DeepVoting: Learning and Fine-Tuning Voting Rules with Canonical Embeddings

Aggregating agent preferences into a collective decision is an important step in many problems (e.g., hiring, elections, peer review) and across areas of computer science (e.g., reinforcement learning, recommender systems). As Social Choice Theory has shown, the problem of designing aggregation rules with specific sets of properties (axioms) can be difficult, or provably impossible in some cases. Instead of designing algorithms by hand, one can learn aggregation rules, particularly voting rules, from data. However, prior work in this area has required extremely large models or been limited by the choice of preference representation, i.e., embedding. We recast the problem of designing voting rules with desirable properties into one of learning probabilistic functions that output distributions over a set of candidates. Specifically, we use neural networks to learn probabilistic social choice functions. Using standard embeddings from the social choice literature we show that preference profile encoding has significant impact on the efficiency and ability of neural networks to learn rules, allowing us to learn rules faster and with smaller networks than previous work. Moreover, we show that our learned rules can be fine-tuned using axiomatic properties to create novel voting rules and make them resistant to specific types of "attack". Namely, we fine-tune rules to resist a probabilistic version of the No Show Paradox.