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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

GCI: A (G)raph (C)oncept (I)nterpretation Framework


Feb 09, 2023
Dmitry Kazhdan, Botty Dimanov, Lucie Charlotte Magister, Pietro Barbiero, Mateja Jamnik, Pietro Lio

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations


Nov 14, 2022
Shea Cardozo, Gabriel Islas Montero, Dmitry Kazhdan, Botty Dimanov, Maleakhi Wijaya, Mateja Jamnik, Pietro Lio

Add code

* Presented at the AIMLAI workshop at the 31st ACM International Conference on Information and Knowledge Management (CIKM 2022) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Failing Conceptually: Concept-Based Explanations of Dataset Shift


May 01, 2021
Maleakhi A. Wijaya, Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik

Add code

* ICLR 2021 Workshop (RobustML), 16 pages, 14 figures; typos corrected 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches


Apr 14, 2021
Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre, Mateja Jamnik, Pietro Liò, Adrian Weller

Add code

* Presented at the RAI, WeaSul, and RobustML workshops at The Ninth International Conference on Learning Representations (ICLR) 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MEME: Generating RNN Model Explanations via Model Extraction


Dec 13, 2020
Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò

Add code

* Presented at the HAMLETS workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Now You See Me (CME): Concept-based Model Extraction


Oct 25, 2020
Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò, Adrian Weller

Add code

* Presented at the AIMLAI workshop at the 29th ACM International Conference on Information and Knowledge Management (CIKM 2020) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email