Abductive and Contrastive Explanations for Scoring Rules in Voting
This work addresses the need for interpretable decision-making in computational social choice, offering incremental improvements by adapting existing explainability methods to voting contexts.
The paper tackles the problem of explaining voting outcomes by applying formal explainability techniques to voting rules, treating them as classifiers. It designs algorithms for computing abductive and contrastive explanations for scoring rules, with results including a lower bound on explanation size for Borda and simulations showing correlations between profile properties and explanation size.
We view voting rules as classifiers that assign a winner (a class) to a profile of voters' preferences (an instance). We propose to apply techniques from formal explainability, most notably abductive and contrastive explanations, to identify minimal subsets of a preference profile that either imply the current winner or explain why a different candidate was not elected. Formal explanations turn out to have strong connections with classical problems studied in computational social choice such as bribery, possible and necessary winner identification, and preference learning. We design algorithms for computing abductive and contrastive explanations for scoring rules. For the Borda rule, we find a lower bound on the size of the smallest abductive explanations, and we conduct simulations to identify correlations between properties of preference profiles and the size of their smallest abductive explanations.