Pith. sign in

REVIEW 4 cited by

Disentangling Interactions and Dependencies in Feature Attribution

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

arxiv 2410.23772 v1 pith:BSPOWMOH submitted 2024-10-31 cs.LG stat.ML

classification cs.LGstat.ML
keywords featureimportancecontributionsdependenciesfeaturesindividualinteractionsscores
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In explainable machine learning, global feature importance methods try to determine how much each individual feature contributes to predicting the target variable, resulting in one importance score for each feature. But often, predicting the target variable requires interactions between several features (such as in the XOR function), and features might have complex statistical dependencies that allow to partially replace one feature with another one. In commonly used feature importance scores these cooperative effects are conflated with the features' individual contributions, making them prone to misinterpretations. In this work, we derive DIP, a new mathematical decomposition of individual feature importance scores that disentangles three components: the standalone contribution and the contributions stemming from interactions and dependencies. We prove that the DIP decomposition is unique and show how it can be estimated in practice. Based on these results, we propose a new visualization of feature importance scores that clearly illustrates the different contributions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms

    stat.ME 2026-07 accept novelty 7.0 of 10

    Structural synergy, defined as the excess predictive power of a joint model over the best additive model, isolates non-additive interaction mechanisms from dependency-driven statistical synergy in complex systems.

  2. Information-theoretic Quantification of High-order Feature Effects in Classification Problems

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A kNN-based CMI estimator applied to classification decomposes feature importance into unique, redundant, and synergistic components, validated on synthetic and real data.

  3. Feature Attribution from First Principles

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Under linearity and a continuity assumption, every feature attribution method is an integral against a signed measure, so the design choice reduces to picking the measure.

  4. Saliency Maps are Ambiguous: Analysis of Logical Relations on First and Second Order Attributions

    cs.LG 2025-01 conditional novelty 4.0 of 10

    On synthetic AND/OR/XOR datasets with perfectly accurate models, every tested saliency method sometimes ranks a truly irrelevant input above a necessary one, so the scores cannot be trusted as relevance rankings.

Pith tools