Call for Papers

Due to the increasing popularity of studies at the intersection of machine learning and strategic behavior, NeurIPS 2021 will host two workshops focusing on this topic: Learning in Presence of Strategic Behavior (Monday) and Decision-Making and Learning with Strategic Feedback (Tuesday). The two workshops will have a joint call for papers.

Topics of interest:
The primary goal of these workshops is to address current challenges and opportunities that arise from interactions of learning systems with social and strategic agents. The aim is to bring together members of different communities, including machine learning, economics, theoretical computer science, and social computing, to share recent results, discuss important directions for future research, and foster collaborations.

Topics of interest include, but are not limited to:

  • Learning from data produced by agents who have a vested interest in the outcome of the learning process
    (e.g., learning economic policy, strategic classification, performative prediction)

  • Dynamics and learning in competitive and cooperative multi-agent environments
    (e.g., through federated, multi-task, and distributed learning)

  • Fairness and welfare-aware machine learning (e.g., in employment and lending)

  • Optimization in non-stationary environments (e.g., learning with strategically induced distribution shift)

  • Learning as a behavioral model
    (e.g., understanding the impact of strategic communication on social learning, persuasion, and belief polarization)

  • Identifying causal effects underlying strategic interactions

  • Practical studies and field experiments with strategic users

  • Modeling strategic behavior, behavioral insights, bounded rationality

Submission Guidelines:
We welcome submissions that describe recent, ongoing, or unfinished work broadly related to the topics above. Papers will be judged based on how well they align with the themes of the two workshops, present perspectives of related communities, the quality of their conceptual ideas, correctness, and novelty. Papers that have been published in ML journals and conferences may be subjected to a higher bar to ensure that their inclusion in these workshops will benefit the community and highlight underexplored research agenda.

The submission deadline for workshop contributions is September 17, 2021 (extended to October 3, 2021 AOE). The workshops are non-archival. Accepted papers will be listed on both workshops’ websites, and the authors will be invited to present a poster at the virtual poster session of both workshops. In addition, a subset of the submissions will be invited for a contributed talk at one of the workshops. All submissions will be peer-reviewed. The reviewing process is double-blind. Submissions should be no more than 8 pages long, any template is allowed. In addition, authors will be asked to provide a short paragraph explaining how their paper relates to the workshops’ topics of interest.

Submit at: