conftrace_

Neil Jethani

3 papers · 2021–2023 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14) ❓ The Questioner

Conferences

AISTATS (2) ICLR (1)

Top co-authors

Rajesh Ranganath (3) Mukund Sudarshan (2) Yindalon Aphinyanaphongs (1) Su-in Lee (1) Ian Connick Covert (1) Adriel Saporta (1)

Keywords

interpretable machine learning (1) feature importance (1) feature attribution (1) model explanation (1) shapley value (1) label leakage (1) amortized explanation (1) fidelity evaluation (1) class-dependent method (1) explanation method evaluation (1) distribution-aware method (1) selector model (1)

Papers

Don’t be fooled: label leakage in explanation methods and the importance of their quantitative evaluation AISTATS 2023 FastSHAP: Real-Time Shapley Value Estimation ICLR 2022 Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations. AISTATS 2021