paper-with-me

Papers

Learning to Estimate Shapley Values with Vision Transformers

2022-06-10 · Ian Covert, Chanwoo Kim, Su-In Lee

Transformers have become a default architecture in computer vision, but understanding what drives their predictions remains a challenging problem. Current explanation approaches rely on attention values or input gradients, but these provide a limited view of a model's dependencies. Shapley values offer a theoretically sound alternative, but their computational cost makes them impractical for large, high-dimensional models. In this work, we aim to make Shapley values practical for vision transformers (ViTs). To do so, we first leverage an attention masking approach to evaluate ViTs with partial information, and we then develop a procedure to generate Shapley value explanations via a separate, learned explainer model. Our experiments compare Shapley values to many baseline methods (e.g., attention rollout, GradCAM, LRP), and we find that our approach provides more accurate explanations than existing methods for ViTs.

📄 PDF Abstract BibTeX arXiv:2206.05282

Code (2)

suinleelab/vit-shapley 공식 구현 pytorch
suinleelab/shapley_algorithms

Similar Papers 제목 키워드 기반

Shapley Value Approximation Based on k-Additive Games

2025-02-07 · Guilherme Dean Pelegrina, Patrick Kolpaczki, Eyke Hüllermeier

The Shapley value is the prevalent solution for fair division problems in which a payout is to be divided among multiple agents. By adopting a game-theoretic view, the idea of fair division and the Shapley value can also…

Efficient Shapley Values Estimation by Amortization for Text Classification

2023-05-31 · Chenghao Yang, Fan Yin, He He, Kai-Wei Chang 외

Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values …

Classificationtext-classificationText Classification

A Multilinear Sampling Algorithm to Estimate Shapley Values

2020-10-22 · Ramin Okhrati, Aldo Lipani

Shapley values are great analytical tools in game theory to measure the importance of a player in a game. Due to their axiomatic and desirable properties such as efficiency, they have become popular for feature importanc…

BIG-bench Machine LearningFeature Importance

Exactly Computing do-Shapley Values

2026-02-06 · R. Teal Witter, Álvaro Parafita, Tomas Garriga, Maximilian Muschalik 외 arxiv

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifyi…

Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features

2021-11-26 · Lars Henry Berge Olsen, Ingrid Kristine Glad, Martin Jullum, Kjersti Aas

Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical fou…

BIG-bench Machine Learning