Feature Attribution

Feature attribution studies how to assign responsibility for a model’s prediction to parts of its input, such as image regions, text tokens, time-series measurements, or graph features. Common approaches include gradients and relevance propagation, perturbation and masking, Shapley values, and counterfactual or causal interventions; some methods instead build explanations into the model. Researchers evaluate explanations for faithfulness, stability, sparsity, localization, and usefulness across tasks such as image classification, language modeling, medical prediction, and time-series forecasting. A central challenge is that attributions can change with the model architecture, baseline, perturbation choices, or correlations among features, so no single method or metric is reliable in every setting.