A Unified Framework for Scalable and Robust Paper Assignment

TL;DR

This paper introduces RAMP, a scalable and robust framework for paper-reviewer assignment that balances expertise, diversity, and strategic robustness efficiently for large conferences.

Contribution

The paper presents RAMP, a novel unified approach that combines linearized optimization with attribute-aware sampling to improve scalability, diversity, and robustness in large-scale peer review assignments.

Findings

RAMP handles over 20,000 papers and reviewers in under 20 minutes.

It effectively balances assignment quality, diversity, and robustness.

The framework is suitable for real-world large conference deployments.

Abstract

Assigning papers to reviewers is a central challenge in the peer-review process of large academic conferences. Program chairs must balance competing objectives, including maximizing reviewer expertise, promoting diversity, and enhancing robustness to strategic manipulation, but it is challenging to do so at the modern conference scale. Existing algorithmic paper assignment approaches either fail to address all of these goals simultaneously or suffer from poor scalability. To address the limitation, we propose Robust Assignment via Marginal Perturbation (RAMP), a unified framework for large-scale peer review. Our approach formulates a linearized perturbed-maximization objective with soft constraints that flexibly balance assignment quality, diversity, and robustness while maintaining runtime efficiency. We further introduce an attribute-aware sampling procedure that converts fractional solutions into integral assignments and improves the diversity and robustness of the final assignment. On datasets with over 20,000 papers and 20,000 reviewers, RAMP runs in under 20 minutes, demonstrating its suitability for real-world deployment.