arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01653cs.LGcs.AIcs.MAcs.SI
收藏

利用对抗性GNNs学习抗毁选举

Learning Resilient Elections with Adversarial GNNs

University of Cambridge(剑桥大学);CERN(欧洲核子研究组织)

Hao Xiang Li, Yash Shah, Lorenzo Giusti

AI总结:

本文提出利用对抗性GNNs学习抗毁选举,通过改进神经网络架构与对抗训练提高投票规则的鲁棒性并最大化社会福利。

摘要:

在面临恶意动机时,达成共识是必不可少的。选举自17世纪以来一直是现代民主运作的典型方式。如今,它们监管市场,为现代推荐系统或点对点网络提供引擎,并仍然是代表民主的主要方法。然而,一种能够满足所有假设场景的理想的通用投票规则仍然是一项具有挑战性的课题,这些系统的设计处于机制设计研究的前沿。自动机制设计是一种有前途的方法,最近的研究表明,集合不变的架构 uniquely 适合于建模选举系统。然而,各种担忧阻碍了将其直接应用于现实世界设置,例如对战略投票的鲁棒性。在本文中,我们扩展了学习投票规则的表达能力,并结合神经网络架构的改进与对抗性训练,以提高投票规则的鲁棒性并最大化社会福利。我们在合成和现实世界数据集上评估了我们方法的有效性。我们的方法通过将选举表示为二分图,并使用图神经网络学习此类投票规则,解决了先前工作在学习投票规则方面的关键限制。我们相信这为将机器学习应用于现实世界选举开辟了新前景。

英文摘要:

In the face of adverse motives, it is indispensable to achieve a consensus. Elections have been the canonical way by which modern democracy has operated since the 17th century. Nowadays, they regulate markets, provide an engine for modern recommender systems or peer-to-peer networks, and remain the main approach to represent democracy. However, a desirable universal voting rule that satisfies all hypothetical scenarios is still a challenging topic, and the design of these systems is at the forefront of mechanism design research. Automated mechanism design is a promising approach, and recent works have demonstrated that set-invariant architectures are uniquely suited to modelling electoral systems. However, various concerns prevent the direct application to real-world settings, such as robustness to strategic voting. In this paper, we generalise the expressive capability of learned voting rules, and combine improvements in neural network architecture with adversarial training to improve the resilience of voting rules while maximizing social welfare. We evaluate the effectiveness of our methods on both synthetic and real-world datasets. Our method resolves critical limitations of prior work regarding learning voting rules by representing elections using bipartite graphs, and learning such voting rules using graph neural networks. We believe this opens new frontiers for applying machine learning to real-world elections.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑