Towards Foundation Models for Consensus Rank Aggregation

TL;DR

This paper introduces the Kemeny Transformer, a reinforcement learning-based model that efficiently approximates the optimal consensus ranking under Kemeny distance, outperforming classical methods in speed and scalability.

Contribution

We develop a novel Transformer-based algorithm trained with reinforcement learning to approximate Kemeny optimal rankings efficiently.

Findings

Outperforms classical heuristic and Markov-chain methods

Achieves faster inference than ILP solvers

Provides a scalable solution for real-world ranking tasks

Abstract

Aggregating a consensus ranking from multiple input rankings is a fundamental problem with applications in recommendation systems, search engines, job recruitment, and elections. Despite decades of research in consensus ranking aggregation, minimizing the Kemeny distance remains computationally intractable. Specifically, determining an optimal aggregation of rankings with respect to the Kemeny distance is an NP-hard problem, limiting its practical application to relatively small-scale instances. We propose the Kemeny Transformer, a novel Transformer-based algorithm trained via reinforcement learning to efficiently approximate the Kemeny optimal ranking. Experimental results demonstrate that our model outperforms classical majority-heuristic and Markov-chain approaches, achieving substantially faster inference than integer linear programming solvers. Our approach thus offers a practical, scalable alternative for real-world ranking-aggregation tasks.