Spotlight Session

Tue 10:30

SA: Accountability, Transparency and Interpretability

Poster

Thu 15:00

A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
Weichao Zhou · Wenchao Li

Spotlight

Thu 8:40

A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
Weichao Zhou · Wenchao Li

Poster

Wed 15:30

Label-Free Explainability for Unsupervised Models
Jonathan Crabbé · Mihaela van der Schaar

Poster

Tue 15:30

Meaningfully debugging model mistakes using conceptual counterfactual explanations
Abubakar Abid · Mert Yuksekgonul · James Zou

Spotlight

Wed 7:35

Label-Free Explainability for Unsupervised Models
Jonathan Crabbé · Mihaela van der Schaar

Poster

Tue 15:30

A Consistent and Efficient Evaluation Strategy for Attribution Methods
Yao Rong · Tobias Leemann · Vadim Borisov · Gjergji Kasneci · Enkelejda Kasneci

Poster

Tue 15:30

Robust Models Are More Interpretable Because Attributions Look Normal
Zifan Wang · Matt Fredrikson · Anupam Datta

Spotlight

Tue 7:40

Robust Models Are More Interpretable Because Attributions Look Normal
Zifan Wang · Matt Fredrikson · Anupam Datta

Spotlight

Tue 11:00

A Consistent and Efficient Evaluation Strategy for Attribution Methods
Yao Rong · Tobias Leemann · Vadim Borisov · Gjergji Kasneci · Enkelejda Kasneci

Spotlight

Tue 10:30

Meaningfully debugging model mistakes using conceptual counterfactual explanations
Abubakar Abid · Mert Yuksekgonul · James Zou

Poster

Thu 15:00

Global Optimization Networks
Sen Zhao · Erez Louidor · Maya Gupta