How to do fast, accurate multi-category classification

Many of today’s most useful AI systems are multilabel classifiers: they map input data into multiple categories at once. An object recognizer, for instance, might classify a given image as containing sky, sea, and boats but not desert or clouds.

Earlier this month, at the International Conference on Machine Learning, my colleagues and I presented a new approach to doing computationally efficient multilabel classification. In tests, we compared our approach to four leading alternatives using three different data sets. On five different performance measures, our system demonstrated improvements across the board.

The need for multilabel classification arises in many different contexts. Originally, it was investigated as a means of doing text classification: a single news article, for instance, might touch on multiple topics. Since then, it’s been used for everything from predicting protein function from raw sequence data to classifying audio files by genre.

The challenge of multilabel classification is to capture dependencies between different labels. If an image features sea, for instance, it’s much more likely to also feature boats than an image that features desert. In principle, the way to capture such dependencies is to learn a joint probability, which represents the likelihood of any combination of probabilities for all labels.

In practice, calculating an accurate joint probability for more than a handful of labels requires an impractically large amount of data. Two years ago, at NeurIPS, my colleagues and I demonstrated that using recurrent neural networks to chain single-label classifiers in sequence was a more computationally efficient way to capture label dependencies. Recurrent neural networks, or RNNs, process sequenced inputs in order, so that the output corresponding to any given input factors in the inputs and outputs that preceded it. RNNs thus automatically consider dependencies.

Our earlier paper, however, assumed that the order in which the classifiers are applied is fixed, regardless of context. Order matters because errors by classifiers early in the chain propagate through subsequent classifications. If the classifier chain erroneously labels an image as containing sea, for instance, it becomes more likely to mislabel it as containing boats.

The way to combat this problem is to move more error-prone classifiers later in the chain. But a given classifier’s propensity for error is relative to its inputs: some classifiers are very reliable for certain types of data but unreliable for others.

Our new approach is to train a system to dynamically vary the order in which the chained classifiers process the inputs, according to features of the input data. This ensures that the classifiers that are most error prone relative to a particular input move to the back of the chain.

In our experiments, we explored two different techniques for doing this. Our first technique used an RNN to generate a sequence of labels for a particular input. Then we excised the erroneous labels while preserving the order of the correct ones. If the resulting sequence omitted any correct labels, we appended them at the end in a random order. This new sequence then became a target output, which we used to re-train the RNN on the same input data.

In this example, the numbers 1–5 represent the correct labels for a single input to a recurrent neural network (RNN). The RNN outputs a sequence of labels, some of which are correct (blue) but most of which are wrong (red). We excise the erroneous labels, preserving the order of the correct ones, and append all the missing labels (green) in a random order. This new sequence serves as a target output for re-training the RNN on the same data.

By preserving the order of the correct labels, we ensure that classifiers later in the chain learn to take advantage of classifications earlier in the chain. Initially, the output of the RNN is entirely random, but it eventually learns to tailor its label sequences to the input data. Note that while the training data is annotated to indicate the true labels, it is not annotated to indicate the ideal sequence of classifications. Hence the need for us to generate new training targets on the fly.

Reinforcement learning is the second technique we used to train an RNN to do dynamic classifier chaining. In reinforcement learning, a machine learning system learns a “policy,” which consists of a set of actions to take under different circumstances. It learns the policy through trial and error, gauging its success according to a “reward function”, which measures how far a selected action takes it toward some predefined goal.

In our case, the actions were simply the applications of labels to the input data, and the reward function measured the accuracy of the classification that resulted from the chain of classifiers.

In tests, we compared our systems to four different baselines. Each adopted a different strategy for determining classifier order. Two chained classifiers according to how common their labels were, the third used an arbitrary but fixed ordering, and the fourth generated a separate arbitrary ordering for each input.

We used five different metrics to evaluate system performance. One considered only the accuracy of the single most probable label, two the accuracies of the three most probable labels, and two the accuracies of the five most probable labels. For the three-label and five-label cases, we used two different evaluation strategies. One measured overall accuracy across labels, while the other assigned greater value to accurate assessments of the first few labels.

Our best-performing system combined the outputs of our two dynamic-chaining algorithms to produce a composite classification. On each of the five metrics, and on three different data sets, that combination outperformed whichever of the four baselines offered the best performance, usually by about 2% to 3% and in one instance by nearly 5%.

Research areas

Related content

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, 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: 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: 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 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 is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, IL, Chicago
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist ILocation: Chicago, IllinoisPosition Responsibilities:Build the core intelligence, insights, and algorithms that support the real estate acquisition strategies for Amazon physical stores. Tackle cutting-edge, complex problems such as predicting the optimal location for new Amazon stores by bringing together numerous data assets, and using best-in-class modeling solutions to extract the most information out of them. Work with business stakeholders, software development engineers, and other data scientists across multiple teams to develop innovative solutions at massive is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, WA, Seattle
Are you motivated to explore research in ambiguous spaces? Are you interested in conducting research that will improve the employee and manager experience at Amazon? Do you want to work on an interdisciplinary team of scientists that collaborate rather than compete? Join us at PXT Central Science!The People eXperience and Technology Central Science Team (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal.We are seeking a senior Applied Scientist with expertise in more than one or more of the following areas: machine learning, natural language processing, computational linguistics, algorithmic fairness, statistical inference, causal modeling, reinforcement learning, Bayesian methods, predictive analytics, decision theory, recommender systems, deep learning, time series modeling. In this role, you will lead and support research efforts within all aspects of the employee lifecycle: from candidate identification to recruiting, to onboarding and talent management, to leadership and development, to finally retention and brand advocacy upon exit.The ideal candidate should have strong problem-solving skills, excellent business acumen, the ability to work independently and collaboratively, and have an expertise in both science and engineering. The ideal candidate is not methods-driven, but driven by the research question at hand; in other words, they will select the appropriate method for the problem, rather than searching for questions to answer with a preferred method. The candidate will need to navigate complex and ambiguous business challenges by asking the right questions, understanding what methodologies to employ, and communicating results to multiple audiences (e.g., technical peers, functional teams, business leaders).About the teamWe are a collegial and multidisciplinary team of researchers in People eXperience and Technology (PXT) that combines the talents of science and engineering to develop innovative solutions to make Amazon Earth's Best Employer. We leverage data and rigorous analysis to help Amazon attract, retain, and develop one of the world’s largest and most talented workforces.
US, WA, Bellevue
Job summaryThe 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 Research 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, Cambridge
Job summaryMULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist IILocation: Cambridge, MassachusettsPosition Responsibilities:Utilize code (Python, R, etc.) to build ML models to solve specific business problems. Build and measure novel online & offline metrics for personal digital assistants and customer scenarios, on diverse devices and endpoints. Research and implement novel machine learning algorithms and models. Collaborate with researchers, software developers, and business leaders to define product requirements and provide modeling solutions. Communicate verbally and in writing to business customers and leadership team with various levels of technical knowledge, educating them about our systems, as well as sharing insights and is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000