Skip to yearly menu bar Skip to main content



Workshops
Affinity Poster Session
Charlie Gauthier · Claire Vernade · David Dobre · Gauthier Gidel · Joan Bruna

[ MH1-2-3-4 ]

Workshop
Yu Cheng · Boxin Wang · Bo Li · Tom Goldstein · Sanmi Koyejo · Yejin Choi

[ AD12 ]

In recent years, the landscape of AI has been significantly altered by the advances in large-scale pre-trained models. Scaling up the models with more data and parameters has significantly improved performance and achieved great success in various applications, from natural language understanding to multi-modal representation learning. However, when applying large-scale AI models to real-world applications, there have been concerns about their potential security, privacy, fairness, robustness, and ethics issues. In the wrong hands, machine learning could be used to negatively impact mission-critical domains, including healthcare, education, and law, resulting in economic and environmental consequences and legal and ethical concerns. For example, existing studies have shown that large-scale pre-trained language models contain toxicity in open-ended generation and have the risk of amplifying bias against marginalized groups, such as BIPOC and LGBTQ+. Moreover, large-scale models can unintentionally leak sensitive personal information during the pre-training stage. Last but not least, machine learning models are often viewed as "blackboxes" and may produce unpredictable, inaccurate, and unexplainable results, especially under domain shifts or maliciously tailored attacks. To address these negative societal impacts in large-scale models, researchers have investigated different approaches and principles to ensure robust and trustworthy large-scale AI systems. This workshop is to bridge …

Workshop
Rishabh Agarwal · Ted Xiao · Yanchao Sun · Max Schwarzer · Susan Zhang

[ AD1 ]

Learning “tabula rasa”, that is, from scratch without much previously learned knowledge, is the dominant paradigm in reinforcement learning (RL) research. However, learning tabula rasa is the exception rather than the norm for solving larger-scale problems. Additionally, the inefficiency of tabula rasa RL typically excludes the majority of researchers outside certain resource-rich labs from tackling computationally demanding problems. To address the inefficiencies of tabula rasa RL and help unlock the full potential of deep RL, our workshop aims to bring further attention to this emerging paradigm of reusing prior computation in RL, discuss potential benefits and real-world applications, discuss its current limitations and challenges, and come up with concrete problem statements and evaluation protocols for the research community to work on. Furthermore, we hope to foster discussions via panel discussions (with audience participation), several contributed talks and by welcoming short opinion papers in our call for papers.

Workshop
Christian Schroeder de Witt · Sumitra Ganesh · Ani Calinescu · Yang Zhang · Ayush Chopra · Swapneel Mehta · Pablo Samuel Castro · Jakob Foerster

[ AD4 ]

Many of the world's most pressing issues, such as climate change, pandemics, financial market stability and fake news, are emergent phenomena that result from the interaction between a large number of strategic or learning agents. Understanding these systems is thus a crucial frontier for scientific and technology development that has the potential to permanently improve the safety and living standards of humanity. Agent-Based Modelling (ABM) (also known as individual-based modelling) is an approach toward creating simulations of these types of complex systems by explicitly modelling the actions and interactions of the individual agents contained within. However, current methodologies for calibrating and validating ABMs rely on human expert domain knowledge and hand-coded behaviours for individual agents and environment dynamics.Recent progress in AI has the potential to offer exciting new approaches to learning, calibrating, validation, analysing and accelerating ABMs. This interdisciplinary workshop is meant to bring together practitioners and theorists to boost ABM method development in AI, and stimulate novel applications across disciplinary boundaries and continents - making ICLR the ideal venue.Our inaugural workshop will be organised along two axes. First, we seek to provide a venue where ABM researchers from a variety of domains can introduce AI researchers to their respective …

Workshop
Konstantin Klemmer · Sasha Luccioni · Simone Fobi · Rasika Bhalerao · Utkarsha Agwan · Marcus Voss · Olalekan Akintande · Yoshua Bengio

[ Auditorium ]

Climate change is one of the greatest problems society has ever faced, with increasingly severe consequences for humanity as natural disasters multiply, sea levels rise, and ecosystems falter. While climate change is a truly global problem, it manifests itself via many local effects, which pose unique problems and require corresponding actions. These actions can take many forms, from designing smart electric grids to tracking greenhouse gas emissions through satellite imagery. While no silver bullet, machine learning can be an invaluable tool in fighting climate change via a wide array of applications and techniques. These applications require algorithmic innovations in machine learning and close collaboration with diverse fields and practitioners. This workshop is intended as a forum for those in the global machine learning community who wish to help tackle climate change, and is further aimed to help foster cross-pollination between researchers in machine learning and experts in complementary climate-relevant fields. Building on our past workshops on this topic, this workshop particularly aims to explore the connection between global perspectives and local challenges in the context of applying machine learning towards tackling climate change. We want to take the opportunity of the first leading machine learning conference being hosted in person …

Workshop
Hao CHEN · Luyang Luo · Daguang Xu · Varut Vardhanabhuti · Yuyin Zhou · Jing Qin · Yueming Jin · Marius George Linguraru · Pheng-Ann Heng · Le Lu · Danny Chen · Kwang-Ting Cheng

[ Virtual ]

Machine learning (ML) has achieved or even exceeded human performance in many healthcare tasks, owing to the fast development of ML techniques and the growing scale of medical data. However, ML techniques are still far from being widely applied in practice. Real-world scenarios are far more complex, and ML is often faced with challenges in its trustworthiness such as lack of explainability, generalization, fairness, privacy, etc. Improving the credibility of machine learning is hence of great importance to enhance the trust and confidence of doctors and patients in using the related techniques. We aim to bring together researchers from interdisciplinary fields, including but not limited to machine learning, clinical research, and medical imaging, etc., to provide different perspectives on how to develop trustworthy ML algorithms to accelerate the landing of ML in healthcare.

Workshop
T. Konstantin Rusch · Aditi Krishnapriyan · Emmanuel de Bézenac · Ben Chamberlain · Elise van der Pol · Patrick Kidger

[ MH1 ]

Combining physics with machine learning is a rapidly growing field of research. Thus far, most of the work in this area focuses on leveraging recent advances in classical machine learning to solve problems that arise in the physical sciences. In this workshop, we wish to focus on a slightly less established topic, which is the converse: exploiting structures (or symmetries) of physical systems as well as insights developed in physics to construct novel machine learning methods and gain a better understanding of such methods. A particular focus will be on the synergy between the scientific problems and machine learning and incorporating structure of these problems into the machine learning methods which are used in that context. However, the scope of application of those models is not limited to problems in the physical sciences and can be applied even more broadly to standard machine learning problems, e.g. in computer vision, natural language processing or speech recognition.

Workshop
Ananya Kumar · Tengyu Ma · Tiffany Vlaar · Aditi Raghunathan · Hanie Sedghi · Yamini Bansal · Sang Michael Xie · Percy Liang · Mathilde Caron

[ AD10 ]

Foundation models (FMs) are models that are trained on a large and diverse pool of data and can be adapted to a wide range of tasks. Recent examples of FMs include large language models (GPT-3, BERT, PaLM), image representation encoders (SimCLR), and image-text models (CLIP, DALL-E), which have all revolutionized the way models are built in their domains. Foundation models are poorly understood: the core driving principle behind Foundation Models (FMs) is transfer learning, but scale and modern self supervision techniques have led to emergent capabilities we might not have anticipated. The goal of this workshop is to highlight research that aims to improve our understanding of FMs. We liberally interpret understanding as any research ranging from purely empirical papers that highlight interesting phenomena, to those which attempt to explain or provide theoretical foundations for such phenomena in potentially simplified settings.

Workshop
Hyunjik Kim · Emilien Dupont · Jonathan Schwarz · Thu Nguyen-Phuoc · Srinath Sridhar · Vincent Sitzmann

[ MH4 ]

Addressing problems in different science and engineering disciplines often requires solving optimization problems, including via machine learning from large training data. One class of methods has recently gained significant attention for problems in computer vision and visual computing: coordinate-based neural networks parameterizing a field, such as a neural network that maps a 3D spatial coordinate to a flow field in fluid dynamics, or a colour and density field in 3D scene representation. Such networks are often referred to as "neural fields". The application of neural fields in visual computing has led to remarkable progress on various computer vision problems such as 3D scene reconstruction and generative modelling, leading to more accurate, higher fidelity, more expressive, and computationally cheaper solutions. Given that neural fields can represent spatio-temporal signals in arbitrary input/output dimensions, they are highly general as a tool to reason about real-world observations, be it common modalities in machine learning and vision such as image, 3D shapes, 3D scenes, video, speech/audio or more specialized modalities such as flow fields in physics, scenes in robotics, medical images in computational biology, weather data in climate science. However, though some adjacent fields such as robotics have recently seen an increased interest in this …

Workshop
Aniket Anand Deshmukh · Henry Gouk · Da Li · Cuiling Lan · Kaiyang Zhou · Timothy Hospedales

[ Virtual ]

The real challenge for any machine learning system is to be reliable and robust in any situation, even if it is different compared to training conditions. Existing general purpose approaches to domain generalization (DG)—a problem setting that challenges a model to generalize well to data outside the distribution sampled at training time—have failed to consistently outperform standard empirical risk minimization baselines. In this workshop, we aim to work towards answering a single question: what do we need for successful domain generalization? We conjecture that additional information of some form is required for a general purpose learning methods to be successful in the DG setting. The purpose of this workshop is to identify possible sources of such information, and demonstrate how these extra sources of data can be leveraged to construct models that are robust to distribution shift. Examples areas of interest include using meta-data associated with each domain, examining how multimodal learning can enable robustness to distribution shift, and flexible frameworks for exploiting properties of the data that are known to be invariant to distribution shift.

Workshop
Thiviyan Thanapalasingam · Emile van Krieken · Halley Young · Disha Shrivastava · Kevin Ellis · Jakub Tomczak

[ AD11 ]

The Neurosymbolic Generative Models (NeSy-GeMs) workshop at ICLR 2023 aims to bridge the Neurosymbolic AI and Generative Modeling communities, bringing together machine learning, neurosymbolic programming, knowledge representation and reasoning, tractable probabilistic modeling, probabilistic programming, and application researchers to discuss new research directions and define novel open challenges.

Workshop
Tian Xie · Xiang Fu · Simon Batzner · Hanchen Wang · Adji Dieng · Ekin Cubuk · Elsa Olivetti · Kristin Persson · Tommi Jaakkola · Max Welling

[ Virtual ]

The discovery of new materials drives the development of key technologies like solar cells, batteries, carbon capture, and catalysis. While there has been growing interest in materials discovery with machine learning, the specific modeling challenges posed by materials have been largely unknown to the broader community. Compared with drug-like molecules and proteins, the modeling of materials has the following two major challenges. First, materials-specific inductive biases are needed to develop successful ML models. For example, materials often don’t have a handy representation like 2D graphs for molecules or sequences for proteins. Second, there exists a broad range of interesting materials classes, such as inorganic crystals, polymers, catalytic surfaces, nanoporous materials, and more. Each class of materials demands a different approach to represent their structures, and new tasks/data sets to enable rapid ML developments.This workshop aims at bringing together the community to discuss and tackle these two types of challenges. In the first session, we will feature speakers to discuss the latest progress in developing ML models for materials focusing on algorithmic challenges, covering topics like representation learning, generative models, pre-training, etc. In particular, what can we learn from the more developed field of ML for molecules and 3D geometry and …

Workshop
Hongyang Li · Mengye Ren · Li Chen · Chonghao Sima · Kashyap Chitta · Holger Caesar · Ping Luo · Wei Zhang

[ AD1 ]

Autonomous Driving (AD) is a complex research area. Through the aid of Machine Learning (ML) techniques, AD systems have rapidly developed, yet there are several challenges involved in deploying these ML algorithms to systems in production. Solving these challenges is beyond the capability of any single company or institution, necessitating large-scale communication and collaboration. Our goal is to provide a platform for this at ICLR, and promote the real-world impact of ML research toward self-driving technology. To this end, we propose a workshop titled “Scene Representations for Autonomous Driving” (SR4AD). We have invited a diverse span of keynote speakers (different regions, academic/industry, junior/senior) to contribute to the workshop. In addition, our program includes a call for contributed papers and a call for competition participation around two new and exciting benchmark tasks for mapping and planning. Finally, to encourage broad discussions, we conclude with a panel debate regarding promising future directions.

Workshop
Adrián Javaloy · Miguel Vasco · Imant Daunhawer · Petra Poklukar · Yuge Shi · Danica Kragic · Isabel Valera

[ Virtual ]

Following deep learning, multimodal machine learning has made steady progress, becoming ubiquitous in many domains. Learning representations from multiple modalities can be beneficial since different perceptual modalities can inform each other and ground abstract phenomena in a more robust, generalisable way. However, the complexity of different modalities can hinder the training process, requiring careful design of the model in order to learn meaningful representations. In light of these seemingly conflicting aspects of multimodal learning, we must improve our understanding of what makes each modality different, how they interact, and what are the desiderata of multimodal representations. With this workshop, we aim to bring the multimodal community together, promoting work on multimodal representation learning that provides systematic insights into the nature of the learned representations, as well as ways to improve and understand the training of multimodal models, both from a theoretical and empirical point of view.In particular, we focus on the following questions:(Representation) How do we identify useful properties of multimodal representations?(Training) How can we promote useful properties of multimodal representations?(Modalities) What makes a modality different? How can we improve their interactions?The MRL workshop has an objective to bring together experts from the multimodal learning community in order to advance …

Workshop
Girmaw Abebe Tadesse · Esube Bekele · Timnit Gebru · Matimba Shingange · Waheeda Saib · Luis Oala · Aisha Alaagib

[ MH1 ]

The constant progress being made in machine learning needs to extend across borders if we are to democratize ML in developing countries. Adapting state-of-the-art (SOTA) methods to resource constrained environments such as developing countries can be challenging in practice. Recent breakthroughs in natural language processing and generative image models, for instance, rely on increasingly complex and large models that are pre-trained on large unlabeled datasets. In most developing countries, resource constraints make the adoption of these breakthrough challenges. Methods such as transfer learning will not fully solve the problem either due to bias in pre-training datasets that do not reflect environments in developing countries or the cost of fine-tuning larger models. This gap in resources between SOTA requirements and developing country capacities hinders a democratic development of machine learning methods and infrastructure.

Practical Machine Learning for Developing Countries (PML4DC) workshop is a full-day event that has been running regularly for the past 3 years at ICLR (past events include PML4DC 2020, PML4DC 2021 and PML4DC 2022). PML4DC aims to foster collaborations and build a cross-domain community by featuring invited talks, panel discussions, contributed presentations (oral and poster) and round-table mixers.

The main goal of PML4DC is to bring together researchers …

Workshop
Baharan Mirzasoleiman · Zhangyang Wang · Decebal Constantin Mocanu · Elena Mocanu · Utku Evci · Trevor Gale · Aleksandra Nowak · Ghada Sokar · Zahra Atashgahi

[ AD12 ]

Deep networks with billions of parameters trained on large datasets have achieved unprecedented success in various applications, ranging from medical diagnostics to urban planning and autonomous driving, to name a few. However, training large models is contingent on exceptionally large and expensive computational resources. Such infrastructures consume substantial energy, produce a massive amount of carbon footprint, and often soon become obsolete and turn into e-waste. While there has been a persistent effort to improve the performance of machine learning models, their sustainability is often neglected. This realization has motivated the community to look closer at the sustainability and efficiency of machine learning, by identifying the most relevant model parameters or model structures. In this workshop, we examine the community’s progress toward these goals and aim to identify areas that call for additional research efforts. In particular, by bringing researchers with diverse backgrounds, we will focus on the limitations of existing methods for model compression and discuss the tradeoffs among model size and performance. The main goal of the workshop is to bring together researchers from academia, and industry with diverse expertise and points of view on network compression, to discuss how to effectively evaluate and enforce machine learning pipelines to …

Workshop
Elizaveta Semenova · Seth Flaxman · Swapnil Mishra · Abraham Owodunni · Timothy Wolock · Juliette Unwin · Emmanuelle Dankwa · Adam Howes

[ AD10 ]

During the Covid-19 pandemic, in spite of the impressive advances in machine learning (ML) in recent decades, the successes of this field were modest at best. Much work remains, for both ML and global health (GH) researchers, to deliver true progress in GH This workshop will start a lasting and consistent effort to close the gap between advances in ML, practitioners and policy makers working in public health globally. It will focus on difficult public health problems and relevant ML and statistical methods.We will use this opportunity to bring together researchers from different communities to share new ideas and past experiences. We will facilitate rapid communication of the latest methodological developments in ML to parties who are in positions to use them and establish feedback loops for assessing the applicability and relevance of methods that are available and gaps that exist. It will be a unique opportunity to challenge both research communities and demonstrate important, policy-relevant applications of sophisticated methods at one of the most prestigious annual ML conferences.This will be the first ever ML conference workshop on the topic ``Machine Learning & Global Health'', sponsored by the Machine Learning & Global Health Network (MLGH.NET). By showcasing key applied challenges, …

Workshop
Hannah Kerner · Hamed Alemohammad · Moise Busogi · Ronny Hänsch · Gedeon Muhawenayo · Catherine L Nakalembe · Ange Tesire · Gabriel Tseng · Ivan Zvonkov

[ MH3 ]

Remote sensing data (also referred to as Earth observation or satellite data) has become an increasingly popular modality for machine learning research. This interest has largely been driven by the opportunities that remote sensing data present for contributing to challenges urgently important to society, such as climate change, food security, conservation, disasters, and poverty. This growing interest in ML research for remote sensing data is also driven by the challenges presented by its unique characteristics compared to other data modalities (e.g., images, text, video). Remote sensing datasets are very high-dimensional and often have spatial, temporal, and spectral dimensions more complex than traditional RGB images or videos. The diversity of instruments used for observing the Earth at different wavelengths, temporal cadences, and spatial resolutions has driven active research in domain adaptation, data fusion, and other topic areas. In this workshop, we aim to stimulate and highlight research on new methods, datasets, and systems for machine learning for remote sensing data and especially encourage submissions and discussions about research in the African context.

Workshop
Amartya Sanyal · Alexandru Tifrea · Ankit Pensia · Franziska Boenisch · Varun Kanade · Fanny Yang · Prateek Jain · Sara Hooker · Jamie Morgenstern

[ MH2 ]

Machine Learning (ML) algorithms are known to suffer from various issues when it comes to their trustworthiness. This can hinder their deployment in sensitive application domains in practice. But how much of this problem is due to limitations in available data and/or limitations in compute (or memory)? In this workshop, we will look at this question from both a theoretical perspective, to understand where fundamental limitations exist, and from an applied point of view, to investigate which issues we can mitigate by scaling up our datasets and computer architectures.

Workshop
Bonaventure Dossou · Constantine Lignos · Hady Elsahar · David Adelani · Atnafu Lambebo Tonja · Salomey Osei · Happy Buzaaba · Clemencia N Siro · Vukosi Marivate · shamsuddeen muhammad · Tajuddeen Gwadabe · Anuoluwapo Aremu

[ Auditorium ]

Over 1 billion people live in Africa, and its residents speak more than 2,000 languages. But those languages are among the least represented in NLP research, and work on African languages is often sidelined at major venues. Over the past few years, a vibrant, collaborative community of researchers has formed around a sustained focus on NLP for the benefit of the African continent: national, regional, continental, and even global collaborative efforts focused on African languages, African corpora, and tasks with importance in the African context. The AfricaNLP workshops have been a central venue in organizing, sustaining, and growing this focus, and we propose to continue this tradition with an AfricaNLP 2023 workshop in Kigali. The wave of large language models built in 2022 through collaborative networks and large investments in compute have inspired the theme for the 2023 workshop: “African NLP in the Era of Large Language Models.” We plan to invite a variety of speakers from industry, research networks and academia to get their perspectives on the development of large language models and how African languages have and have not been represented in this work, and we will provide a venue to discuss the benefits and potential harms of …

Workshop
Heike Leutheuser · Laura Manduchi · Alexander Marx · Emanuele Palumbo · Ece Özkan Elsen · Julia Vogt

[ Virtual ]

Time series data have been used in many applications in healthcare, such as the diagnosis of a disease, prediction of disease progression, clustering of patient groups, online monitoring and dynamic treatment regimes, to name a few. More and more methods build on representation learning to tackle these problems by first learning a (typically low-dimensional) representation of the time series and then use the learned representation for the corresponding downstream task.Machine learning (ML) provides a powerful set of tools for time series data, but its applicability in healthcare is still limited. As a result, the potential of time series analysis cannot be fully realised currently. Furthermore, it is expected that in the coming years, the availability and nature of time series data will continue to increase. These data could support all components of healthcare to benefit everyone. Handling time series data is a challenge, especially in the medical domain, for reasons such as the following:- Labeling, in general and in particular of long-term recordings, is a nontrivial task requiring appropriate experts like clinicians who are restricted in their time- Time series data acquired within real-life settings and novel measurement modalities are recorded without supervision having no labels at all- The high-dimensionality …

Workshop
Pascal Notin · Sonali Parbhoo · Patrick Schwab · Ece Özkan Elsen · Stefan Bauer · Debora Marks · Yarin Gal · Ashkan Soleymani · Clare Lyle · Max Shen · Ehsan Hajiramezanali

[ Virtual ]

We are at a pivotal time in healthcare characterized by unprecedented scientific and technological progress in recent years together with the promise borne by personalized medicine to radically transform the way we provide care to patients. However, drug discovery has become an increasingly challenging endeavor: not only has the success rate of developing new therapeutics been historically low, but this rate has been steadily declining. The average cost to bring a new drug to market (factoring in failures) is now estimated at 2.6 billion – 140% higher than a decade earlier. Machine learning-based approaches present a unique opportunity to address this challenge. While there has been growing interest and pioneering work in the machine learning (ML) community over the past decade, the specific challenges posed by drug discovery are largely unknown by the broader community. Last year, the first MLDD workshop at ICLR 2022 brought together hundreds of attendees, world-class experts in ML for drug discovery, received about 60 paper submissions from the community, and featured a two-month community challenge in parallel to the workshop. Building on the success from last year, we would like to organize a second instance of the MLDD workshop at ICLR 2023, with the ambition …

Workshop
Torsten Scholak · Zijian Wang · Disha Shrivastava · Gabriel Orlanski · Devjeet Roy

[ Virtual ]

An exciting application area of machine learning and deep learning methods is completion, repair, synthesis, and automatic explanation of program code. This field has received a fair amount of attention in the last decade (see e.g. Oda et al. (2015); Balog et al. (2017); Allamanis et al. (2018)), yet arguably the recent application of large scale language modelling techniques to the domain of code holds a tremendous promise to completely revolutionize this area (Chen et al., 2021; Austin et al., 2021). The new large pretrained models excel at completing code and synthesizing code from natural language descriptions; they work across a wide range of domains, tasks, and programming languages. The excitement about new possibilities is spurring tremendous interest in both industry and academia. Yet, we are just beginning to explore the potential of large-scale deep learning for code, and state-of-the-art models still struggle with correctness and generalization. This calls for platforms to exchange ideas and discuss the challenges in this line of work. The second Deep Learning for Code (DL4C) workshop will provide such a platform at ICLR 2023.

Workshop
Xinyu Zhang · Tauhidur Rahman · Yuan Yuan · Ke Sun · Yuanyuan Yang · Brad Campbell · Zhiting Hu

[ Virtual ]

As the emerging Internet of Things (IoT) brings a massive population of multi-modal sensors in the environment, there is a growing need in developing new Machine Learning (ML) techniques to analyze the data and unleash its power. A data-driven IoT ecosystem forms the basis of Ambient Intelligence, i.e., smart environment that is sensitive to the presence of humans and can ultimately help automate human life. IoT data are highly heterogeneous, involving not only the traditional audio-visual modalities, but also many emerging sensory dimensions that go beyond human perception. The rich IoT sensing paradigms pose vast new challenges and opportunities that call for coordinated research efforts between the ML and IoT communities. On one hand, the IoT data require new ML hardware/software platforms and innovative processing/labeling methods for efficient collection, curation, and analysis. On the other hand, compared with traditional audio/visual/textual data that have been widely studied in ML, the new IoT data often exhibit unique challenges due to the highly heterogeneous modalities, disparate dynamic distributions, sparsity, intensive noise, etc. Besides, the involved rich environment and human interactions pose challenges for privacy and security. All those properties hence require new paradigms of ML based perception and understanding. The objective of this …

Workshop
Guanhong Tao · Kaiyuan Zhang · Shawn Shan · Emily Wenger · Rui Zhu · Eugene Bagdasaryan · Naren Sarayu Manoj · Taylor Kulp-McDowall · Yousra Aafer · Shiqing Ma · Xiangyu Zhang

[ Virtual ]

Backdoor attacks aim to cause consistent misclassification of any input by adding a specific pattern called a trigger. Recent studies have shown the feasibility of launching backdoor attacks in various domains, such as computer vision (CV), natural language processing (NLP), federated learning (FL), etc. As backdoor attacks are mostly carried out through data poisoning (i.e., adding malicious inputs to training data), it raises major concerns for many publicly available pre-trained models. Defending against backdoor attacks has sparked multiple lines of research. Many defense techniques are effective against some particular types of backdoor attacks. However, with increasingly emerging diverse backdoors, the defense performance of existing work tends to be limited. This workshop, Backdoor Attacks aNd DefenSes in Machine Learning (BANDS), aims to bring together researchers from government, academia, and industry that share a common interest in exploring and building more secure machine learning models against backdoor attacks.