Group Fairness in Peer Review

Conferences like AAMAS and NeurIPS have attracted submissions from a large number of communities. This has resulted in a poor reviewing experience for communities, whose submissions are assigned to less qualified reviewers outside of their communities. An often-advocated solution is to break up such large conferences into smaller conferences, but this can lead to the isolation of various communities. We tackle this challenge by introducing a notion of group fairness, called core, which requires every subset of researchers to be treated in such a manner such that they cannot benefit from organizing a smaller conference on their own. We study a simple peer review model, prove that it always admits a reviewing assignment in the core, and design an efficient algorithm to find one such assignment. On the negative side, we show that the core is incompatible with achieving a good worstcase approximation of social welfare, an often-sought desideratum. We complement these results by conducting experiments with real data.