Learning to Elect

TL;DR

This paper demonstrates that set-input neural networks can learn, mimic, and discover voting rules that optimize social welfare, generalizing well across different scenarios and election sizes.

Contribution

It introduces neural network architectures capable of automatically learning and discovering voting rules tailored to specific social welfare objectives.

Findings

Neural networks can accurately mimic existing voting rules.

They can discover near-optimal voting rules for maximizing social welfare.

The learned rules generalize across different utility distributions and election sizes.

Abstract

Voting systems have a wide range of applications including recommender systems, web search, product design and elections. Limited by the lack of general-purpose analytical tools, it is difficult to hand-engineer desirable voting rules for each use case. For this reason, it is appealing to automatically discover voting rules geared towards each scenario. In this paper, we show that set-input neural network architectures such as Set Transformers, fully-connected graph networks and DeepSets are both theoretically and empirically well-suited for learning voting rules. In particular, we show that these network models can not only mimic a number of existing voting rules to compelling accuracy -- both position-based (such as Plurality and Borda) and comparison-based (such as Kemeny, Copeland and Maximin) -- but also discover near-optimal voting rules that maximize different social welfare functions. Furthermore, the learned voting rules generalize well to different voter utility distributions and election sizes unseen during training.