Call for Papers

Submission deadline: July 29th, 2020 midnight UTC

Submit at: https://cmt3.research.microsoft.com/REVEAL2020.


State-of-the-art recommender systems are notoriously hard to design and improve upon, due to their interactive and dynamic nature. In particular, they involve a multi-step decision-making process, where a stream of interactions occurs between the user and the system. Leveraging reward signals from these interactions and creating a scalable and performant recommendation inference model is a key challenge. Traditionally, to make the problem tractable, the interactions are often viewed as independent, but in order to improve recommender systems further, the models will need to take into account the delayed effects of each recommendation and start reasoning/planning for longer-term user satisfaction. To this end, our workshop invites contributions that enable recommender systems to adapt effectively to diverse forms of user feedback and to optimize the quality of each user's long-term experience -- specifically approaches that leverage bandit and reinforcement learning from user interactions.

Potential contributions include (but are not limited to):

  • Reinforcement learning and bandits for recommendation
  • Robust estimators, counterfactual and off-policy evaluation
  • Causal recommender systems
  • Using simulation for recommender systems evaluation
  • New evaluation datasets
  • New offline metrics for recommender systems


Formatting instructions: Submissions are limited to a single extended abstract of at most two pages in RecSys format. Accepted submissions will be presented as talks and/or as posters. Note that ACM has changed the archive format of its publications. Make sure to follow the latest instructions: https://recsys.acm.org/recsys20/call/#content-tab-1-3-tab


Publication of submissions: If authors would like to provide longer versions of their submission, we will link to their papers on Arxiv. To be included on the workshop homepage, authors should send us the link to their Arxiv paper by September 3rd.


Reviewing process: The reviews will be single-blind.