Evaluating and Aggregating Feature-based Model Explanations
read the original abstract
A feature-based model explanation denotes how much each input feature contributes to a model's output for a given data point. As the number of proposed explanation functions grows, we lack quantitative evaluation criteria to help practitioners know when to use which explanation function. This paper proposes quantitative evaluation criteria for feature-based explanations: low sensitivity, high faithfulness, and low complexity. We devise a framework for aggregating explanation functions. We develop a procedure for learning an aggregate explanation function with lower complexity and then derive a new aggregate Shapley value explanation function that minimizes sensitivity.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Extremal Contours: Gradient-driven contours for compact visual attribution
A training-free method using Fourier-parameterized star-convex contours optimized via gradients to generate compact, faithful visual attributions for image classifiers on benchmarks like ImageNet.
-
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
A conditional invariance framework defines explanation fairness as explanations being statistically independent of protected attributes given task-relevant features, unifying existing metrics and enabling procedural b...
-
H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
H-Sets detects higher-order feature interactions in image classifiers via Hessian-guided pair merging and attributes them with IDG-Vis to generate more interpretable saliency maps than existing marginal or coarse methods.
-
Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2
AttnLRP explanations of DNABERT-2 reliably capture known biological patterns in genomic sequences, showing that transformer-based genome language models can yield biologically meaningful insights comparable to CNNs.
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
-
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.