First Workshop Causal Representation Learning at UAI 2022: https://crl-uai-2022.github.io/
5 August 2022, Eindhoven, The Netherlands, hybrid
Submission deadline: June 6, 2022, 23:59 AoE

***AIM AND TOPICS***

Machine learning (ML) has established itself as the dominant and most successful paradigm for artificial intelligence (AI). A key strength of ML over earlier (symbolic, logic and rule-based) approaches to AI, is its ability to infer useful features or representations of often very high-dimensional observations in an automated, data-driven way. However, in doing so, it generally only leverages statistical information (e.g., correlations present in a training set) and consequently struggles at tasks such as knowledge transfer, systematic generalization, or planning, which are thought to require higher-order cognition.

Causal inference (CI), on the other hand, is concerned with going beyond the statistical level of description (“seeing”) and instead aims to reason about the effect of interventions or external manipulations to a system (“doing”) as well as about hypothetical counterfactual scenarios (“imagining”). Similar to classic approaches to AI, CI typically assumes that the causal variables of interest (i.e., an appropriate level of description of a given system) are given from the outset. However, real-world data often comprises high-dimensional, low-level observations and is thus usually not structured into such meaningful causal units.

The emerging field of causal representation learning (CRL) aims to combine the strengths of ML and CI. Much like ML went beyond symbolic AI in not requiring that the symbols that algorithms manipulate be given a priori, in CRL low-dimensional, high-level variables along with their causal relations should be learned from raw, unstructured data, leading to representations that support notions such as intervention, reasoning, and planning. In this sense, CRL aligns with the general goal of modern ML to learn meaningful representations of data, where meaningful can also include robust, explainable, or fair.

One aim of this first workshop on CRL is to bring together researchers focusing mainly on either CI or representation learning, from both theoretical and applied perspectives. Moreover, the workshop aims at engaging the various communities interested in learning robust and transferable representations from different perspectives, in order to foster an exchange of ideas. Given that this is still a young, emerging line of research, another goal is to establish a common vocabulary and to identify useful frameworks for addressing CRL.

We welcome submissions related to any aspects of CRL, including but not limited to:
– Learning latent (structural) causal models & structured (deep) generative models
– Interventional representations, causal digital twins & structured (causal) world models
– Post-hoc extraction of causal relations from (deep) generative models
– Self-supervised causal representation learning
– Multi-environment & multi-view causal representation learning
– Micro vs. macro/coarse-grained/multi-level causal systems
– Identifiable representation learning & nonlinear ICA
– Uncertainty quantification in (causal) representation learning
– Group-theoretic & symmetry-based views on disentanglement
– Invariance & equivariance in representation learning
– Interdisciplinary perspectives on causal representation learning, including from cognitive science, psychology, (computational) neuroscience or philosophy
– Real-world applications of causal representation learning, including in biology, medical sciences, or robotics

***IMPORTANT DATES***

Paper submission deadline: June 1, 2022, 23:59 AoE  June 6, 2022, 23:59 AoE
Notification to authors: July 1, 2022, 23:59 AoE
Camera-ready version: TBA
Workshop Date: August 5, 2022

***SUBMISSION INSTRUCTIONS***

Submissions should be formatted using the UAI latex template and formatting instructions. Papers must be submitted as a PDF file and should be 4-6 pages in length, including all main results, figures, and tables. Appendices containing additional details are allowed, but reviewers are not expected to take this into account. The workshop will not have proceedings, so you can submit recent work or work in progress.