REVIEW 4 cited by
Shapley explainability on the data manifold
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Explainability in AI is crucial for model development, compliance with regulation, and providing operational nuance to predictions. The Shapley framework for explainability attributes a model's predictions to its input features in a mathematically principled and model-agnostic way. However, general implementations of Shapley explainability make an untenable assumption: that the model's features are uncorrelated. In this work, we demonstrate unambiguous drawbacks of this assumption and develop two solutions to Shapley explainability that respect the data manifold. One solution, based on generative modelling, provides flexible access to data imputations; the other directly learns the Shapley value-function, providing performance and stability at the cost of flexibility. While "off-manifold" Shapley values can (i) give rise to incorrect explanations, (ii) hide implicit model dependence on sensitive attributes, and (iii) lead to unintelligible explanations in higher-dimensional data, on-manifold explainability overcomes these problems.
Forward citations
Cited by 4 Pith papers
-
Causal SHAP: Feature Attribution with Dependency Awareness through Causal Discovery
Causal SHAP replaces SHAP's independence assumption with a PC-discovered causal graph and IDA-derived causal strengths, zeroing out features that are correlated but not causal.
-
Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments
SILVER with RL-guided labeling: SHAP plus clustering plus policy-query labels plus decision trees or regression to interpret multi-action Atari policies.
-
ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Things
ShaTS computes Shapley attributions directly on semantic groups of time-series features, improving sensor- and process-level anomaly explanations over post hoc SHAP on the SWaT dataset.
-
Evaluating Explainable AI Methods for Geoscientific Regression: Insights from Applications and the Lorenz-63 System
A review plus Lorenz-63 illustration showing that classification-oriented XAI methods need careful baseline, off-manifold, and aggregation choices for geoscientific regression.
Discussion (0). Continue with ORCID to comment.