Allocation Multiplicity: Evaluating the Promises of the Rashomon Set

Abstract

The Rashomon set of equally-good models promises less discriminatory algorithms, reduced outcome homogenization, and fairer decisions through model ensembles or reconciliation. However, we argue from the perspective of allocation multiplicity that these promises may remain unfulfilled. When there are more qualified candidates than resources available, many different allocations of scarce resources can achieve the same utility. This space of equal-utility allocations may not be faithfully reflected by the Rashomon set, as we show in a case study of healthcare allocations. We attribute these unfulfilled promises to several factors: limitations in empirical methods for sampling from the Rashomon set, the standard practice of deterministically selecting individuals with the lowest risk, and structural biases that cause all equally-good models to view some qualified individuals as inherently risky.

To appear in the proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT 2025)

References in corpus (6)

• Algorithmic Monoculture and Social Welfare
• On The Impact of Machine Learning Randomness on Group Fairness
• Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
• Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints
• Algorithmic Pluralism: A Structural Approach To Equal Opportunity
• One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions