FastSHAP: Real-Time Shapley Value Estimation
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
Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations.
Benchmark evidence is limited
Evidence graph: 2 refs, 1 links.
Utility signals: depth 60/100, grounding 58/100, status medium.
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.
No verified maintained repo yet
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- This is primarily a method paper. Reproduce it within a maintained framework baseline instead of chasing paper-specific repos.
- Start with framework-native implementations (e.g. PyTorch optimizer module, Optax, or Transformers training loops).
- Replicate the paper ablation settings first, then compare against modern baselines.
Time to first repro: a few hours
This is primarily a method paper. Reproduce it within a maintained framework baseline instead of chasing paper-specific repos.
- No maintained paper-verified implementation is currently available
Reproduction readiness
No repo
No verified implementation available
- No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
Validation caveat
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
Related papers
- An Empirical and Comparative Analysis of Data Valuation with Scalable AlgorithmsSearch on Paper2Code
2019 · Semantic similarity
- A Projected Stochastic Gradient Algorithm for Estimating Shapley Value Applied in Attribute ImportanceSearch on Paper2Code
2020 · Semantic similarity
- Explaining Deep Neural Networks with a Polynomial Time Algorithm for\n Shapley Values ApproximationSearch on Paper2Code
2019 · Semantic similarity
- Computing Shapley Effects for Sensitivity AnalysisSearch on Paper2Code
2021 · Semantic similarity
- Shapley Decomposition of R-Squared in Machine Learning ModelsSearch on Paper2Code
2019 · Semantic similarity
- L-Shapley and C-Shapley: Efficient Model Interpretation for Structured DataSearch on Paper2Code
2018 · Semantic similarity
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXJump to Paper2Code search queries derived from this paper's research context.