paper-with-me

홈 › Papers

Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning

2021-02-28 · ICLR 2022 4 · Mark Hamilton, Scott Lundberg, Lei Zhang, Stephanie Fu, William T. Freeman

Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficult to interpret, and there are several competing techniques one can use to explain a search engine's behavior. We show that the theory of fair credit assignment provides a $\textit{unique}$ axiomatic solution that generalizes several existing recommendation- and metric-explainability techniques in the literature. Using this formalism, we show when existing approaches violate "fairness" and derive methods that sidestep these shortcomings and naturally handle counterfactual information. More specifically, we show existing approaches implicitly approximate second-order Shapley-Taylor indices and extend CAM, GradCAM, LIME, SHAP, SBSM, and other methods to search engines. These extensions can extract pairwise correspondences between images from trained $\textit{opaque-box}$ models. We also introduce a fast kernel-based method for estimating Shapley-Taylor indices that require orders of magnitude fewer function evaluations to converge. Finally, we show that these game-theoretic measures yield more consistent explanations for image similarity architectures.

📄 PDF Abstract BibTeX arXiv:2103.00370

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualFairnessImage RetrievalImage Similarity SearchRetrieval

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…
LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…
SHAP 설명 없음

Similar Papers 제목 키워드 기반

Towards Axiomatic Explanations for Neural Ranking Models

2021-06-15 · Michael Völske, Alexander Bondarenko, Maik Fröbe, Matthias Hagen 외

Recently, neural networks have been successfully employed to improve upon state-of-the-art performance in ad-hoc retrieval tasks via machine-learned ranking functions. While neural retrieval models grow in complexity and…

Document RankingInformation RetrievalRetrieval

ir_explain: a Python Library of Explainable IR Methods

2024-04-29 · Sourav Saha, Harsh Agarwal, V Venktesh, Avishek Anand 외

While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the use of large neural architectures and the …

Information RetrievalRetrieval

An Axiomatic Approach to Model-Agnostic Concept Explanations

2024-01-12 · Zhili Feng, Michal Moshkovitz, Dotan Di Castro, J. Zico Kolter

Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To addr…

Model Selection

Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions

2025-05-04 · Oliver Savolainen, Dur e Najaf Amjad, Roxana Petcu

This reproducibility study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models," which investigates how neural retrieval models encode t…

Information RetrievalRetrieval

Model Explanations via the Axiomatic Causal Lens

2021-09-08 · Gagan Biradar, Vignesh Viswanathan, Yair Zick

Explaining the decisions of black-box models is a central theme in the study of trustworthy ML. Numerous measures have been proposed in the literature; however, none of them take an axiomatic approach to causal explainab…

Feature Importancemodel