|
Poster
|
Tue 9:00 |
Tradeoffs in Data Augmentation: An Empirical Study Raphael Gontijo Lopes · Sylvia Smullin · Ekin Cubuk · Ethan Dyer |
|
|
Poster
|
Mon 9:00 |
Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization Joshua Chang · Patrick A Fletcher · Jungmin Han · Ted Chang · Shashaank Vattikuti · Bart Desmet · Ayah Zirikly · Carson Chow |
|
|
Poster
|
Wed 1:00 |
Explainable Deep One-Class Classification Philipp Liznerski · Lukas Ruff · Robert A Vandermeulen · Billy J Franks · Marius Kloft · Klaus R Muller |
|
|
Poster
|
Tue 1:00 |
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization Judith Borowski · Roland Zimmermann · Judith Schepers · Robert Geirhos · Thomas S Wallis · Matthias Bethge · Wieland Brendel |
|
|
Poster
|
Mon 9:00 |
Using latent space regression to analyze and leverage compositionality in GANs Lucy Chai · Jonas Wulff · Phillip Isola |
|
|
Poster
|
Tue 9:00 |
DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues Rishabh Joshi · Vidhisha Balachandran · Shikhar Vashishth · Alan Black · Yulia Tsvetkov |
|
|
Oral
|
Mon 5:30 |
Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability Suraj Srinivas · François Fleuret |
|
|
Expo Talk Panel
|
Tue 14:00 |
Interpretability with skeptical and user-centric mind Been Kim |
|
|
Poster
|
Mon 9:00 |
Representation learning for improved interpretability and classification accuracy of clinical factors from EEG Garrett Honke · Irina Higgins · Nina Thigpen · Vladimir Miskovic · Katie Link · Sunny Duan · Pramod Gupta · Julia Klawohn · Greg Hajcak |
|
|
Poster
|
Wed 17:00 |
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation Mrigank Raman · Aaron Chan · Siddhant Agarwal · PeiFeng Wang · Hansen Wang · Sungchul Kim · Ryan Rossi · Handong Zhao · Nedim Lipka · Xiang Ren |
|
|
Poster
|
Wed 17:00 |
Influence Functions in Deep Learning Are Fragile Samyadeep Basu · Phil Pope · Soheil Feizi |
|
|
Poster
|
Tue 9:00 |
Getting a CLUE: A Method for Explaining Uncertainty Estimates Javier Antorán · Umang Bhatt · Tameem Adel · Adrian Weller · José Miguel Hernández Lobato |