Graceful AI

How to make trained systems evolve gracefully.

As machine-learning-based decision systems improve rapidly, we are discovering that it is no longer enough for them to perform well on their own. They should also behave nicely toward their predecessors. When we replace an old trained classifier with a new one, we should expect a smooth transition and a peaceful transfer of decision powers.

Stefano 2.jpg
Stefano Soatto, vice president of applied science for AWS AI.
Credit: Todd Cheney

At Amazon Web Services (AWS), we are constantly working to improve the performance of our learning-based classification systems. Performance is typically measured by average error on test data that are representative of future use cases. We scientists get very excited when we can reduce the average error, and we hope that customers will be delighted when they replace the existing system with a new and improved one. 

However, it is possible for a new model to significantly improve average performance and yet introduce errors that the old model did not make. Those errors can be rare yet so detrimental as to nullify the benefit of the improved model. In some cases, post-processing pipelines built on top of a model can break. In other cases, users are so accustomed to the behavior of the old system that any introduced error contributes to a perceived “regression” in performance.

Regression in model update.png
When updating an old classifier (red) to a new one (dashed blue line), we correct mistakes (top right, white), but we also introduce new ones (negative flips, bottom-left, red). While on average, the errors decrease (from 57% to 42% in this toy example), regression can wreak havoc with downstream processing, nullifying the benefit of the update.
From "Positive-congruent training: Towards regression-free model updates"

You may have experienced this phenomenon when using the search feature in your photo collection. Occasionally, the provider updates the photo management software, presumably improving it. However, if an image that you were able to retrieve previously suddenly goes missing from the search, the natural reaction is surprise: How is this version any better? Give me the old one back!

When the software update occurs, the search feature is usually unavailable for a period of time; the larger your photo collection, the longer the interruption typically lasts. During this time, the system reprocesses old images to create indices and clusters them based on identities. If the model introduces new mistakes, old images may be left out of searches that used to retrieve them.

Which prompts the question, Why is it necessary to reprocess old data? Can we design and train new learning-based models in a manner that is compatible with previous ones, so that it is not necessary to reprocess the entire gallery?

These questions generally pertain to the need to train machine-learning-based systems, not in isolation, but in reference to other models. Specifically, we want the new models to be compatible with classifiers or clustering algorithms designed for the old models, and we want them to not introduce new mistakes. 

Compatible updates

Today, requirements beyond accuracy have begun to drive the machine learning process. These demands include explainability, transparency, fairness, and, now, compatibility and regression minimization. We call the ability to meet those demands “graceful AI”. 

We at AWS first faced this challenge when responding to a customer request to reduce the cost of re-indexing data, which can be significant for large photo collections. 

At the time, there was no literature on the topic. We trained a deep-learning model to minimize the average error while using the “classifier head” of an old model — the last few layers of the model, which issue the final classification decision. In other words, we forced the data representation computed by the new model to live in the same space as the old one, so the same clustering or decision rules could be used without the need to re-index old data. 

Backward-compatible model update.png
Without backward-compatible representation, updating the embedding model for a retrieval/search system means that all previously processed gallery features have to be recomputed by the new model (backfilling), as the new embedding cannot be directly compared with the old one. With a backward-compatible representation, direct comparison becomes possible, eliminating the need to backfill.
From "Towards backward-compatible representation learning"

If this approach worked, customers could start using new models immediately, with no re-indexing time or cost, and the old indexed data could be combined with the new. And it did work, as we described in the paper “Towards backward-compatible representation learning”, presented at last year's Conference on Computer Vision and Pattern Recognition (CVPR). It was the first paper in this increasingly important area of investigation in machine learning, around which we are organizing a tutorial at the upcoming International Conference on Computer Vision (ICCV).

For services that require more complex post-processing than clustering, it is paramount to minimize the number of new errors introduced by model updates. In a forthcoming oral presentation at CVPR, our team will present an approach that we call positive-congruent training, or PC training, which aims to train a new classifier without introducing errors relative to the old one. This is a first step towards regression constrained training. PC training is necessary to avoid rare but harmful mistakes that you wish to never make.

PC training is not just a matter of forcing the new model to mimic the old one — a process known as model distillation. Model distillation mimics the old model, including its errors; we want to be close to the old model only when it gets it right. 

Even when the average error is reduced to a minimum, it is still possible to reduce what we call the “negative flip rate” (NFR), which measures the percentage of new errors compared to the old model. This can be done by trading errors, keeping the average error rate constant (unless the average error rate is precisely zero, which is almost never the case in the real world). So minimizing the NFR is a separate criterion from the standard error rate, and PC training represents a new branch of research in machine learning.

It is possible for a new model to significantly improve average performance and yet introduce errors that the old model did not make. Those errors can be rare yet so detrimental as to nullify the benefit of the improved model.
Stefano Soatto

Machine-learning-based systems will continue to evolve, and eventually we will do away with the artificial separation of training (when the model parameters are learned from a fixed training dataset) and inference (when new data is presented to elicit a decision or action). As we make steps toward such “lifelong learning”, it is important for new models developed in the meantime to play nicely with existing ones. 

We have sown the first seeds of work in this area, but much remains to be done. As models are repeatedly updated, a growing set of compatibility constraints will ultimately weigh negatively on overall performance, much as backward compatibility with all previous versions makes some software so unwieldy. 

We are pleased that some of our models at AWS AI Applications are already backward-compatible, which means that customers will be able to upgrade to new models without having to change their processing pipelines or re-index old data. In 2021, any transfer of decision power should occur without drama. 

Modified models

Another version of the incompatibility problem arises when one wishes to deploy the same system on different devices with diverse resource constraints. One might, for instance, have a large and powerful model running in the cloud and smaller versions of it running on edge devices such as smartphones.

We’ve found that, to ensure compatibility, it’s not enough for the smaller models to approximate the accuracy of the large model; they also need to approximate its architecture. Again at the next CVPR, we will present a paper on “heterogeneous visual search”, which shows how to enforce this type of compatibility across platforms.

Finally, all of the above would be easier if deep neural networks were linear systems, and training consisted of minimizing a convex loss function. As we all know, this is not the case. The niche literature on linearizing deep neural networks has mostly focused on analyzing those networks’ behavior; their performance has been far below that of the full nonlinear, nonconvex originals. 

However, we have recently shown that, if linearization is done right, by modifying the loss function, the model, and the optimization, we can train linear models that perform just as well as their nonlinear counterparts. “LQF: Linear quadratic fine-tuning”, also to be presented at CVPR, describes modifying the architecture of a ResNet backbone by replacing ReLu with leaky ReLu, modifying the loss function from cross-entropy to least-square, and modifying the optimization by preconditioning using Kronecker factorization.

We are excited to continue exploring how these and other developments can lead to more transparent, more interpretable, and more “gracious” AI systems.

Related content

US, WA, Seattle
Note that this posting is for a handful of teams within Amazon Robotics. Teams include: Robotics, Computer Vision, Machine Learning, Optimization, and more.Are you excited about building high-performance robotic systems that can perceive and learn to help deliver for customers? The Amazon Robotics team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.Amazon Robotics is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. We will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. Come join us!A day in the lifeAs an intern you will develop a new algorithm to solve one of the challenging computer vision and manipulation problems in Amazon's robotic warehouses. Your project will fit your academic research experience and interests. You will code and test out your solutions in increasingly realistic scenarios and iterate on the idea with your mentor to find the best solution to the problem.
US, WA, Bellevue
The Global Supply Chain-ACES organization aims to raise the bar on Amazon’s customer experience by delivering holistic solutions for Global Customer Fulfillment that facilitate the effective and efficient movement of product through our supply chain. We develop strategies, processes, material handling and technology solutions, reporting and other mechanisms, which are simple, technology enabled, globally scalable, and locally relevant. We achieve this through cross-functional partnerships, listening to the needs of our customers and prioritizing initiatives to deliver maximum impact across the value chain. Within the organization, our Quality team balances tactical operation with operations partners with global engagement on programs to deliver improved inventory accuracy in our network. The organization is looking for an experienced Principal Data Scientist to partner with senior leadership to develop long term strategic solutions. As a Principal Scientist, they will lead critical initiatives for Global Supply Chain, leveraging complex data analysis and visualization to:a. Collaborate with business teams to define data requirements and processes;b. Automate data pipelines;c. Design, develop, and maintain scalable (automated) reports and dashboards that track progress towards plans;d. Define, track and report program success metrics.e. Serve as a technical science lead on our most demanding, cross-functional projects.
US, MA, North Reading
Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart team of doers that work passionately to apply cutting edge advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even imagine yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. The Research Science team at Amazon Robotics is seeking interns with a passion for robotic research to work on cutting edge algorithms for robotics. Our team works on challenging and high-impact projects, including allocating resources to complete a million orders a day, coordinating the motion of thousands of robots, autonomous navigation in warehouses, and learning how to grasp all the products Amazon sells. We are seeking internship candidates with backgrounds in computer vision, machine learning, resource allocation, discrete optimization, search, planning/scheduling, and reinforcement learning. As an intern you will develop a new algorithm to solve one of the challenging computer vision and manipulation problems in Amazon's robotic warehouses. Your project will fit your academic research experience and interests. You will code and test out your solutions in increasingly realistic scenarios and iterate on the idea with your mentor to find the best solution to the problem.
US, WA, Seattle
Are you excited about building high-performance robotic systems that can perceive, learn, and act intelligently alongside humans? The Robotics AI team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.The Amazon Robotics team is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. Come join us!
US, WA, Bellevue
Employer: Amazon.com Services LLCPosition: Research Scientist IILocation: Bellevue, WA Multiple Positions Available1. Research, build and implement highly effective and innovative methods in Statistical Modeling, Machine Learning, and other quantitative techniques such as operational research and optimization to deliver algorithms that solve real business problems.2. Take initiative to scope and plan research projects based on roadmap of business owners and enable data-driven solutions. Participate in shaping roadmap for the research team.3. Ensure data quality throughout all stages of acquisition and processing of the data, including such areas as data sourcing/collection, ground truth generation, data analysis, experiment, evaluation and visualization etc.4. Navigate a variety of data sources, understand the business reality behind large-scale data and develop meaningful science solutions.5. Partner closely with product or/and program owners, as well as scientists and engineers in cross-functional teams with a clear path to business impact and deliver on demanding projects.6. Present proposals and results in a clear manner backed by data and coupled with conclusions to business customers and leadership team with various levels of technical knowledge, educating them about underlying systems, as well as sharing insights.7. Perform experiments to validate the feature additions as requested by domain expert teams.8. Some telecommuting benefits available.The pay range for this position in Bellevue, WA is $136,000-$184,000 (yr); however, base pay offered may vary depending on job-related knowledge, skills, and experience. A sign-on bonus and restricted stock units may be provided as part of the compensation package, in addition to a full range of medical, financial, and/or other benefits, dependent on the position offered. This information is provided by the Washington Equal Pay Act. Base pay information is based on market location. Applicants should apply via Amazon's internal or external careers site.#0000
US, VA, Arlington
The 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. As Director for PXT Central Science Technology, you will be responsible for leading multiple teams through rapidly evolving complex demands and define, develop, deliver and execute on our science roadmap and vision. You will provide thought leadership to scientists and engineers to invent and implement scalable machine learning recommendations and data driven algorithms supporting flexible UI frameworks. You will manage and be responsible for delivering some of our most strategic technical initiatives. You will design, develop and operate new, highly scalable software systems that support Amazon’s efforts to be Earth’s Best Employer and have a significant impact on Amazon’s commitment to our employees and communities where we both serve and employ 1.3 million Amazonians. As Director of Applied Science, you will be part of the larger technical leadership community at Amazon. This community forms the backbone of the company, plays a critical role in the broad business planning, works closely with senior executives to develop business targets and resource requirements, influences our long-term technical and business strategy, helps hire and develop engineering leaders and developers, and ultimately enables us to deliver engineering innovations.This role is posted for Arlington, VA, but we are flexible on location at many of our offices in the US and Canada.
US, VA, Arlington
Employer: Amazon.com Services LLCPosition: Data Scientist IILocation: Arlington, VAMultiple Positions Available1. Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.2. Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.3. Leverage big data to explore and introduce areas of analytics and technologies.4. Analyze data to identify opportunities to impact populations.5. Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.6. Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.7. Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.8. Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools. #0000
US, TX, Dallas
Employer: Amazon.com Services LLCPosition: Data Scientist II (multiple positions available)Location: Dallas, TX Multiple Positions Available:1. Assist customers to deliver Machine Learning (ML) and Deep Learning (DL) projects from beginning to end, by aggregating data, exploring data, building and validating predictive models, and deploying completed models to deliver business impact to the organization;2. Apply understanding of the customer’s business need and guide them to a solution using AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances;3. Use Deep Learning frameworks like MXNet, PyTorch, Caffe 2, Tensorflow, Theano, CNTK, and Keras to help our customers build DL models;4. Research, design, implement and evaluate novel computer vision algorithms and ML/DL algorithms;5. Work with data architects and engineers to analyze, extract, normalize, and label relevant data;6. Work with DevOps engineers to help customers operationalize models after they are built;7. Assist customers with identifying model drift and retraining models;8. Research and implement novel ML and DL approaches, including using FPGA;9. Develop computer vision and machine learning methods and algorithms to address real-world customer use-cases; and10. Design and run experiments, research new algorithms, and work closely with engineers to put algorithms and models into practice to help solve customers' most challenging problems.11. Approximately 15% domestic and international travel required.12. Telecommuting benefits are available.#0000
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Manager III, Data ScienceLocation: Bellevue, WashingtonPosition Responsibilities:Manage a team of data scientists working to build large-scale, technical solutions to increase effectiveness of Amazon Fulfillment systems. Define key business goals and map them to the success of technical solutions. Aggregate, analyze and model data from multiple sources to inform business decisions. Manage and quantify improvement in the customer experience resulting from research outcomes. Develop and manage a long-term research vision and portfolio of research initiatives, with algorithms and models that to be integrated in production systems. Hire and mentor junior scientists.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, VA, Arlington
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist IILocation: Arlington, VirginiaPosition Responsibilities:Design and implement scalable and reliable approaches to support or automate decision making throughout the business. Apply a range of data science techniques and tools combined with subject matter expertise to solve difficult business problems and cases in which the solution approach is unclear. Acquire data by building the necessary SQL / ETL queries. Import processes through various company specific interfaces for accessing Oracle, RedShift, and Spark storage systems. Build relationships with stakeholders and counterparts. Analyze data for trends and input validity by inspecting univariate distributions, exploring bivariate relationships, constructing appropriate transformations, and tracking down the source and meaning of anomalies. Build models using statistical modeling, mathematical modeling, econometric modeling, network modeling, social network modeling, natural language processing, machine learning algorithms, genetic algorithms, and neural networks. Validate models against alternative approaches, expected and observed outcome, and other business defined key performance indicators. Implement models that comply with evaluations of the computational demands, accuracy, and reliability of the relevant ETL processes at various stages of production.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000