2024 Poster "explainable ai" Papers
10 papers found
Attribution-based Explanations that Provide Recourse Cannot be Robust
Hidde Fokkema, Rianne de Heide, Tim van Erven
ICML 2024posterarXiv:2205.15834
Counterfactual Metarules for Local and Global Recourse
Tom Bewley, Salim I. Amoukou, Saumitra Mishra et al.
ICML 2024posterarXiv:2405.18875
EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
Shengyao Lu, Bang Liu, Keith Mills et al.
ICML 2024poster
Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
Zhuomin Chen, Jiaxing Zhang, Jingchao Ni et al.
ICML 2024poster
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
Amin Parchami, Moritz Böhle, Sukrut Rao et al.
ECCV 2024posterarXiv:2402.03119
18
citations
Graph Neural Network Explanations are Fragile
Jiate Li, Meng Pang, Yun Dong et al.
ICML 2024poster
Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen et al.
ICML 2024posterarXiv:2405.09800
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
Yi Cai, Gerhard Wunder
ICML 2024posterarXiv:2308.09381
Position: Do Not Explain Vision Models Without Context
Paulina Tomaszewska, Przemyslaw Biecek
ICML 2024posterarXiv:2404.18316
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
Hengyi Wang, Shiwei Tan, Hao Wang
ICML 2024poster