Toggle Poster Visibility
Spotlight
Tue Jul 19 10:30 AM -- 10:35 AM (PDT) @ Ballroom 3 & 4
Meaningfully debugging model mistakes using conceptual counterfactual explanations
Spotlight
Tue Jul 19 10:35 AM -- 10:40 AM (PDT) @ Ballroom 3 & 4
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
Spotlight
Tue Jul 19 10:40 AM -- 10:45 AM (PDT) @ Ballroom 3 & 4
Robust Counterfactual Explanations for Tree-Based Ensembles
Spotlight
Tue Jul 19 10:45 AM -- 10:50 AM (PDT) @ Ballroom 3 & 4
A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions
Spotlight
Tue Jul 19 10:50 AM -- 10:55 AM (PDT) @ Ballroom 3 & 4
Estimating and Penalizing Induced Preference Shifts in Recommender Systems
Spotlight
Tue Jul 19 10:55 AM -- 11:00 AM (PDT) @ Ballroom 3 & 4
Framework for Evaluating Faithfulness of Local Explanations
[
Paper PDF]
Spotlight
Tue Jul 19 11:00 AM -- 11:05 AM (PDT) @ Ballroom 3 & 4
A Consistent and Efficient Evaluation Strategy for Attribution Methods
Oral
Tue Jul 19 11:05 AM -- 11:25 AM (PDT) @ Ballroom 3 & 4
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Spotlight
Tue Jul 19 11:25 AM -- 11:30 AM (PDT) @ Ballroom 3 & 4
Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
Spotlight
Tue Jul 19 11:30 AM -- 11:35 AM (PDT) @ Ballroom 3 & 4
XAI for Transformers: Better Explanations through Conservative Propagation
Spotlight
Tue Jul 19 11:35 AM -- 11:40 AM (PDT) @ Ballroom 3 & 4
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
Spotlight
Tue Jul 19 11:40 AM -- 11:45 AM (PDT) @ Ballroom 3 & 4
Interpretable Off-Policy Learning via Hyperbox Search
Spotlight
Tue Jul 19 11:45 AM -- 11:50 AM (PDT) @ Ballroom 3 & 4
Neuron Dependency Graphs: A Causal Abstraction of Neural Networks
Spotlight
Tue Jul 19 11:50 AM -- 11:55 AM (PDT) @ Ballroom 3 & 4
On the Adversarial Robustness of Causal Algorithmic Recourse
Spotlight
Tue Jul 19 11:55 AM -- 12:00 PM (PDT) @ Ballroom 3 & 4
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations