paper-with-me

Papers

Generalized Priority-Aware Shapley Value

2026-05-14 · Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang arxiv

Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to be binary and acyclic, a restriction spectacularly violated in real-data examples such as aggregated human preferences and multi-criterion comparisons. We introduce the generalized priority-aware Shapley value (GPASV), a random order value defined on arbitrary directed weighted priority graphs, in which pairwise edges penalize rather than forbid order violations. GPASV covers a range of classical models as boundary cases. We establish GPASV through an axiomatic characterization, develop the associated computational methods, and introduce a priority sweeping diagnostic extending PASV's. We apply GPASV to LLM ensemble valuation on the cyclic Chatbot Arena preference graph, illustrating that priority-aware valuation is not a one-button operation: different balances of pairwise graph priority versus individual soft priority produce substantively different valuations of the same data.

📄 PDF Abstract BibTeX arXiv:2605.15018

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Priority-Aware Shapley Value

2026-02-10 · Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang arxiv

Shapley values are widely used for model-agnostic data valuation and feature attribution, yet they implicitly assume contributors are interchangeable. This can be problematic when contributors are dependent (e.g., reused…

Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning

2026-03-14 · Adam Belahcen, Stéphane Mussard arxiv

We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features. Each hypercube is discret…

From Shapley Values to Generalized Additive Models and back

2022-09-08 · Sebastian Bordt, Ulrike Von Luxburg

In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. This work offers a partial reconciliation between the two by establishing…

Additive models

Computing Exact Shapley Values in Polynomial Time for Product-Kernel Methods

2025-05-22 · Majid Mohammadi, Siu Lun Chau, Krikamol Muandet

Kernel methods are widely used in machine learning due to their flexibility and expressive power. However, their black-box nature poses significant challenges to interpretability, limiting their adoption in high-stakes a…

Computational Efficiency

Fast Algorithms for Game-Theoretic Centrality Measures

2015-12-06 · Piotr Lech Szczepański

In this dissertation, we analyze the computational properties of game-theoretic centrality measures. The key idea behind game-theoretic approach to network analysis is to treat nodes as players in a cooperative game, whe…