Weighted Envy-free Allocation with Subsidy

Haris Aziz (UNSW), Xin Huang (Kyushu University), Kei Kimura (Kyushu University), Indrajit Saha (Kyushu University), Zhaohong Sun (Kyushu University), Mashbat Suzuki (UNSW), Makoto Yokoo (Kyushu University)

Abstract

We consider the problem of fair allocation of indivisible items with subsidies when agents have weighted entitlements. Specifically, we extend the envy-freeability studied in the unweighted case to the weighted envy-freeability and delve deeper into its properties. We first highlight various important differences from the unweighted case, e.g., the sufficient conditions that lead to envy-freeability in the unweighted case do not lead to weighted envy-freeability in the weighted case. We then present various results concerning weighted envy-freeability including general characterizations, algorithms for achieving and testing weighted envy-freeability, lower and upper bounds of the amount of subsidies for weighted envy-freeable allocations. Additionally, we design algorithms that ensure weighted envy-freeability while incorporating other fairness properties, such as weighted envy-freeness up to one item transfer.