Skip to content
OpenTrain AIFor AI Companies

FastSHAP: Real-Time Shapley Value Estimation

Neil Jethani, Mukund Sudarshan, Ian Covert, Su‐In Lee, Rajesh RanganathPublished Jul 15, 2021
DOI Publisher
Researcher verdict
Context only
Use as context only
Benchmark evidence
Missing
Not verified yet
Time to first repro
A few hours
Fast first run
Risk flags
1
Review before use

Abstract

Domain fit: Niche / domain-specific · No strong AI-core implementation/artifact signals were detected from current providers.

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders of magnitude speedup.

Results and benchmarks

Freshness tier: cold
Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations.

Implementation

No direct implementation yet

Maintained implementation evidence is not confirmed for this paper yet.

Use the implementation status and reproduction sections for the current action plan.

Implementation evidence summary
Confidence: low

This is primarily a method paper. Reproduce it within a maintained framework baseline instead of chasing paper-specific repos.

Reproduction risks
  • No maintained paper-verified implementation is currently available

Reproduction readiness

Time to first repro: hours
Last checked: Aug 25, 2026

No repo

No verified implementation available

  • No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.

Hugging Face artifacts

No trustworthy direct or curated related Hugging Face artifacts were found yet. Use targeted searches to quickly locate candidate models, datasets, and demos.

Tip: start with models, then check datasets and spaces if you need evaluation data or demos.

Research context

2

Citations

34

References

Tasks

Shapley value, Speedup, Computer science, Least-squares function approximation, Black box, Physical Sciences

Methods

Mathematical optimization

Domains

Value (mathematics), Mathematics, Artificial Intelligence

Evaluation and human feedback data

Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.

Open in HFEPX
Explore similar papers