Newest papers

FairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food Recommendation

Kodur Sai Vinay Sathvik, Kakoli Bora, Tejaswini R. M · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31506 · cited by 0 works (OpenAlex) · open-access PDF

French

Les systèmes d'assignation de ressources fixes de smoender servent généralement un utilisateur à la fois. Cependant, dans les ménages, les membres partagent un pantry fini et suivent différentes règles diététiques, faisant des recommandations indépendantes susceptibles d'augmenter les conflits de ressources et les violations diététiques. Nous formulons des recommandations alimentaires ménagères en tant qu'attributions optimales de Shapley et de Banzhaf et présentons FairFRESH, un cadre neuro-symbolique qui apprend à se conformer à un seuil d'utilité diététique par membre, établit des garanties d'approximation pour toute la cupidité sous des objectifs de bien-être explicites, impose des règles diététiques à travers un filtre déterministe et

Machine translation (Meta M2M100); the English original follows.

Abstract

Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recommendations prone to resource conflicts and dietary violations. We formulate household food recommendation as constrained fair division and present FairFRESH, a neuro-symbolic framework that learns per-member utilities, allocates foods under explicit welfare objectives, enforces dietary rules through a deterministic filter, and explains recommendations using Shapley and Banzhaf attributions. Theoretically, we show that no finite penalty guarantees compliance near a dietary-rule threshold, establish approximation guarantees for greedy allocation under utilitarian and smoothed Nash objectives in the stock-free model before filtering, and characterize the scale invariance of Nash welfare. We also use the minimax theorem to analyze rotating shared meals. On NHANES-derived data, the learned utility model achieves Recall@20 of 0.293, outperforming five learned recommenders (at most 0.244) but not a previous-day repetition heuristic (0.321). On held-out four-person households, Nash allocation reduces Gini disparity by 42% relative to conflict resolution while improving Recall@20 from 0.180 to 0.197. It comes within 2% of an upper bound on the smoothed Nash optimum, and rescaling one member's utilities changes at most 1.5% of assignments. All recommendations satisfy the encoded dietary rules, while attribution scores correlate with utility loss upon component removal (r = 0.76). In simulation, shared meals reduce pantry use by about one-third, and weekly rotation increases the worst-off member's utility by 38% over the best fixed meal.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Fair division, Nash equilibrium, Best response, Computer science, Ranking (information retrieval), Resource allocation

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange