Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

Interpretable Deepfake Detection via Dynamic Prototypes

Jun 28, 2020
Loc Trinh, Michael Tsang, Sirisha Rambhatla, Yan Liu


  Access Model/Code and Paper
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection

Jun 19, 2020
Michael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, Yan Liu

* Published in ICLR 2020 

  Access Model/Code and Paper
How does this interaction affect me? Interpretable attribution for feature interactions

Jun 19, 2020
Michael Tsang, Sirisha Rambhatla, Yan Liu


  Access Model/Code and Paper
Extracting Interpretable Concept-Based Decision Trees from CNNs

Jun 16, 2019
Conner Chyung, Michael Tsang, Yan Liu

* presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA 

  Access Model/Code and Paper
Can I trust you more? Model-Agnostic Hierarchical Explanations

Dec 12, 2018
Michael Tsang, Youbang Sun, Dongxu Ren, Yan Liu


  Access Model/Code and Paper
Detecting Statistical Interactions from Neural Network Weights

Feb 27, 2018
Michael Tsang, Dehua Cheng, Yan Liu

* Published in ICLR 2018 

  Access Model/Code and Paper