Pith. sign in

REVIEW 4 cited by

Understanding Global Feature Contributions With Additive Importance Measures

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2004.00668 v2 pith:6X5UCX6M submitted 2020-04-01 cs.LG stat.ML

Ian Covert , Scott Lundberg , Su-In Lee This is my paper · ORCID
classification cs.LGstat.ML
keywords featureimportancepowerpredictiveadditiveglobalmeasuresmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.

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. Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Conditional attribution retrieves contextually similar normal states from VAE latent spaces and UMAP embeddings to explain time-series anomalies while preserving dependencies, improving root-cause accuracy on SWaT and...

  2. Unifying Attribution-Based Explanations Using Functional Decomposition

    cs.LG 2024-12 reject novelty 6.0 of 10

    A unification framework for XAI attribution methods whose core canonical decomposition theorem fails because the components sum to the fully removed function rather than to the original function.

  3. 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.

  4. Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in Practice

    cs.CY 2024-12 conditional novelty 5.0 of 10

    A short educational workshop increased self-reported transparency literacy and advocacy willingness in a small, self-selected sample of professionals.

Pith tools