# EMERGENT: Efficient and Manipulation-resistant Matching using GFlowNets

arXiv: https://arxiv.org/abs/2506.12033 · HTML: https://mlsanity.com/paper/2506.12033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 7 of 7)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [Better Training of GFlowNets with Local Credit and Incomplete Trajectories](https://mlsanity.com/paper/2302.01687/) (2023)
- [Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets](https://mlsanity.com/paper/2203.03684/) (2022)
- [Learning to Elect](https://mlsanity.com/paper/2108.02768/) (2021)
- [School Choice as a One-Sided Matching Problem: Cardinal Utilities and Optimization](https://mlsanity.com/paper/1304.7413/) (2013)
- [Bounded Incentives in Manipulating the Probabilistic Serial Rule](https://mlsanity.com/paper/2001.10640/) (2020)

## Abstract (arXiv)

The design of fair and efficient algorithms for allocating public resources, such as school admissions, housing, or medical residency, has a profound social impact. In one-sided matching problems, where individuals are assigned to items based on ranked preferences, a fundamental trade-off exists between efficiency and strategyproofness. Existing algorithms like Random Serial Dictatorship (RSD), Probabilistic Serial (PS), and Rank Minimization (RM) capture only one side of this trade-off: RSD is strategyproof but inefficient, while PS and RM are efficient but incentivize manipulation. We propose EMERGENT, a novel application of Generative Flow Networks (GFlowNets) to one-sided matching, leveraging its ability to sample diverse, high-reward solutions. In our approach, efficient and manipulation-resistant matches emerge naturally: high-reward solutions yield efficient matches, while the stochasticity of GFlowNets-based outputs reduces incentives for manipulation. Experiments show that EMERGENT outperforms RSD in rank efficiency while significantly reducing strategic vulnerability compared to matches produced by RM and PS. Our work highlights the potential of GFlowNets for applications involving social choice mechanisms, where it is crucial to balance efficiency and manipulability.