Submissions

The increasing popularity of machine learning (ML) models in various high-stakes domains such as finance, criminal justice and healthcare has resulted in a call for greater transparency into the mechanisms behind their predictions. Since transparency in algorithmic decision-making systems has undoubtedly become an ethical and sometimes legal obligation, there has been a recent surge of interest towards the field of algorithmic recourse. Algorithmic recourse aims to design mechanisms that provide actionable feedback about how to change the outcomes of ML models. In this workshop, we aim to identify how to bridge the gap between theory and practice for algorithmic recourse.

We welcome submissions of full papers as well as work in progress and accept submissions of work recently published or currently under review. Examples of topics of interest include:

• Technical methods for achieving recourse (e.g., via counterfactual explanations) for various data types (e.g., tabular, image, text, time series, etc)

• Causal approaches to recourse

• Interactions between recourse and other explainability methods (e.g., feature attributions, decision rules, influential samples, etc)

• Interactions between recourse and other ethical criteria (e.g., confidentiality, fairness, strategic behavior, etc)

• Human-subject studies examining how stakeholders understand or interact with recourse methods

• Frameworks for operationalizing recourse in practice

• Analysis of shortcomings of existing recourse methods

• Legal perspectives on recourse

• Psychological perspectives on recourse

• Behavioral perspectives on recourse

• Philosophical perspectives on recourse

Important dates:

• Submission deadline: June 18, 23:59 PT

• Author notification: July 9

Submissions must be at most 4 pages long (not including references and an unlimited number of pages for supplemental material, which reviewers are not required to take into account) and adhere to the ICML format. The main content, references and appendices should be submitted as a single pdf file. Papers should be anonymized and submitted through https://cmt3.research.microsoft.com/AR2021/.

The workshop will not have formal proceedings, but authors of accepted papers can choose to have either a link to an arxiv version of their paper or a pdf published on the workshop webpage.

There will be $1000 for Best Paper Awards, sponsored by the Partnership on AI. The comittee for selecting the awards is made up of Amir Hossein-Karimi, Stratis Tsirtsis, and Ana Lucic.