Research map / Learning theory and algorithms / Prediction and decision losses
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DASP uncertainty propagation to approximate Shapley values | DASP · Parkinsons Telemonitoring test samples | Shapley-value approximation quality | Helped |
| Use DASP rather than sampling-based Shapley approximators | Parkinsons Telemonitoring test samples · Parkinsons Telemonitoring test samples | network evaluations at comparable approximation quality | Helped |
| Use DASP rather than backpropagation-based attribution methods | DNA sequence classification · DNA Sequences | Shapley-value approximation quality | Helped |
| Use DASP rather than KernelSHAP | DNA sequence classification · DNA Sequences | network evaluations at comparable rank correlation | Helped |
| Use DASP rather than biased attribution approximators | MNIST classification · MNIST | Shapley-value approximation accuracy | Helped |
| Use DASP rather than Shapley sampling or KernelSHAP | MNIST classification · MNIST | network evaluations at comparable performance | Helped |
| Use KernelSHAP rather than simple Shapley sampling | MNIST classification · MNIST | Shapley-value approximation quality | Hurt |
Closest papers by meaning
- Shapley Explanation Networks (ICLR 2021 · similarity 0.89)
- shapiq: Shapley Interactions for Machine Learning (NeurIPS 2024 · similarity 0.87)
- Approximating the Shapley Value without Marginal Contributions (AAAI 2024 · similarity 0.86)
- Explaining Probabilistic Models with Distributional Values (ICML 2024 · similarity 0.85)
- Provably Accurate Shapley Value Estimation via Leverage Score Sampling (ICLR 2025 · similarity 0.85)
- Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.