From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
cs.LG, cs.AI, cs.CV
Submitted: 2026-03-05
Updated: 2026-11-07
Code: https://github.com/cenweizhang/OTFlowSHAP
Terminology
Sources
- Using the Path of Least Resistance to Explain Deep Networks
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Flow Matching for Generative Modeling
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- SmoothGrad: removing noise by adding noise
- Striving for Simplicity: The All Convolutional Net
- Denoising Diffusion Implicit Models
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Shapley explainability on the data manifold
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning