?

Day 3

#4: How to migrate Oracle Database to Spanner?

Day 4

#5: How to set up hybrid architecture for cloud bursting?

Day 5

#6: How to build a data lake in Google Cloud?

Day 6

#7: How to host websites on Google Cloud?

Day 7

#8: How to set up Continuous Integration and Continuous Delivery (CICD) pipeline on Google Cloud?

Day 8

#9: How to build serverless microservices in Google Cloud?

Day 9

#10: Machine Learning on Google Cloud

Day 10

#11: Serverless image, video or text processing in Google Cloud

Day 11

#12: Internet of Things (IoT) on Google Cloud

Day 12

#13: How to set up BeyondCorp zero trust security model?

Day 13

Wrap up with a puzzle

Wrap up!

We hope you enjoy this list of the most common reference architectures. Please let us know your thoughts in the comments below!

Machine Learning-based Damage Assessment for Disaster Relief



Natural disasters, such as earthquakes, hurricanes, and floods, affect large areas and millions of people, but responding to such disasters is a massive logistical challenge. Crisis responders, including governments, NGOs, and UN organizations, need fast access to comprehensive and accurate assessments in the aftermath of disasters to plan how best to allocate limited resources.To this end, very high resolution (VHR) satellite imagery, with up to 0.3 meter resolution, is becoming an increasingly important tool for crisis response, giving responders an unprecedented breadth of visual information about how terrain, infrastructure, and populations are changed by disasters.

However, intensive manual labor is still required to extract operationally-relevant information — collapsed buildings, cracks in bridges, where people have set up temporary shelters — from the raw satellite imagery. As an example, for the 2010 Haiti earthquake, analysts manually examined over 90,000 buildings in the Port-au-Prince area alone, rating the damage each one incurred on a five point scale. Many of these manual analyses take teams of experts many weeks to complete, whereas they are most needed within 48-72 hours after the disaster, when the most urgent decisions are made.

To help mitigate the impact of such disasters, we present "Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks", which details a machine learning (ML) approach to automatically process satellite data to generate building damage assessments. Developed in partnership with the United Nations World Food Program (WFP) Innovation Accelerator, we believe this work has the potential to drastically reduce the time and effort required for crisis workers to produce damage assessment reports. In turn, this would reduce the turnaround times needed to deliver timely disaster aid to the most severely affected areas, while increasing the overall coverage of such critical services.

The Approach
The automatic damage assessment process is split into two steps: building detection and damage classification. In the building detection step, our approach uses an object detection model to draw bounding boxes around each building in the image. We then extract pre-disaster and post-disaster images centered on each detected building and use a classification model to determine whether the building is damaged.

The classification model consists of a convolutional neural network to which is input two 161 pixel x 161 pixel RGB images, corresponding to a 50 m x 50 m ground footprint, centered on a given building. One image is from before the disaster event, and the other image is from after the disaster event. The model analyzes differences in the two images and outputs a score from 0.0 to 1.0, where 0.0 means the building was not damaged, and 1.0 means the building was damaged.

Because the before and after images are taken on different dates, at different times of day, and in some cases by different satellites altogether, there can be a host of different problems that arise. For example, the brightness, contrast, color saturation, and lighting conditions of the images may differ significantly, and the pixels in the image may be misaligned.

To correct for differences in color and illumination, we use histogram equalization to normalize the colors in the before and after images. We also make the model more robust to insignificant color differences by using standard data augmentation techniques, such as randomly perturbing the contrast and saturation of the images, during training.

Training Data
One of the main challenges of this work is assembling a training data set. Data availability in this application is inherently limited because there are only a handful of disasters that have high resolution satellite images and an even smaller number that have existing damage assessments. For labels, we use publicly available damage assessments manually generated by humanitarian organizations operating in this space, such as UNOSAT and REACH. We obtain the original satellite images on which the manual assessments are performed and then use Google Earth Engine to spatially join the damage assessment labels with the satellite images in order to produce the final training examples. All images used to train the model were sourced from commercially available sources.
Examples of individual image patches that capture before and after images of damaged and undamaged buildings from different disasters.
Results
We evaluated this technology for 3 major past earthquakes: the 2010 earthquake in Haiti (magnitude 7.0), the 2017 event in Mexico City (magnitude 7.1), and the series of earthquakes occuring in Indonesia in 2018 (magnitudes 5.9 - 7.5). For each event, we trained the model on buildings in one part of the region affected by the quake and tested it on buildings in another part of the region. We used human expert damage assessments performed by UNOSAT and REACH as the ground truth for evaluation. We measure the model’s quality using both true accuracy (compared to expert assessment) and the area under the ROC curve (AUROC), which captures the trade-off between the model’s true positive and false positive rates of detection, and is a common way to measure quality when the number of positive and negative examples in the test dataset is imbalanced. An AUROC value of 0.5 means that the model’s predictions are random, while a value of 1.0 means the model is perfectly accurate. According to crisis responder feedback, 70% accuracy is the threshold needed for making high-level decisions in the first 72 hours after the disaster.
Area under the
Event Accuracy ROC curve
2010 Haiti earthquake 77% 0.83
2017 Mexico City earthquake 71% 0.79
2018 Indonesia earthquake 78% 0.86
Evaluation of model predictions against human expert assessments (higher is better).
Example model predictions from the 2010 Haiti earthquake. Prediction values closer to 1.0 means the model is more confident that the building is damaged. Values closer to 0.0 means the building is not damaged. A threshold value of 0.5 is typically used to distinguish between damaged/undamaged predictions, but this can be tuned to make the predictions more or less sensitive.
Future Work
While the current model works reasonably well when trained and tested on buildings from the same regions (e.g., same city or country), the ultimate goal is to have a model that can accurately assess building damage for disasters that happen anywhere in the world, and not just those that look similar to the ones the model has been trained on. This is challenging because the variety of the available training data for past disasters is inherently limited to a handful of events that occurred in a few geographic locations. Generalizing to future disasters that will likely occur in new locations is therefore still a challenge for our model and is the focus of ongoing work. We envision a system that can be interactively trained, validated, and deployed by expert analysts so that important aid distribution decisions are always verified by experienced crisis responders. Our hope is that this technology can help communities get the aid that they need in times of most critical need in a timely fashion.

Acknowledgements
This post reflects the work of our co-authors Wenhan Lu and Zebo Li. We would also like to thank Maolin Zuo for his contributions to the project. In tackling this problem, we have had a very productive partnership with the United Nations World Food Programme (WFP) Innovation Accelerator, an organization that identifies, funds, and supports startups and innovative projects to disrupt world hunger.

Source: Google AI Blog


Free Universal Sound Separation

We are happy to announce the release of FUSS: the Free Universal Sound Separation dataset.

Audio recordings often contain a mixture of different sound sources; Universal sound separation is the ability to separate such a mixture into its component sounds, regardless of the types of sound present. Previously, sound separation work has focused on separating mixtures of a small number of sound types, such as "speech" versus "nonspeech", or different instances of the same type of sound, such as speaker #1 versus speaker #2. Often in such work, the number of sounds in a mixture is also assumed to be known a priori. The FUSS dataset shifts focus to the more general problem of separating a variable number of arbitrary sounds from one another.

One major hurdle to training models in this domain is that even if you have high-quality recordings of sound mixtures, you can't easily annotate these recordings with ground truth. High-quality simulation is one approach to overcome this limitation. To achieve good results, you need a diverse set of sounds, a realistic room simulator, and code to mix these elements together for realistic, multi-source, multi-class audio with ground truth. With FUSS, we are releasing all three of these.

FUSS relies on Creative Commons licensed audio clips from freesound.org. We filtered these by license type, then using a pre-release of FSD50k [1], further filtered out sounds that aren't separable by humans when mixed together. We were left with about 23 hours of audio, consisting of 12,377 sounds useful for mixing (7,237 train, 2,883 validation, 2,257 eval). Using these clips, we created 20,000 training mixtures, 1,000 validation mixtures, and 1,000 eval mixtures.

We developed our own room simulator implemented in tensorflow, which generates the impulse response of a box shaped room with frequency-dependent reflective properties given a sound source location and a mic location. As part of the dataset release, we provide pre-calculated room impulse responses used for each audio sample along with mixing code, so the research community can simulate novel audio without running the computationally expensive room simulator. Future work may include releasing the code for our room simulator and extending the simulator capabilities to address more extensive acoustic properties of rooms, materials with different reflective properties, novel room shapes, etc.

Finally, we have released a masking-based separation model, based on an improved time-domain convolutional network (TDCN++), described in our recent publications [2, 3]. On the eval set, this model achieves 12.5 dB of scale-invariant signal-to-noise ratio improvement (SI-SNRi) on mixtures with two to four sources, while reconstructing single-source mixtures with 37.6 dB absolute SI-SNR.

Source audio, reverb impulse responses, reverberated mixtures and sources created by the mixing code, and a baseline model checkpoint are available for download. Code for reverberating and mixing the audio data and for training the released model is available on our github page.

The dataset will also be used in the DCASE challenge, as a component of the Sound Event Detection and Separation task. The released model will serve as a baseline for this competition, and a benchmark to demonstrate progress against in future experiments.

Our hope is this dataset will lower the barrier to new research, and particularly will allow for fast iteration and application of novel techniques from other machine learning domains to the sound separation challenge.

By John Hershey, Scott Wisdom, and Hakan Erdogan, Google Research

References:
[1] Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font Corbera, Dmitry Bogdanov, Andrés Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. "Freesound Datasets: A Platform for the Creation of Open Audio Datasets." International Society for Music Information Retrieval Conference (ISMIR), pp. 486–493. Suzhou, China, 2017.
[2] Ilya Kavalerov, Scott Wisdom, Hakan Erdogan, Brian Patton, Kevin Wilson, Jonathan Le Roux, and John R. Hershey. "Universal Sound Separation." IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 175-179. New Paltz, NY, USA, 2019.
[3] Efthymios Tzinis, Scott Wisdom, John R. Hershey, Aren Jansen, and Daniel P. W. Ellis. "Improving Universal Sound Separation Using Sound Classification." IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2020.

Semantic Reactor: A tool for experimenting with NLU models

Companies are using natural language understanding (NLU) to create digital personal assistants, customer service bots, and semantic search engines for reviews, forums and the news.

However, the perception that using NLU and machine learning is costly and time consuming prevents a lot of potential users from exploring its benefits.

To dispel some of the intimidation of using NLU, and to demonstrate how it can be easily used with pre-trained, generic models, we have released a tool, the Semantic Reactor, and open-sourced example code, The Mystery of the Three Bots.

The Semantic Reactor

The Semantic Reactor is a Google Sheets Add-On that allows the user to sort lines of text in a sheet using a variety of machine-learning models. It is released as a whitelisted experiment, so if you would like to check it out, fill out this application at the Google Cloud AI Workshop. Once approved, you’ll be emailed instructions on how to install it.

The tool offers ranking methods that determine how the list will be sorted. With the semantic similarity method, the lines more similar in meaning to the input will be ranked higher.



With the input-response method, the lines that are the most appropriate conversational responses are ranked higher.

Why use the Semantic Reactor?

There are a lot of interesting things you can do with the Semantic Reactor, but let’s look at the following two:
  • Writing dialogue for a bot that exists within a well-defined environment and has a clear purpose (like a customer service bot) using semantic similarity.
  • Searching within large collections of text, like from a message board. For that, we will use input-response.

Writing Dialogue for a Bot Using Semantic Similarity

For the sake of an example, let’s say you are writing dialogue for a bot that answers questions about a product, in this case, cookies.

If you’ve been running a cookie hotline for a while, you probably can list the most common cookie questions. With that data, you can create your cookie bot. Start by opening a Google Sheet and writing the common questions and answers (questions in the A column, answers in the B).

Here is the start of what that Sheet might look like. Make a copy of the Sheet, which will allow you to use the Semantic Reactor Add-on. Use the tool to experiment with new QA pairs and how each model reacts to them.

Here are a few queries to try, using the semantic similarity rank method:

Query: What are cookie ingredients?
Returns: What are cookies made of?

Query: Are cookies biscuits?
Returns: Are cookies also called biscuits?

Query: What should I serve with cookies?
Returns: What drinks go well with cookies?



Of course, that small list of responses won’t cover many of the questions people will ask your cookie bot. What the Reactor allows you to do is quickly add new QA pairs as you learn about what your users want to ask.

For example, maybe people are asking a lot about cookie calories.

You’d write the new question in column A, and the new answer in column B, and then test a few different phrasings with the Reactor. You might need to tweak the target response a few times to make sure it matches a wide variety of phrasings. You should also experiment with the three different models to see which one performs the best.

For instance, let’s say the new target question you want the model to match to is: “How many calories does a typical cookie have?”

That question might be phrased by users as:
  • Are cookies caloric?
  • A lot of calories in a cookie?
  • Will cookies wreck my diet?
  • Are cookies fattening?


The more you test with live users, the more you’ll find that they phrase their questions in ways you don’t expect. As with all things based on machine learning, constantly refreshing data, testing and improvement is all part of the process.

Searching Through Text Using Input-Response

Sometimes you can’t anticipate what users are going to ask, and sometimes you might be dealing with a lot of potential responses, maybe thousands. In cases like that, you should use the input-response ranking method. That means the model will examine the list of potential responses and then rank each one according to what it thinks is the most likely response.

Here is a Sheet containing a list of simple conversational responses. Using the input-response ranking method, try a few generic conversational openers like “Hello” or “How’s it going?”

Note that in input-response mode, the model is predicting the most likely conversational response to an input and not the most semantically similar response.

Note that “Hello,” in input-response mode, returns “Nice to meet you.” In semantic similarity mode, “Hello” returns what the model thinks is semantically closest to “Hello,” which is “What’s up?”

Now try your own! Add potential responses. Switch between the models and ranking methods to see how it changes the results (be sure to hit the “reload” button every time you add new responses).

Example Code

One of the models available on TensorFlow Hub is the Universal Sentence Encoder Lite. It’s only 1.6MB and is suitable for use within websites and on-device applications.

An open sourced sample game that uses the USE Lite is Mystery of the Three Bots on Github. It’s a simple demonstration that shows how you can use a small semantic ML model to drive conversations with game characters. The corpora the game uses were created and tested using the Semantic Reactor.

You can play a running version of the game here. You can experiment with the corpora of two of the characters, the Maid and the Butler, contained within this Sheet. Be sure to make a copy of the Sheet so you can edit and add new QA pairs.

Where To Get The Models Used Within The Semantic Reactor

All of the models used in the Semantic Reactor are published and available online.
  • Local – Minified TensorFlow.js version of the Universal Sentence Encoder.
  • Basic Online – Basic version of the Universal Sentence Encoder.
  • Multilingual Online – Universal Sentence Encoder trained on question/ answer pairs in 16 languages.

Final Thoughts

These language models are far from perfect. They use their training to give a best estimate on what to return based on the list of responses you gave it. Machine learning is about calculation, prediction, and training. Models can be improved over time with more data and tuning, and in turn, be made more accurate.

Also, because conversational models are trained on dialogue between people, and because people are biased, the models will display biases that exist in the data that they were trained on, sometimes in ways you can’t predict. For more on model bias, and more detail about how these models were trained, see the Semantic Experiences for Developers page.

By Ben Pietrzak, Steve Pucci, Aaron Cohen — Google AI  

Highlights from the 2019 Google AI Residency Program



This fall marks the successful conclusion to the fourth year of the Google AI Residency Program. Started in 2016 with 27 individuals in Mountain View, CA, the 12-month program has grown to nearly 100 residents from nine locations across the globe. Program participants have gone on to great success in PhD programs, academia, non-profits, and industry. Many have also become full-time Google researchers.

The program’s latest installment was our most successful yet, as residents advanced progress in a broad range of research fields, such as machine perception, algorithms and optimization, language understanding, healthcare and many more. Below are a handful of innovative projects from some of this year’s alumni.
  • A large-scale study on cross-lingual transfer in massive multilingual neural machine translation models (recently highlighted as part of this post), trained on billions of sentence pairs from more than 100 languages in order to significantly improve translation for both low- and high-resource languages.
    Visualization of the clustering of encoder representations of all modeled languages, based on representational similarity. Encoder representations of different languages cluster according to linguistic similarity. Languages are color-coded by their linguistic family.
  • A generative model for Scalable Vector Graphics (SVGs), which can be used to aid designers in generating fonts.
  • Top: Unlike pixel representations of icons (right), in this case a "6", SVGs (left; middle) are scale-invariant representations. Bottom: By modelling SVGs directly, we can aid artists in quickly and intuitively iterating over typography designs.
  • A method to learn GANs using discrepancy divergence, a measure that accounts for both the loss function and hypothesis set to provide theoretical learning guarantees.
  • As more generators are added to the DGAN ensemble more modes in the real distribution are covered. From left to right: 1 generator, 5 generators, and 10 generators.
  • A likelihood ratio method for deep generative models that effectively corrects for confounding background statistics to improve out-of-distribution (OOD) detection, and a new benchmark dataset for OOD detection in genomics.
  • Log-likelihood (left) and log likelihood-ratio (right) of each pixel for Fashion-MNIST. The likelihood is dominated by the “background” pixels, whereas the likelihood ratio focuses on the “semantic” pixels and is thus better for OOD detection.
  • A study showing when label smoothing helps, focusing on its impact on calibration of predictions, representations learned by the penultimate layer and effectiveness of knowledge distillation.
  • 2D-projection of representations of three CIFAR100 classes. Without label smoothing, examples are spread, but with label smoothing each example is encouraged to be equally distant to the clusters of the other classes, attenuating intra-class variation and inter-class similarity structure.
The successes of our AI residents go beyond academic publishing. Their achievements include:
  • Organizing a workshop, bringing together experts in theoretical physics and deep learning, to explore how tools from physics can shed light on the theory of deep learning.
  • Founding Queer in AI, an organization for fostering a community of queer researchers and raising awareness of queer issues in AI/ML.
  • Organizing a hands-on Tensorflow tutorial on using Deep Learning for Natural Language Processing.
  • Automatically learning neural net architectures with AdaNet, an open-source, TensorFlow-based framework.
  • Developing Coconet, the model behind the first AI-powered Doodle (created to celebrate renowned German composer and musician Johann Sebastian Bach).
Also, beginning with the next program cycle, residents will be hosted for a duration of 12 months, with the option of extending up to 18 months! This exciting shift comes as part of our effort to improve the overall program experience and outcomes for residents as the program continues to grow and scale.

If you are interested in joining our fifth cohort, applications for the 2020 Google AI Residency program are now open! Visit g.co/airesidency/apply for more information on how to apply. Please submit your application as soon as possible, as we will be considering candidates on a rolling basis. Please see g.co/airesidency for more resident profiles, past resident publications, blog posts and stories. We can’t wait to see where the next year will take us, and hope you’ll consider joining our research teams across the world!

Source: Google AI Blog


The Visual Task Adaptation Benchmark



Deep learning has revolutionized computer vision, with state-of-the-art deep networks learning useful representations directly from raw pixels, leading to unprecedented performance on many vision tasks. However, learning these representations from scratch typically requires hundreds of thousands of training examples. This burden can be reduced by using pre-trained representations, which have become widely available through services such as TensorFlow Hub (TF Hub) and PyTorch Hub. But their ubiquity can itself be a hindrance. For example, for the task of extracting features from images, there can be over 100 models from which to choose. It is hard to know which methods provide the best representations, since different sub-fields use different evaluation protocols, which do not always reflect the final performance on new tasks.

The overarching goal of representation research is to learn representations a single time on large amounts of generic data without the need to train them from scratch for each task, thus reducing data requirements across all vision tasks. But in order to reach that goal, the research community must have a uniform benchmark against which existing and future methods can be evaluated.

To address this problem, we are releasing "The Visual Task Adaptation Benchmark" (VTAB, available on GitHub), a diverse, realistic, and challenging representation benchmark based on one principle — a better representation is one that yields better performance on unseen tasks, with limited in-domain data. Inspired by benchmarks that have driven progress in other fields of machine learning (ML), such as ImageNet for natural image classification, GLUE for Natural Language Processing, and Atari for reinforcement learning, VTAB follows similar guidelines: (i) minimal constraints on solutions to encourage creativity; (ii) a focus on practical considerations; and (iii) challenging tasks for evaluation.

The Benchmark
VTAB is an evaluation protocol designed to measure progress towards general and useful visual representations, and consists of a suite of evaluation vision tasks that a learning algorithm must solve. These algorithms may use pre-trained visual representations to assist them and must satisfy only two requirements:
    i) They must not be pre-trained on any of the data (labels or input images) used in the downstream evaluation tasks.
    ii) They must not contain hardcoded, task-specific, logic. Alternatively put, the evaluation tasks must be treated like a test set — unseen.
These constraints ensure that solutions that are successful when applied to VTAB will be able to generalize to future tasks.

The VTAB protocol begins with the application of an algorithm (A) to a number of independent tasks, drawn from a broad distribution of vision problems. The algorithm may be pre-trained on upstream data to yield a model that contains visual representations, but it must also define an adaptation strategy that consumes a small training set for each downstream task and return a model that makes task-specific predictions. The algorithm’s final score is its average test score across tasks.
The VTAB protocol. Algorithm A is applied to many tasks T, drawn from a broad distribution of vision problems PT. In the example, pet classification, remote sensing, and maze localization are shown.
VTAB includes 19 evaluation tasks that span a variety of domains, divided into three groups — natural, specialized, and structured. Natural image tasks include images of the natural world captured through standard cameras, representing generic objects, fine-grained classes, or abstract concepts. Specialized tasks utilize images captured using specialist equipment, such as medical images or remote sensing. The structured tasks often derive from artificial environments that target understanding of specific changes between images, such as predicting the distance to an object in a 3D scene (e.g., DeepMind Lab), counting objects (e.g., CLEVR), or detecting orientation (e.g., dSprites for disentangled representations).

While highly diverse, all of the tasks in VTAB share one common feature — people can solve them relatively easily after training on just a few examples. To assess algorithmic generalization to new tasks with limited data, performance is evaluated using only 1000 examples per task. Evaluation using the full dataset can be performed for comparison with previous publications.

Findings Using VTAB
We performed a large scale study testing a number of popular visual representation learning algorithms against VTAB. The study included generative models (GANs and VAEs), self-supervised models, semi-supervised models and supervised models. All of the algorithms were pre-trained on the ImageNet dataset. We also compared each of these approaches using no pre-trained representations, i.e., training “from-scratch”. The figure below summarizes the main pattern of results.
Performance of different classes of representation learning algorithms across different task groups: natural, specialized and structured. Each bar shows the average performance of all methods in that class across all tasks in the group.
Overall we find that generative models do not perform as well as the other methods, even worse than from-scratch training. However, self-supervised models perform much better, significantly outperforming from-scratch training. Better still is supervised learning using the ImageNet labels. Interestingly, while supervised learning is significantly better on the Natural group of tasks, self-supervised learning is close on the other two groups whose domains are more dissimilar to ImageNet.

The best performing representation learning algorithm, of those we tested, is S4L, which combines both supervised and self-supervised pre-training losses. The figure below contrasts S4L with standard supervised ImageNet pre-training. S4L appears to improve performance particularly on the Structured tasks. However, representation learning yields a much smaller benefit over training from-scratch groups other than the Natural tasks, indicating that there is much progress required to attain a universal visual representation.
Top: Performance of S4L versus from-scratch training. Each bar corresponds to a task. Positive-valued bars indicate tasks where S4L outperforms from-scratch. Negative bars indicate that from-scratch performed better. Bottom: S4L versus Supervised training on ImageNet. Positive bars indicate that S4L performs better. The bar colour indicates the task group: Red=Natural, Green=Specialized, Blue=Structured. We can see that additional self-supervision tends to help on structured tasks beyond just using ImageNet labels.
Summary
The code to run VTAB is available on GitHub, including the 19 evaluation datasets and exact data splits. Having a publicly available set of benchmarks ensures the reproducibility of results. Progress is tracked with the public leaderboard, and the models evaluated are uploaded to TF Hub for public use and reproduction. A shell script is provided to perform adaptation and evaluation on all the tasks, with a standardized evaluation protocol making VTAB readily accessible across the industry. Since VTAB can be executed on both TPU and GPU, it is highly efficient. One can obtain comparable results with a single NVIDIA Tesla P100 accelerator in a few hours.

The Visual Task Adaptation Benchmark has helped us better understand which visual representations generalize to the broad spectrum of vision tasks, and provides direction for future research. We hope these resources are useful in driving progress toward general and practical visual representations, and as a result, affords deep learning to the long tail of vision problems with limited labelled data.

Acknowledgements
The core team behind this work includes Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, and Sylvain Gelly.

Source: Google AI Blog


Innovations in Graph Representation Learning



Relational data representing relationships between entities is ubiquitous on the Web (e.g., online social networks) and in the physical world (e.g., in protein interaction networks). Such data can be represented as a graph with nodes (e.g., users, proteins), and edges connecting them (e.g., friendship relations, protein interactions). Given the widespread prevalence of graphs, graph analysis plays a fundamental role in machine learning, with applications in clustering, link prediction, privacy, and others. To apply machine learning methods to graphs (e.g., predicting new friendships, or discovering unknown protein interactions) one needs to learn a representation of the graph that is amenable to be used in ML algorithms.

However, graphs are inherently combinatorial structures made of discrete parts like nodes and edges, while many common ML methods, like neural networks, favor continuous structures, in particular vector representations. Vector representations are particularly important in neural networks, as they can be directly used as input layers. To get around the difficulties in using discrete graph representations in ML, graph embedding methods learn a continuous vector space for the graph, assigning each node (and/or edge) in the graph to a specific position in a vector space. A popular approach in this area is that of random-walk-based representation learning, as introduced in DeepWalk.

Left: The well-known Karate graph representing a social network. Right: A continuous space embedding of the nodes in the graph using DeepWalk.
Here we present the results of two recent papers on graph embedding: “Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts” presented at WWW’19 and “Watch Your Step: Learning Node Embeddings via Graph Attention” at NeurIPS’18. The first paper introduces a novel technique to learn multiple embeddings per node, enabling a better characterization of networks with overlapping communities. The second addresses the fundamental problem of hyperparameter tuning in graph embeddings, allowing one to easily deploy graph embeddings methods with less effort. We are also happy to announce that we have released the code for both papers in the Google Research github repository for graph embeddings.

Learning Node Representations that Capture Multiple Social Contexts
In virtually all cases, the crucial assumption of standard graph embedding methods is that a single embedding has to be learned for each node. Thus, the embedding method can be said to seek to identify the single role or position that characterizes each node in the geometry of the graph. Recent work observed, however, that nodes in real networks belong to multiple overlapping communities and play multiple roles—think about your social network where you participate in both your family and in your work community. This observation motivates the following research question: is it possible to develop methods where nodes are embedded in multiple vectors, representing their participation in overlapping communities?

In our WWW’19 paper, we developed Splitter, an unsupervised embedding method that allows the nodes in a graph to have multiple embeddings to better encode their participation in multiple communities. Our method is based on recent innovations in overlapping clustering based on ego-network analysis, using the persona graph concept, in particular. This method takes a graph G, and creates a new graph P (called the persona graph), where each node in G is represented by a series of replicas called the persona nodes. Each persona of a node represents an instantiation of the node in a local community to which it belongs. For each node U in the graph, we analyze the ego-network of the node (i.e., the graph connecting the node to its neighbors, in this example A, B, C, D) to discover local communities to which the node belongs. For instance, in the figure below, node U belongs to two communities: Cluster 1 (with the friends A and B, say U’s family members) and Cluster 2 (with C and D, say U’s colleagues).
Ego-net of node U
Then, we use this information to “split” node U into its two personas U1 (the family persona) and U2 (the work persona). This disentangles the two communities, so that they no longer overlap.
The ego-splitting method separating the U nodes in 2 personas.
This technique has been used to improve the state-of-the-art results in graph embedding methods, showing up to 90% reduction in link prediction (i.e., predicting which link will form in the future) error on a variety of graphs. The key reason for this improvement is the ability of the method to disambiguate highly overlapping communities found in social networks and other real-world graphs. We further validate this result with an in-depth analysis of co-authorship graphs where authors belong to overlapping research communities (e.g., machine learning and data mining).
Top Left: A typical graphs with highly overlapping communities. Top Right: A traditional embedding of the graph on the left using node2vec. Bottom Left: A persona graph of the graph above. Bottom Right: The Splitter embedding of the persona graph. Notice how the persona graph clearly disentangles the overlapping communities of the original graph and Splitter outputs well-separated embeddings.
Automatic hyper-parameter tuning via graph attention.
Graph embedding methods have shown outstanding performance on various ML-based applications, such as link prediction and node classification, but they have a number of hyper-parameters that must be manually set. For example, are nearby nodes more important to capture when learning embeddings than nodes that are further away? Even though experts may be able to fine tune these hyper-parameters, one must do so independently for each graph. To obviate such manual work, in our second paper, we proposed a method to learn the optimal hyper-parameters automatically.

Specifically, many graph embedding methods, like DeepWalk, employ random walks to explore the context around a given node (i.e. the direct neighbors, the neighbors of the neighbors, etc). Such random walks can have many hyper-parameters that allow tuning of the local exploration of the graph, thus regulating the attention given by the embeddings to nearby nodes. Different graphs may present different optimal attention patterns and hence different optimal hyperparameters (see the picture below, where we show two different attention distributions). Watch Your Step formulates a model for the performance of the embedding methods based on the above mentioned hyper-parameters. Then we optimize the hyper-parameters to maximize the performance predicted by the model, using standard backpropagation. We found that the values learned by backpropagation agree with the optimal hyper-parameters obtained by grid search.
Our new method for automatic hyper-parameter tuning, Watch Your Step, uses an attention model to learn different graph context distributions. Shown above are two example local neighborhoods about a center node (in yellow) and the context distributions (red gradient) that was learned by the model. The left-side graph shows a more diffused attention model, while the distribution on the right shows one concentrated on direct neighbors.
This work falls under the growing family of AutoML, where we want to alleviate the burden of optimizing the hyperparameters—a common problem in practical machine learning. Many AutoML methods use neural architecture search. This paper instead shows a variant, where we use the mathematical connection between the hyperparameters in the embeddings and graph-theoretic matrix formulations. The “Auto” portion corresponds to learning the graph hyperparameters by backpropagation.

We believe that our contributions will further advance the state of the research in graph embedding in various directions. Our method for learning multiple node embeddings draws a connection between the rich and well-studied field of overlapping community detection, and the more recent one of graph embedding which we believe may result in fruitful future research. An open problem in this area is the use of multiple-embedding methods for classification. Furthermore, our contribution on learning hyperparameters will foster graph embedding adoption by reducing the need for expensive manual tuning. We hope the release of these papers and code will help the research community pursue these directions.

Acknowledgements
We thank Sami Abu-el-Haija who contributed to this work and is now a Ph.D. student at USC.

Source: Google AI Blog


ML Kit expands into NLP with Language Identification and Smart Reply

Posted by Christiaan Prins and Max Gubin

Today we are announcing the release of two new features to ML Kit: Language Identification and Smart Reply.

You might notice that both of these features are different from our existing APIs that were all focused on image/video processing. Our goal with ML Kit is to offer powerful but simple-to-use APIs to leverage the power of ML, independent of the domain. As such, we are excited to expand ML Kit with solutions for Natural Language Processing (NLP)!

NLP is a category of ML that deals with analyzing and generating text, speech, and other kinds of natural language data. We're excited to start out with two APIs: one that helps you identify the language of text, and one that generates reply suggestions in chat applications. Both of these features work fully on-device and are available on the latest version of the ML Kit SDK, on iOS (9.0 and higher) and Android (4.1 and higher).

Generate reply suggestions based on previous messages

A new feature popping up in messaging apps is to provide the user with a selection of suggested responses, either as actions on a notification or inside the app itself. This can really help a user to quickly respond when they are busy or a handy way to initiate a longer message.

With the new Smart Reply API you can now quickly achieve the same in your own apps. The API provides suggestions based on the last 10 messages in a conversation, although it still works if only one previous message is available. It is a stateless API that fully runs on-device, so we don't keep message history in memory nor send it to a server.

textPlus app providing response suggestions using Smart Reply

We have worked closely with partners like textPlus to ensure Smart Reply is ready for prime time and they have now implemented in-app response suggestions with the latest version of their app (screenshot above).

Adding Smart Reply to your own app is done with a simple function call (using Swift in this example):

let smartReply = NaturalLanguage.naturalLanguage().smartReply()
smartReply.suggestReplies(for: conversation) { result, error in
    guard error == nil, let result = result else {
        return
    }
    if (result.status == .success) {
        for suggestion in result.suggestions {
            print("Suggested reply: \(suggestion.text)")
        }
    }
}

After you initialize a Smart Reply instance, call suggestReplies with a list of recent messages. The callback provides the result which contains a list of suggestions.

For details on how to use the Smart Reply API, check out the documentation.

Tell me more ...

Although as a developer, you can just pick up this new API and easily get it integrated in your app, it may be interesting to reveal a bit on how it works under the hood. At the core of Smart Reply is a machine-learned model that is executed using TensorFlow Lite and has a state-of-the-art modern architecture based on SentencePiece text encoding[1] and Transformer[2].

However, as we realized when we started development of the API, the core suggestion model is not all that's needed to provide a solution that developers can use in their apps. For example, we added a model to detect sensitive topics, so that we avoid making suggestions in response to profanity or in cases of personal tragedy/hardship. Also, we included language identification, to ensure we do not provide suggestions for languages the core model is not trained on. The Smart Reply feature is launching with English support first.

Identify the language of a piece of text

The language of a given text string is a subtle but helpful piece of information. A lot of apps have functionality with a dependency on the language: you can think of features like spell checking, text translation or Smart Reply. Rather than asking a user to specify the language they use, you can use our new Language Identification API.

ML Kit recognizes text in 103 different languages and typically only requires a few words to make an accurate determination. It is fast as well, typically providing a response within 1 to 2 ms across iOS and Android phones.

Similar to the Smart Reply API, you can identify the language with a function call (using Swift in this example):

let languageId = NaturalLanguage.naturalLanguage().languageIdentification()
languageId.identifyLanguage(for: "¿Cómo estás?") { languageCode, error in
  guard error == nil, let languageCode = languageCode else {
    print("Failed to identify language with error: \(error!)")
    return
  }

  print("Identified Language: \(languageCode)")
}

The identifyLanguage functions takes a piece of a text and its callback provides a BCP-47 language code. If no language can be confidently recognized, ML Kit returns a code of und for undetermined. The Language Identification API can also provide a list of possible languages and their confidence values.

For details on how to use the Language Identification API, check out the documentation.

Get started today

We're really excited to expand ML Kit to include Natural Language APIs. Give the two new NLP APIs a spin today and let us know what you think! You can always reach us in our Firebase Talk Google Group.

As ML Kit grows we look forward to adding more APIs and categories that enables you to provide smarter experiences for your users. With that, please keep an eye out for some exciting ML Kit announcements at Google I/O.

Using Deep Learning to Improve Usability on Mobile Devices



Tapping is the most commonly used gesture on mobile interfaces, and is used to trigger all kinds of actions ranging from launching an app to entering text. While the style of clickable elements (e.g., buttons) in traditional desktop graphical user interfaces is often conventionally defined, on mobile interfaces it can still be difficult for people to distinguish tappable versus non-tappable elements due to the diversity of styles. This confusion can lead to false affordances (e.g., a feature that could be mistaken for a button) and a lack of discoverability that can lead to user frustration, uncertainty, and errors. To avoid this, interface designers can conduct a study or a visual affordance test to help clarify the tappability of items in their interfaces. However, such studies are time-consuming and their findings are often limited to a specific app or interface design.

In our CHI'19 paper, "Modeling Mobile Interface Tappability Using Crowdsourcing and Deep Learning", we introduced an approach for modeling the usability of mobile interfaces at scale. We crowdsourced a task to study UI elements across a range of mobile apps to measure the perceived tappability by a user. Our model predictions were consistent with the user group at the ~90% level, demonstrating that a machine learning model can be effectively used to estimate the perceived tappability of interface elements in their design without the need for expensive and time consuming user testing.
Predicting Tappability with Deep Learning
Designers often use visual properties such as the color or depth of an element to signify its availability for interaction on interfaces, e.g., the blue color and underline of a link. While these common signifiers are useful, it is not always clear when to apply them in each specific design setting. Furthermore, with design trends evolving, traditional signifiers are constantly being altered and challenged, potentially causing user uncertainty and mistakes.

To understand how users perceive this changing landscape, we analyzed the potential signifiers affecting tappability in real mobile apps—element type (e.g., check boxes, text boxes, etc.), location, size, color, and words. We started by crowdsourcing volunteers to label the perceived clickability of ~20,000 unique interface elements from ~3,500 apps. With the exception of text boxes, type signifiers yielded low uncertainty in user perceived tappability. The location signifier refers to the position of a feature on the screen and is informed by the common layout design in mobile apps, as demonstrated in the figure below.
Heatmaps displaying the accuracy of tappable and non-tappable elements by location, where warmer colors represent areas of higher accuracy. Users labeled non-tappable elements more accurately towards the upper center of the interface, and tappable elements towards the bottom center of the interface.
The impact of element size was relatively weak, but did indicate confusion in the case of large non-tappable elements. Users showed a tendency to bright colors and short word counts for tappable elements, though word semantics also played a significant role.

We used these labels to train a simple deep neural network that predicts the likelihood that a user will perceive an interface element as tappable versus non-tappable. For a given element of the interface, the model uses a range of features, including the spatial context of the element on the screen (location), the semantics and functionality of the element (words and type), and the visual appearance (size as well as raw pixels). The neural network model applies a convolutional neural network (CNN) to extract features from raw pixels, and uses learned semantic embeddings to represent text content and element properties. The concatenation of all these features are then fed to a fully-connected network layer, the output of which produces a binary classification of an element's tappability.

Evaluation of the Model
The model allowed us to automatically diagnose mismatches between the tappability of each interface element as perceived by a user—predicted by our model—and the intended or actual tappable state of the element specified by the developer or designer. In the example below, our model predicts that there is a 73% chance that a user would think the labels such as "Followers" or "Following" are tappable, while these interface elements are in fact not programmed to be tappable.
To understand how our model behaves compared to human users, particularly when there is ambiguity in human perception, we generated a second, independent dataset by crowdsourcing an effort among 290 volunteers to label each of 2,000 unique interface elements with respect to their perceived tappability. Each element was labeled independently by five different users. We found that more than 40% of the elements in our sample were labeled inconsistently by volunteers. Our model matches this uncertainty in human perception quite well, as demonstrated in the figure below.
The scatterplot of the tappability probability predicted by the model (the Y axis) versus the consistency in the human user labels (the X axis) for each element in the consistency dataset.
When users agree an element's tappability, our model tends to give a more definite answer—a probability close to 1 for tappable and close to 0 for not tappable. When workers are less consistent on an element (towards the middle of the X axis), our model is also less certain about the decision. Overall, our model achieved reasonable accuracy of matching human perception in identifying tappable UI elements with a mean precision of 90.2% and recall of 87.0%.

Predicting tappability is merely one example of what we can do with machine learning to solve usability issues in user interfaces. There are many other challenges in interaction design and user experience research where deep learning models can offer a vehicle to distill large, diverse user experience datasets and advance scientific understandings about interaction behaviors.

Acknowledgements
This research was a joint work of Amanda Swangson, summer intern at Google, and Yang Li, a Research Scientist in Deep Learning and Human Computer Interaction.

Source: Google AI Blog


A Summary of the Google Flood Forecasting Meets Machine Learning Workshop



Recently, we hosted the Google Flood Forecasting Meets Machine Learning workshop in our Tel Aviv office, which brought hydrology and machine learning experts from Google and the broader research community to discuss existing efforts in this space, build a common vocabulary between these groups, and catalyze promising collaborations. In line with our belief that machine learning has the potential to significantly improve flood forecasting efforts and help the hundreds of millions of people affected by floods every year, this workshop discussed improving flood forecasting by aggregating and sharing large data sets, automating calibration and modeling processes, and applying modern statistical and machine learning tools to the problem.

Panel on challenges and opportunities in flood forecasting, featuring (from left to right): Prof. Paolo Burlando (ETH Zürich), Dr. Tyler Erickson (Google Earth Engine), Dr. Peter Salamon (Joint Research Centre) and Prof. Dawei Han (University of Bristol).
The event was kicked off by Google's Yossi Matias, who discussed recent machine learning work and its potential relevance for flood forecasting, crisis response and AI for Social Good, followed by two introductory sessions aimed at bridging some of the knowledge gap between the two fields - introduction to hydrology for computer scientists by Prof. Peter Molnar of ETH Zürich, and introduction to machine learning for hydrologists by Prof. Yishay Mansour of Tel Aviv University and Google

Included in the 2-day event was a wide range of fascinating talks and posters across the flood forecasting landscape, from both hydrologic and machine learning points of view.

An overview of research areas in flood forecasting addressed in the workshop.
Presentations from the research community included:
Alongside these talks, we presented the various efforts across Google to try and improve flood forecasting and foster collaborations in the field, including:
Additionally, at this workshop we piloted an experimental "ML Consultation" panel, where Googlers Gal Elidan, Sasha Goldshtein and Doron Kukliansky gave advice on how to best use machine learning in several hydrology-related tasks. Finally, we concluded the workshop with a moderated panel on the greatest challenges and opportunities in flood forecasting, with hydrology experts Prof. Paolo Burlando of ETH Zürich, Prof. Dawei Han of the University of Bristol, Dr. Peter Salamon of the Joint Research Centre and Dr. Tyler Erickson of Google Earth Engine.
Flood forecasting is an incredibly important and challenging task that is one part of our larger AI for Social Good efforts. We believe that effective global-scale solutions can be achieved by combining modern techniques with the domain expertise already existing in the field. The workshop was a great first step towards creating much-needed understanding, communication and collaboration between the flood forecasting community and the machine learning community, and we look forward to our continued engagement with the broad research community to tackle this challenge.

Acknowledgements
We would like to thank Avinatan Hassidim, Carla Bromberg, Doron Kukliansky, Efrat Morin, Gal Elidan, Guy Shalev, Jennifer Ye, Nadav Rabani and Sasha Goldshtein for their contributions to making this workshop happen.

Source: Google AI Blog