Learning computational tasks from single examples

New “meta-learning” approach improves on the state of the art in “one-shot” learning.

In the past decade, deep-learning systems have proven remarkably successful at many artificial-intelligence tasks, but their applications tend to be narrow. A computer vision system trained to recognize cats and dogs, for instance, would need significant retraining to start recognizing sharks and sea turtles.

Meta-learning is a paradigm intended to turn machine learning systems into generalists. A meta-learning model is trained on a range of related tasks, but it learns not only how to perform those tasks but also how to learn to perform them. The idea is that it could then be adapted to new tasks with only a handful of labeled training examples, drastically reducing the need for labor-intensive data annotation.

At the (virtual) International Conference on Learning Representations, we will present an approach that improves performance on meta-learning tasks without increasing the data annotation requirements. The key idea is to adapt the meta-learning procedure so that it can leverage small sets of unlabeled data, in addition to the traditional labeled examples.

Meta-learning
In meta-learning, a machine learning model learns how to learn. During meta-training, the model is trained on a group of related tasks — using data from “support sets” — and tested using data from “query sets”. But the query sets are labeled, so the model can assess how effectively it's learning. During meta-testing, the model is again trained on a group of support sets, but it's evaluated on its ability to classify unlabeled query data.
Stacy Reilly

The intuition is that even without labels, these extra data still contain a lot of useful information. Suppose, for instance, that a meta-learning system trained on images of terrestrial animals (such as cats and dogs) is being adapted to recognize aquatic animals. Unlabeled images of aquatic animals (i.e., images that don’t indicate whether an animal is a shark or a sea turtle) still tell the model something about the learning task, such as the lighting conditions and background colors typical of underwater photos.

In experiments, we compared models trained through our approach to 16 different baselines on an object recognition meta-learning task. We found that our approach improved performance on one-shot learning, or learning a new object classification task from only a single labeled example, by 11% to 16%, depending on the architectures of the underlying neural networks.

Meta-learning

In conventional machine learning, a model is fed a body of labeled data and learns to correlate data features with the labels. Then it’s fed a separate body of test data and evaluated on how well it predicts the labels for that data. For evaluation purposes, the system designers have access to the test-data labels, but the model itself doesn’t.

Meta-learning adds another layer of complexity. During meta-training — the analogue of conventional training — the model learns to perform a range of related tasks. Each task has its own sets of training data and test data, and the model sees both. That is, part of its meta-training is learning how particular ways of responding to training data tend to affect its performance on test data.

During meta-testing, it is again trained on a range of tasks. These are related to but not identical to the tasks it saw during meta-training — recognizing aquatic animals, for instance, as opposed to terrestrial animals. Again, for each task, the model sees both training data and test data. But whereas, during meta-training, the test data were labeled, during meta-testing, the labels are unknown and must be predicted.

The terminology can get a bit confusing, so meta-learning researchers typically refer to the meta-learning “training” sets as support sets and the meta-learning “test” sets as query sets. During meta-training, the learning algorithm has access to the labels for both the support sets and the query sets, and it uses them to produce a global model. During meta-testing, it has access only to the labels for the support sets, which it uses to adapt the global model to each of the new tasks.

Our approach has two key innovations. First, during meta-training, we do not learn a single global model. Instead, we train an auxiliary neural network to produce a local model for each task, based on the corresponding support set. Second and more important, during meta-training we also train a second auxiliary network to leverage the unlabeled data of the query sets. Then, during meta-testing, we can use the query sets to fine-tune the local models, improving performance.

Leveraging unlabeled data

A machine learning system is governed by a set of parameters, and in meta-learning, meta-training optimizes them for a particular family of tasks — such as recognizing animals. During meta-testing or operational deployment, the model uses a handful of training examples to optimize those parameters for a new task.

A particular set of parameter values defines a point in a multidimensional space, and adaptation to a new task can be thought of as searching the space for the point representing the optimal new settings.

Meta-learning parameter space
In traditional meta-learning (left), the result of training is a model (φ) that can be adapted to a new set of related tasks (1 – 4). Adaptation involves searching for the optimal settings 1 – θ4) of the model parameters, based on a small set of labeled data (dl1 – dl4). Our system (right), by contrast, uses the labeled data and the available unlabeled data (x1 – x4) to better approximate those settings.

A traditional meta-learning system might begin its search at the point defined by the global model (φ in the figure above); this is the initialization step. Then, using the labeled data of the support set, it would work its way toward the settings that correspond to the new task; this is the adaptation step.

With our approach, by contrast, the initialization network selects a starting search location on the basis of the data in the support set 01(dl1) – θ04(dl4) in the figure above). Then it works its way toward the optimal settings using the unlabeled data of the query set (x1 – x4, above). More precisely, the second auxiliary neural network estimates the gradient implied by the query set data.

In the same way that the parameter settings of a machine learning model can be interpreted as a point in a representational space, so can the parameter settings and the resulting error rate on a particular data set. The multidimensional graph that results is like a topological map, with depressions that represent low error rates and peaks that represent high error rates. In this context, machine learning is a matter of identifying the slope of a depression — a gradient — and moving down it, toward a region of low error.

This is how many machine learning systems learn, but typically, they have the advantage of knowing, from training data labels, what the true error rate is for a given set of system parameters. In our case, because we’re relying on the unlabeled query set data, we can only guess at the true gradients.

That’s where the second auxiliary neural network comes in: it infers gradients from query set data. The system as a whole then uses the inferred gradients to fine-tune the initial parameter settings supplied by the first neural network.

The approach can be explained and justified through connections to two topics in theoretical machine learning, namely empirical Bayes and information bottleneck. These theoretical developments are beyond the scope of this blog post, but the interested reader can consult the full manuscript.

The associated software code has also been open-sourced as part of the Xfer repository.

Although our system beat all 16 baselines on the task of one-shot learning, there were several baseline systems that outperformed it on five-shot learning, or learning with five examples per new task. The approaches used by those baselines are complementary to our approach, and we believe that combining approaches could yield even lower error rates. Going forward, that’s one of several extensions of this work that we will be pursuing.

Research areas
About the Author
Pablo Garcia Moreno is an applied scientist in the Alexa Shopping organization.
About the Author
Andreas Damianou is a senior applied scientist in the Alexa Shopping organization.

Related content

US, WA, Seattle
Job summaryWW Installments is one of the fastest growing businesses within Amazon and we are looking for an Economist to join the team. This group has been entrusted with a massive charter that will impact every customer that visits Amazon.com. We are building the next generation of features and payment products that maximize customer enablement in a simple, transparent, and customer obsessed way. Through these products, we will deliver value directly to Amazon customers improving the shopping experience for hundreds of millions of customers worldwide. Our mission is to delight our customers by building payment experiences and financial services that are trusted, valued, and easy to use from anywhere in any way.Economists at Amazon are solving some of the most challenging applied economics questions in the tech sector. Amazon economists apply the frontier of economic thinking to market design, pricing, forecasting, program evaluation, online advertising and other areas. Our economists build econometric models using our world class data systems, and apply economic theory to solve business problems in a fast-moving environment. A career at Amazon affords economists the opportunity to work with data of unparalleled quality, apply rigorous applied econometric approaches, and work with some of the most talented applied econometricians in the trade.As the Economist within WW Installments, you will be responsible for building long-term causal inference models and experiments. These analysis represent a core capability for WW Installments and businesses across Amazon. Your work will directly impact customers by influencing how objective functions are designed and which inputs are consumed for modeling. You will work across functions including machine learning, business intelligence, data engineering, software development, and finance to induce data driven decisions at every level of the organization.Key job responsibilitiesThis role will be responsible for:• Developing a causal inference and experimentation roadmap for the WW Installments Competitive Pricing team.• Apply expertise in causal and econometric modeling to develop large-scale systems that are deployed across Amazon businesses.• Identify business opportunities, define and execute modeling approach, then deliver outcomes to various Amazon businesses with an Amazon-wide perspective for solutions.• Lead the project plan from a scientific perspective on product launches including identifying potential risks, key milestones, and paths to mitigate risks• Own key inputs to reports consumed by VPs and Directors across Amazon.• Identifying new opportunities to influence business strategy and product vision using causal inference.• Continually improve the WW Installments experimentation roadmap automating and simplifying whenever possible.• Coordinate support across engineers, scientists, and stakeholders to deliver analytical projects and build proof of concept applications.• Work through significant business and technical ambiguity delivering on analytics roadmap across the team with autonomy.
US, WA, Seattle
Job summaryWW Installments is one of the fastest growing businesses within Amazon and we are looking for an Applied Scientist to join the team. This group has been entrusted with a massive charter that will impact every customer that visits Amazon.com. We are building the next generation of features and payment products that maximize customer enablement in a simple, transparent, and customer obsessed way. Through these products, we will deliver value directly to Amazon customers improving the shopping experience for hundreds of millions of customers worldwide. Our mission is to delight our customers by building payment experiences and financial services that are trusted, valued, and easy to use from anywhere in any way.As an Applied Scientist within WW Installments, you will be responsible for building machine learning models and pipelines with direct customer impact. These models represent a core capability for WW Installments and businesses across Amazon. Your work will directly impact customers by influencing how they interact with financing options to make purchases. You will work across functions including data engineering, software development, and business to induce data driven decisions at every level of the organization.Key job responsibilitiesThis role will be responsible for:• Developing production machine learning models and pipelines for the WW Installments Competitive Pricing team that directly impact customers.• Apply expertise in machine learning to develop large-scale production systems that are deployed across Amazon businesses.• Identify business opportunities, define and execute modeling approach, then deliver outcomes to various Amazon businesses with an Amazon-wide perspective for solutions.• Lead the implementation of production ML from a scientific perspective including identifying potential risks, key milestones, and paths to mitigate risks.• Identifying new opportunities to influence business strategy and product vision using data science and machine learning.• Continually improve the WW Installments ML roadmap automating and simplifying whenever possible.• Coordinate support across engineers, scientists, and stakeholders to deliver ML pipelines, analytics projects, and build proof of concept applications.• Work through significant business and technical ambiguity delivering on analytics roadmap across the team with autonomy.
US, WA, Seattle
Job summaryWW Installments is one of the fastest growing businesses within Amazon and we are looking for a Data Scientist to join the team. This group has been entrusted with a massive charter that will impact every customer that visits Amazon.com. We are building the next generation of features and payment products that maximize customer enablement in a simple, transparent, and customer obsessed way. Through these products, we will deliver value directly to Amazon customers improving the shopping experience for hundreds of millions of customers worldwide. Our mission is to delight our customers by building payment experiences and financial services that are trusted, valued, and easy to use from anywhere in any way.As a Data Scientist within WW Installments, you will be responsible for building machine learning models and pipelines with direct customer impact. These models represent a core capability for WW Installments and businesses across Amazon. Your work will directly impact customers by influencing how they interact with financing options to make purchases. You will work across functions including data engineering, software development, and business to induce data driven decisions at every level of the organization.Key job responsibilitiesThis role will be responsible for:• Developing machine learning models and pipelines for the WW Installments Competitive Pricing team.• Apply expertise in machine learning to develop large-scale systems that are deployed across Amazon businesses.• Identify business opportunities, define and execute modeling approach, then deliver outcomes to various Amazon businesses with an Amazon-wide perspective for solutions.• Lead the project plan from a scientific perspective on product launches including identifying potential risks, key milestones, and paths to mitigate risks.• Own key inputs to reports consumed by VPs and Directors across Amazon.• Identifying new opportunities to influence business strategy and product vision using data science and machine learning.• Continually improve the WW Installments ML roadmap automating and simplifying whenever possible.• Coordinate support across engineers, scientists, and stakeholders to deliver ML pipelines, analytics projects, and build proof of concept applications.• Work through significant business and technical ambiguity delivering on analytics roadmap across the team with autonomy.
US, CA, San Diego
Job summaryPrivate Brands is fast-growing within Amazon, and is a highly visible, emerging business. We have a unique business and obsess over quality and building global brands our customers love. We aspire to be part of our customers’ everyday lives by offering them unique products at compelling prices backed by Amazon’s strong customer obsessed reputation.Private Brands Intelligence (PBI) is looking for a Data Scientist to join our team in building Machine Learning solutions at scale. PBI applies Machine Learning, Causal Inference, and Econometrics/Economics to derive actionable insights about the complex economy of Amazon’s retail business. We also develop statistical models and algorithms to drive strategic business decisions and improve operations. We are an interdisciplinary team of Economists, Scientists, and Engineers incubating and building Day One solutions using cutting-edge technology, to solve some of the toughest business problems at Amazon.You will work with business leaders, scientists, economists, and engineers to translate business and functional requirements into concrete deliverables, including the design, development, testing, and deployment of highly scalable distributed services. You will partner with scientists, economists, and engineers to help invent and implement scalable ML and econometric models while building tools to help our customers gain and apply insights.This is a unique, high visibility opportunity for someone who wants to have business impact, dive deep into large-scale economic problems, enable measurable actions on the Consumer economy, and work closely with scientists and economists. We are particularly interested in candidates with experience building predictive models and working with distributed systems.As a Data Scientist, you bring business and industry context to science and technology decisions. You set the standard for scientific excellence and make decisions that affect the way we build and integrate algorithms. Your solutions are exemplary in terms of algorithm design, clarity, model structure, efficiency, and extensibility. You tackle intrinsically hard problems, acquiring expertise as needed. You decompose complex problems into straightforward solutions.
US, VA, Arlington
Job summaryThis role will sit in our new headquarters in Northern Virginia, where Amazon will invest $2.5 billion dollars, occupy 4 million square feet of energy efficient office space, and create at least 25,000 new full-time jobs.The AWS Infrastructure Data Center Planning and Delivery (DCPD) Data Science team owns supply chain management activities at a global scale.We consolidate usage and supply chain health data and forecasts at a variety of horizons to ensure that we have the right strategic lens associated with each decision we make.We identify gaps to ensure that the AWS business is able to support any and all customers who want to capitalize on the scalability, flexibility, and cost-efficiency of AWS. Our actions and decisions decide the where, how, and what will make it into each of our data centers and we need you to help us to make those decisions and clearly explain the why.The Business Insights and Optimization (BIO) team owns data science, engineering, and business intelligence solutions feeding this team.We identify gaps in our capacity planning and delivery mechanisms and design/build systems which will fix those gaps.We are end to end data product owners and the analysis, models we produce drives billions of dollars of decisions annually.Data Scientists on this team have end to end range and capabilities.They work directly with business owners to understand how they use data to drive their business.They design modeling frameworks to dive deep into these raw sources of information to get the most out of the data they have.They work directly with data engineers to build automated pipelines and production scale information systems and models.They build automated tools which will allow their results to be shared with the business at scale.They align with business owners to continuously track their work to ensure maximum impact from their projects.They monitor performance of their work to evaluate whether improvements are needed after tracking has started in production.
US, CA, Sunnyvale
Job summaryAmong the goals of the Alexa Devices AI team, is to make Alexa the most knowledgeable and trusted ally for notifications, annoucements, pickup services and voice assistance while on the go.Key job responsibilities1. As an Applied Scientist on our team you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art NLU (Natural language understanding) developments.2. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to traing Machine Learning models for their application in NLU.3. This role requires a pragmatic technical leader comfortable with ambiguity, capable of summarizing complex data and models through clear visual and written explanations.4. The ideal candidate will have experience with machine learning models and their application in AI systems. We are particularly interested in experience applying natural language processing, deep learning at scale. Additionally, we are seeking candidates with strong interest in data/research sciences and engineering, creativity, curiosity, and great judgment.5. You will interact with various stake holders: product leaders, program managers, other domain managers and developers on regular basis for requirement collections, deliveries, and other related communication6. You will help attract and recruit technical talentA day in the lifeApplied Scientist will help develop novel algorithms and apply modeling techniques to advance the state of the art in spoken language understanding (SLU) and to improve the customer experience in engaging with Alexa.About the teamThe Alexa Devices AI science team's work directly impacts the experience and engagement of customers who rely on Alexa while in-the-car, on-the-go and at-home.
US, VA, Arlington
Job summaryThe Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal.We are looking for an economist with expertise in applying causal inference, experimental design, or causal machine learning techniques to topics in labor, personnel, education, health, public, or behavioral economics. We are particularly interested in candidates with experience applying these skills to strategic problems with significant business and/or social policy impact.Candidates will work with economists and engineers to estimate and validate their models on large scale data, and will help business partners turn the results of their analysis into policies, programs, and actions that have a major impact on Amazon’s business and its workforce. We are looking for creative thinkers who can combine a strong economic toolbox with a desire to learn from others, and who know how to execute and deliver on big ideas.Ideal candidates will own key inputs to all stages of research projects, including model development, survey administration, experimental design, and data analysis. They will be customer-centric, working closely with business partners to define key research questions, communicate scientific approaches and findings, listen to and incorporate partner feedback, and deliver successful solutions.
US, CA, Palo Alto
Job summaryAmazon is the 4th most popular site in the US (http://www.alexa.com/topsites/countries/US). Our product search engine is one of the most heavily used services in the world, indexes billions of products, and serves hundreds of millions of customers world-wide. We are working on a new AI-first initiative to re-architect and reinvent the way we do search through the use of extremely large scale next-generation deep learning techniques. Our goal is to make step function improvements in the use of advanced Machine Learning (ML) on very large scale datasets, specifically through the use of aggressive systems engineering and hardware accelerators. This is a rare opportunity to develop cutting edge ML solutions and apply them to a problem of this magnitude. Some exciting questions that we expect to answer over the next few years include:· Can a focus on compilers and custom hardware help us accelerate model training and reduce hardware costs?· Can combining supervised multi-task training with unsupervised training help us to improve model accuracy?· Can we transfer our knowledge of the customer to every language and every locale ? The Search Science team is looking for a Senior Applied Science Manager to drive roadmap on making large business impact through application of Deep Learning models via close collaboration with partner teams. The team also has a focus on technology solution for deep-learning based embedding generation, sensitive data ingestion and applications, data quality measurement, improvement, data bias identification and reduction to achieve model fairness.Success in this role will require the courage to chart a new course. You will manage your own team to understand all aspects of the customer journey. You and your team will inform other scientists and engineers by providing insights and building models to help improving training data quality and reducing bias. The research focus includes but not limited to Natural Language Processing, recommendation, applications relevant to Amazon buyers, sellers and more. You will be working with cutting edge technologies that enable big data and parallelizable algorithms. You will play an active role in translating business and functional requirements into concrete deliverables and working closely with software development teams to put solutions into production.
US, WA, Seattle
Job summaryAmazon EC2 provides cloud computing which forms the foundation for the majority of AWS services, as well as a large portion of compute use cases for businesses and individuals around the world. A critical factor in the continued success of EC2 is the ability to provide reliable and cost effective computing. The EC2 Fleet Health and Lifecycle (EC2 FHL) organization is responsible for ensuring that the global EC2 server fleet continues to raise the bar for reliability, security, and efficiency. We are looking for seasoned engineering leaders with passion for technology and an entrepreneurial mindset. At Amazon, it is all about working hard, having fun and making history. If you are ready to make history, we want to hear from you!Come join a brand new team, EC2 Health Analytics, under EC2 Foundational Technology, to solve complex cutting-edge problems to power a faster, more robust and performant EC2 of tomorrow. The charter of our team is to improve customer experience on the EC2 fleet by analyzing hundreds of signals and driving next-generation detection and remediation tools. We apply Machine Learning to predict outcomes and optimize decisions that improve customer experience and operational efficiency. As an Applied Scientist in the EC2 Health Analytics team, you will join an industry-leading engineering team solving challenging problems at massive scale.· Build a world-class forecasting platform that scales to handling billions of time series data in real time.· Drive fleet utilization improvement where each 1% means tens of millions of additional free cash flow.· Automate tactical and strategic capacity planning tools to optimize for service availability and infrastructure cost.· Build recommendation algorithms for improving the AWS customer experience.· · Reduce dependence on manual troubleshooting for deep-dives.What you will learn:· State-of-the-art analytics and forecasting methodologies.· Application of machine learning to large-scale data sets.· · Product recommendation algorithms.· Resource management and admission control for the Cloud.· The internals of all AWS services.Inclusive Team CultureHere at AWS, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences.Work/Life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, CA, Palo Alto
Job summaryThe Amazon Search team creates powerful, customer-focused search and advertising solutions and technologies. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, the Amazon Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. Our team works to maximize the quality and effectiveness of the search experience for visitors to Amazon websites worldwide.