Even though supervised learning using large annotated corpora is still the dominant approach in machine learning, self-supervised learning is gaining considerable popularity. Applying self-supervised learning to audio and speech sequences, however, remains particularly challenging. Speech signals, in fact, are not only high-dimensional, long, and variable-length sequences, but also entail a complex hierarchical structure that is difficult to infer without supervision (e.g.phonemes, syllables, words). Moreover, speech is characterized by an important variability due to different speaker identities, accents, recording conditions and noises that highly increase the level of complexity.

We believe that self-supervised learning will play a crucial role in the future of artificial intelligence, and we think that great research effort is needed to efficiently take advantage of it in audio and speech applications. With our initiative, we wish to foster more progress in the field, and we hope to encourage a discussion amongst experts and practitioners from both academia and industry that might bring different points of view on this topic. Furthermore, we plan to extend the debate to multiple disciplines, encouraging discussions on how insights from other fields (e.g., computer vision and robotics) can be applied to speech, and how findings on speech can be used on other sequence processing tasks. The workshop will be conceived to promote communication and exchange of ideas between machine learning and speech communities. Throughout a series of invited talks, contributed presentations, poster sessions, as well as a panel discussion we want to foster a fruitful scientific discussion that cannot be done with that level of detail during the main ICML conference.

This workshop will bring together artificial intelligence (AI) researchers who study the interpretability of AI systems, develop interpretable machine learning algorithms, and develop methodology to interpret black-box machine learning models (e.g., post-hoc interpretations). This is a very exciting time to study interpretable machine learning, as the advances in large-scale optimization and Bayesian inference that have enabled the rise of black-box machine learning are now also starting to be exploited to develop principled approaches to large-scale interpretable machine learning. Interpretability also forms a key bridge between machine learning and other AI research directions such as machine reasoning and planning. Participants in the workshop will exchange ideas on these and allied topics.

Description: the workshop proposal in “Law and Machine Learning” aims to contribute to the research on social and legal risks of the deployment of AI systems using machine learning based decisions. Today, algorithms have been infiltrating and governing every aspect of our lives as individuals and as a society. Specifically, Algorithmic Decision Systems (ADS) are involved in many social decisions. For instance, such systems are increasingly used to support decision-making in fields, such as child welfare, criminal justice, school assignment, teacher evaluation, fire risk assessment, homelessness prioritization, healthcare, Medicaid benefit, immigration decision systems or risk assessment, and predictive policing, among other things. Law enforcement agencies are increasingly using facial recognition, algorithmic predictive policing systems to forecast criminal activity and allocate police resources. However, these predictive systems challenge fundamental rights and guarantees of the criminal procedure. For several years, numerous studies have revealed, social risks of ML, especially the risks of opacity, bias, manipulation of information.

While it is only the starting point of the deployment of such systems, more interdisciplinary research is needed. Our purpose is to contribute to this new field which brings together legal researchers, mathematicians and computer scientists, by bridging the gap between the performance of algorithmic systems and legal standards. For instance, notions like “privacy” or “fairness” are formulated in law, as well as mathematical definitions in computer science. However, the meaning and the impact of such requirements are not necessarily identical. Besides, legal norms to regulate AI systems appear in certain national laws but have to be relevant and compatible with technical requirements. Furthermore, these standards must be checked by legal experts and regulators, which presupposes that AI systems are sufficiently meaningful and transparent. These issues emerge in different topics, such as privacy in data analysis and fairness in algorithmic decision-making. The topic will cover the research that denounces the risks and, above all, multidisciplinary research that proposes solutions, especially legal and technical solutions.

Analysis of large amounts of data offers new opportunities to understand many processes better. Yet, data accumulation often implies relaxing acquisition procedures or compounding diverse sources, leading to many observations with missing features. From questionnaires to collaborative filtering, from electronic health records to single-cell analysis, missingness is everywhere at play and is rather the norm than the exception. Even “clean” data sets are often barely “cleaned” versions of incomplete data sets—with all the unfortunate biases this cleaning process may have created.

Despite this ubiquity, tackling missing values is often overlooked. Handling missing values poses many challenges, and there is a vast literature in the statistical community, with many implementations available. Yet, there are still many open issues and the need to design new methods or to introduce new point of views: for missing values in a supervised-learning setting, in deep learning architectures, to adapt available methods for high dimensional observed data with different type of missing values, deal with feature mismatch and distribution mismatch. Missing data is one of the eight pillars of causal wisdom for Judea Pearl who brought graphical model reasoning to tackle some missing not at random values.

To the best of our knowledge, this is the first workshop at the major machine learning conferences focusing primarily on missing value problems in recent years. The goal of our workshop is to give more momentum and exposition to research on missing values, both theoretical and methodological, and emphasize the connections with other areas of machine learning (e.g. causal inference, generative modelling, uncertainty quantification, transfer learning, distributional shift, etc.). We will also attach importance to discussing the reproducibility problems that can be caused by missing data, the danger of forgetting the missing values issues and the importance of providing sound implementations.

We welcome both academic and industrial practitioners/researchers. In particular, since missing data is a critical issue in many applications, we would like to federate industrial/applied know-how and various academic approaches.

A person’s health is determined by a variety of factors beyond those captured by electronic health records or the genome. Many healthcare organizations recognize the importance of the social determinants of health (SDH) such as socioeconomic status, employment, food security, education, and community cohesion. Capturing such comprehensive portraits of patient data is necessary to transform a healthcare system and improve population health while simultaneously delivering personalized healthcare provisions. Machine learning (ML) is well-positioned to transform system-level healthcare through the design of intelligent algorithms that incorporate SDH into clinical and policy interventions, such as population health programs and clinical decision support systems. Innovations in health-tech through wearable devices and mobile health, among others, provide rich sources of data, including those characterizing SDH. The guiding metric of success should be health outcomes: the improvement of health and care at both the individual and population levels. This workshop will identify the needs of system-level healthcare transformation that ML may satisfy. We will bring together ML researchers, health policy practitioners, clinical organization experts, and individuals from all areas of clinic-, hospital-, and community-based healthcare.

Until recently, Machine Learning has been mostly applied in industry by consulting academics, data scientists within larger companies, and a number of dedicated Machine Learning research labs within a few of the world’s most innovative tech companies. Over the last few years we have seen the dramatic rise of companies dedicated to providing Machine Learning software-as-a-service tools, with the aim of democratizing access to the benefits of Machine Learning. All these efforts have revealed major hurdles to ensuring the continual delivery of good performance from deployed Machine Learning systems. These hurdles range from challenges in MLOps, to fundamental problems with deploying certain algorithms, to solving the legal issues surrounding the ethics involved in letting algorithms make decisions for your business.

This workshop will invite papers related to the challenges in deploying and monitoring ML systems. It will encourage submission on: subjects related to MLOps for deployed ML systems (such as testing ML systems, debugging ML systems, monitoring ML systems, debugging ML Models, deploying ML at scale); subjects related to the ethics around deploying ML systems (such as ensuring fairness, trust and transparency of ML systems, providing privacy and security on ML Systems); useful tools and programming languages for deploying ML systems; specific challenges relating to deploying reinforcement learning in ML systems
and performing continual learning and providing continual delivery in ML systems;
and finally data challenges for deployed ML systems.

Self-driving cars and advanced safety features present one of today’s greatest challenges and opportunities for Artificial Intelligence (AI). Despite billions of dollars of investments and encouraging progress under certain operational constraints, there are no driverless cars on public roads today without human safety drivers. Autonomous Driving research spans a wide spectrum, from modular architectures -- composed of hardcoded or independently learned sub-systems -- to end-to-end deep networks with a single model from sensors to controls. In any system, Machine Learning is a key component. However, there are formidable learning challenges due to safety constraints, the need for large-scale manual labeling, and the complex high dimensional structure of driving data, whether inputs (from cameras, HD maps, inertial measurement units, wheel encoders, LiDAR, radar, etc.) or predictions (e.g., world state representations, behavior models, trajectory forecasts, plans, controls). The goal of this workshop is to explore the frontier of learning approaches for safe, robust, and efficient Autonomous Driving (AD) at scale. The workshop will span both theoretical frameworks and practical issues especially in the area of deep learning.

Website: https://sites.google.com/view/aiad2020

The ICML Workshop on Retrospectives in Machine Learning will build upon the success of the 2019 NeurIPS Retrospectives workshop to further encourage the publication of retrospectives. A retrospective of a paper or a set of papers, by its author, takes the form of an informal paper. It provides a venue for authors to reflect on their previous publications, to talk about how their thoughts have changed following publication, to identify shortcomings in their analysis or results, and to discuss resulting extensions. The overarching goal of MLRetrospectives is to improve the science, openness, and accessibility of the machine learning field, by widening what is publishable and helping to identify opportunities for improvement. Retrospectives also give researchers and practitioners unable to attend conferences access to the author’s updated understanding of their work, which would otherwise only be accessible to their immediate circle. The machine learning community would benefit from retrospectives on much of the research which shapes our field, and this workshop will present an opportunity for a few retrospectives to be presented.

The workshop will showcase recent research in the field of Computational Biology. Computational biology is an interdisciplinary field that develops and applies analytical methods, mathematical and statistical modeling and simulation to analyze and interpret vast collections of biological data, such as genetic sequences, cellular features or protein structures, and imaging datasets to make new predictions towards clinical response, discover new biology or aid drug discovery. The availability of high-dimensional data, at multiple spatial and temporal resolutions has made machine learning and deep learning methods increasingly critical for computational analysis and interpretation of the data. Conversely, biological data has also exposed unique challenges and problems that call for the development of new machine learning methods.

This workshop aims to bring together researchers working at the unique intersection of Machine Learning and Biology that include areas (and not limited to) such as computational genomics, neuroscience, pathology, radiology, evolutionary biology, population genomics, phenomics, ecology, cancer biology, causality, and representation learning and disentanglement to present recent advances and open questions to the ML community.

The workshop is a sequel to the WCB workshops we organized in the last four years ICML 2019, Long Beach , Joint ICML and IJCAI 2018, Stockholm , ICML 2017, Sydney and ICML 2016, New York as well as Workshop on Bioinformatics and AI at IJCAI 2015 Buenos Aires, IJCAI 2016 New York, IJCAI 2017 Melbourne which had excellent line-ups of talks and was well-received by the community. Every year, we received 60+ submissions. After multiple rounds of rigorous reviewing around 50 submissions were selected from which the best set of papers were chosen for Contributed talks and Spotlights and the rest were invited as Posters. We have a steadfast and growing base of reviewers making up the Program Committee. For the past two editions, a special issue of Journal of Computational Biology has been released with extended versions of a select set of accepted papers.

We invited Thomas Fuchs, Debora Marks, Fabian Theis, Olga Troyanskaya. We have received funding confirmation from PAIGE and Amazon Web Services that we intend to use for student travel awards. In past years, we have also been able to provide awards for the best poster/paper and partially contribute to the student registration fee.

The designers of a machine learning (ML) system typically have far more power over the system than the individuals who are ultimately impacted by the system and its decisions. Recommender platforms shape the users’ preferences; the individuals classified by a model often do not have means to contest a decision; and the data required by supervised ML systems necessitates that the privacy and labour of many yield to the design choices of a few.

The fields of algorithmic fairness and human-centered ML often focus on centralized solutions, lending increasing power to system designers and operators, and less to users and affected populations. In response to the growing social-science critique of the power imbalance present in the research, design, and deployment of ML systems, we wish to consider a new set of technical formulations for the ML community on the subject of more democratic, cooperative, and participatory ML systems.

Our workshop aims to explore methods that, by design, enable and encourage the perspectives of those impacted by an ML system to shape the system and its decisions. By involving affected populations in shaping the goals of the overall system, we hope to move beyond just tools for enabling human participation and progress towards a redesign of power dynamics in ML systems.

Machine learning systems are commonly applied to isolated tasks or narrow domains (e.g. control over similar robotic bodies). It is further assumed that the learning system has simultaneous access to all the data points of the tasks at hand. In contrast, Continual Learning (CL) studies the problem of learning from a stream of data from changing domains, each connected to a different learning task. The objective of CL is to quickly adapt to new situations or tasks by exploiting previously acquired knowledge, while protecting previous learning from being erased. Meeting the objectives of CL will provide an opportunity for systems to quickly learn new skills given knowledge accumulated in the past and continually extend their capabilities to changing environments, a hallmark of natural intelligence.

Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems, where the label space is extremely large. It brings many diverse approaches under the same umbrella including natural language processing (NLP), computer vision, information retrieval, recommendation systems, computational advertising, and embedding methods. Extreme classifiers have been deployed in many real-world applications in the industry ranging from language modelling to document tagging in NLP, face recognition to learning universal feature representations in computer vision, etc. Moreover, extreme classification finds application in recommendation, tagging, and ranking systems since these problems can be reformulated as multi-label learning tasks where each item to be ranked or recommended is treated as a separate label. Such reformulations have led to significant gains over traditional collaborative filtering and content-based recommendation techniques.

The proposed workshop aims to offer a timely collection of information to benefit the researchers and practitioners working in the aforementioned research fields of core supervised learning, theory of extreme classification, as well as application domains. These issues are well-covered by the Topics of Interest in ICML 2020. The workshop aims to bring together researchers interested in these areas to encourage discussion, facilitate interaction and collaboration and improve upon the state-of-the-art in extreme classification. The workshop will provide plethora of opportunities for research discussions, including poster sessions, invited talks, contributed talks, and a panel. During the panel the speakers will discuss challenges & opportunities in the field of extreme classification, in particular: 1) how to deal with the long tail labels problem?, 2) how to effectively combine deep learning approaches with extreme multi-label classification techniques?, 3) how to develop the theoretical foundations for this area? We expect a healthy participation from both industry and academia.

Objects, and the interactions between them, are the foundations on which our understanding of the world is built. Similarly, abstractions centered around the perception and representation of objects play a key role in building human-like AI, supporting high-level cognitive abilities like causal reasoning, object-centric exploration, and problem solving. Indeed, prior works have shown how relational reasoning and control problems can greatly benefit from having object descriptions. Yet, many of the current methods in machine learning focus on a less structured approach in which objects are only implicitly represented, posing a challenge for interpretability and the reuse of knowledge across tasks. Motivated by the above observations, there has been a recent effort to reinterpret various learning problems from the perspective of object-oriented representations.

In this workshop, we will showcase a variety of approaches in object-oriented learning, with three particular emphases. Our first interest is in learning object representations in an unsupervised manner. Although computer vision has made an enormous amount of progress in learning about objects via supervised methods, we believe that learning about objects with little to no supervision is preferable: it minimizes labeling costs, and also supports adaptive representations that can be changed depending on the particular situation and goal. The second primary interest of this workshop is to explore how object-oriented representations can be leveraged for downstream tasks such as reinforcement learning and causal reasoning. Lastly, given the central importance of objects in human cognition, we will highlight interdisciplinary perspectives from cognitive science and neuroscience on how people perceive and understand objects.

We have invited speakers whose research programs cover unsupervised and supervised 2-D and 3-D perception, reasoning, concept learning, reinforcement learning, as well as psychology and neuroscience. We will additionally source contributed works focusing on unsupervised object-centric representations, applications of such object-oriented representations (such as in reinforcement learning), and object-centric aspects of human cognition. To highlight and support research from a range of different perspectives, our invited speakers vary in their domain of expertise, institution, seniority, and gender. We will also encourage participation from underrepresented groups by providing travel grants courtesy of DeepMind and Kakao Brain. We are also planning to coordinate with the main conference and the speakers to provide remote access to the workshop.

In many settings such as education, healthcare, drug design, robotics, transportation, and achieving better-than-human performance in strategic games, it is important to make decisions sequentially. This poses two interconnected algorithmic and statistical challenges: effectively exploring to learn information about the underlying dynamics and effectively planning using this information. Reinforcement Learning (RL) is the main paradigm tackling both of these challenges simultaneously which is essential in the aforementioned applications. Over the last years, reinforcement learning has seen enormous progress both in solidifying our understanding on its theoretical underpinnings and in applying these methods in practice.

This workshop aims to highlight recent theoretical contributions, with an emphasis on addressing significant challenges on the road ahead. Such theoretical understanding is important in order to design algorithms that have robust and compelling performance in real-world applications. As part of the ICML 2020 conference, this workshop will be held virtually. It will feature keynote talks from six reinforcement learning experts tackling different significant facets of RL. It will also offer the opportunity for contributed material (see below the call for papers and our outstanding program committee). The authors of each accepted paper will prerecord a 10-minute presentation and will also appear in a poster session. Finally, the workshop will have a panel discussing important challenges in the road ahead.

ML has shown great promise in modeling and predicting complex phenomenon in many scientificdisciples such as predicting cardiovascular risk factors from retinal images, understanding howelectrons behave at the atomic level [3], identifying patterns of weather and climate phenomena, etc. Further, models are able to learn directly (and better) from raw data as opposed to human selected features. The ability to interpret the model and find significant predictors couldprovide new scientific insights.Traditionally, the scientific discovery process has been based on careful observations of nat-ural phenomenon, followed by systematic human analysis (of hypothesis generation and ex-perimental validation). ML interpretability has the potential to bring a radically different yetprincipled approach. While general interpretability relies on ‘human parsing’ (common sense),scientific domains have semi-structured and highly structured bases for interpretation. Thus,despite differences in data modalities and domains, be it brain sciences, the behavioral sciences,or material sciences, there is a need for a common set of tools that address a similar flavor of problem, one of interpretability or fitting models to a known structure. This workshop aims to bring together members from the ML and physical sciences communities to introduce exciting problems to the broader community, and stimulate the productionof new approaches towards solving open scientific problems.

There has been growing interest in rectifying deep neural network instabilities. Challenges arise when models receive samples drawn from outside the training distribution. For example, a neural network tasked with classifying handwritten digits may assign high confidence predictions to cat images. Anomalies are frequently encountered when deploying ML models in the real world. Well-calibrated predictive uncertainty estimates are indispensable for many machine learning applications, such as self-driving vehicles and medical diagnosis systems. Generalization to unseen and worst-case inputs is also essential for robustness to distributional shift. In order to have ML models reliably predict in open environment, we must deepen technical understanding in the emerging areas of: (1) learning algorithms that can detect changes in data distribution (e.g. out-of-distribution examples); (2) mechanisms to estimate and calibrate confidence produced by neural networks in typical and unforeseen scenarios; (3) methods to improve out-of-distribution generalization, including generalization to temporal, geographical, hardware, adversarial, and image-quality changes; (4) benchmark datasets and protocols for evaluating model performance under distribution shift; and (5) key applications of robust and uncertainty-aware deep learning (e.g., computer vision, robotics, self-driving vehicles, medical imaging) as well as broader machine learning tasks.

This workshop will bring together researchers and practitioners from the machine learning communities, and highlight recent work that contributes to addressing these challenges. Our agenda will feature contributed papers with invited speakers. Through the workshop we hope to help identify fundamentally important directions on robust and reliable deep learning, and foster future collaborations.

Optimization lies at the heart of many exciting developments in machine learning, statistics and signal processing. As models become more complex and datasets get larger, finding efficient, reliable and provable methods is one of the primary goals in these fields.

In the last few decades, much effort has been devoted to the development of first-order methods. These methods enjoy a low per-iteration cost and have optimal complexity, are easy to implement, and have proven to be effective for most machine learning applications. First-order methods, however, have significant limitations: (1) they require fine hyper-parameter tuning, (2) they do not incorporate curvature information, and thus are sensitive to ill-conditioning, and (3) they are often unable to fully exploit the power of distributed computing architectures.


Higher-order methods, such as Newton, quasi-Newton and adaptive gradient descent methods, are extensively used in many scientific and engineering domains. At least in theory, these methods possess several nice features: they exploit local curvature information to mitigate the effects of ill-conditioning, they avoid or diminish the need for hyper-parameter tuning, and they have enough concurrency to take advantage of distributed computing environments. Researchers have even developed stochastic versions of higher-order methods, that feature speed and scalability by incorporating curvature information in an economical and judicious manner. However, often higher-order methods are “undervalued.”


This workshop will attempt to shed light on this statement. Topics of interest include, but are not limited to, second-order methods, adaptive gradient descent methods, regularization techniques, as well as techniques based on higher-order derivatives.