Filter by Keyword:

46 Results

Poster
Mon 1:00 Interpreting and Boosting Dropout from a Game-Theoretic View
Hao Zhang, Sen Li, YinChao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
Poster
Mon 1:00 A Unified Approach to Interpreting and Boosting Adversarial Transferability
Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang
Poster
Mon 1:00 Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability
Suraj Srinivas, François Fleuret
Oral
Mon 5:30 Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability
Suraj Srinivas, François Fleuret
Poster
Mon 9:00 Using latent space regression to analyze and leverage compositionality in GANs
Lucy Chai, Jonas Wulff, Phillip Isola
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
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
Mon 9:00 The role of Disentanglement in Generalisation
Milton Montero, Casimir JH Ludwig, Rui Ponte Costa, Gaurav Malhotra, Jeffrey Bowers
Poster
Mon 9:00 Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
Matthew Leavitt, Ari Morcos
Poster
Mon 17:00 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Lily Weng, Chuang Gan, Meng Wang
Poster
Tue 1:00 Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Judy Borowski, Roland Zimmermann, Judith Schepers, Robert Geirhos, Thomas S Wallis, Matthias Bethge, Wieland Brendel
Spotlight
Tue 3:25 Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Michael Schlichtkrull, Nicola De Cao, Ivan Titov
Poster
Tue 9:00 DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan Black, Yulia Tsvetkov
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
Poster
Tue 9:00 Physics-aware, probabilistic model order reduction with guaranteed stability
Sebastian Kaltenbach, PS Koutsourelakis
Poster
Tue 9:00 The geometry of integration in text classification RNNs
Kyle Aitken, Vinay Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan
Poster
Tue 9:00 Tradeoffs in Data Augmentation: An Empirical Study
Rapha Gontijo Lopes, Sylvia Smullin, Ekin Cubuk, Ethan Dyer
Expo Talk Panel
Tue 14:00 Interpretability with skeptical and user-centric mind
Been Kim
Poster
Tue 17:00 Debiasing Concept-based Explanations with Causal Analysis
Taha Bahadori, David Heckerman
Poster
Tue 17:00 Monotonic Kronecker-Factored Lattice
William Bakst, Nobuyuki Morioka, Erez Louidor
Poster
Wed 1:00 Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
Yuan Yin, Vincent Le Guen, Jérémie DONA, Emmanuel d Bezenac, Ibrahim Ayed, Nicolas THOME, patrick gallinari
Poster
Wed 1:00 Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
Binxin Ru, Xingchen Wan, Xiaowen Dong, Michael Osborne
Poster
Wed 1:00 Explainable Deep One-Class Classification
Philipp Liznerski, Lukas Ruff, Robert A Vandermeulen, Billy J Franks, Marius Kloft, Klaus R Muller
Oral
Wed 4:05 Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández Lobato
Poster
Wed 9:00 Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Michael Schlichtkrull, Nicola De Cao, Ivan Titov
Poster
Wed 9:00 Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Robert Csordas, Sjoerd van Steenkiste, Jürgen Schmidhuber
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 BERTology Meets Biology: Interpreting Attention in Protein Language Models
Jesse Vig, Ali Madani, Lav R Varshney, Caiming Xiong, Richard Socher, Nazneen Rajani
Poster
Wed 17:00 Evaluations and Methods for Explanation through Robustness Analysis
Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep K Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh
Poster
Wed 17:00 Influence Functions in Deep Learning Are Fragile
Samyadeep Basu, Phil Pope, Soheil Feizi
Poster
Wed 17:00 Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
Sharon Zhou, Eric Zelikman, Fred Lu, Andrew Ng, Gunnar E Carlsson, Stefano Ermon
Poster
Wed 17:00 NBDT: Neural-Backed Decision Tree
Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Suzanne Petryk, Sarah A Bargal, Joseph E Gonzalez
Poster
Wed 17:00 A Geometric Analysis of Deep Generative Image Models and Its Applications
Binxu Wang, Carlos Ponce
Poster
Thu 1:00 Interpretable Models for Granger Causality Using Self-explaining Neural Networks
Ričards Marcinkevičs, Julia E Vogt
Oral
Thu 4:20 Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
Yuan Yin, Vincent Le Guen, Jérémie DONA, Emmanuel d Bezenac, Ibrahim Ayed, Nicolas THOME, patrick gallinari
Poster
Thu 17:00 Multi-timescale Representation Learning in LSTM Language Models
Shivangi Mahto, Vy Vo, Javier Turek, Alexander Huth
Poster
Thu 17:00 A Learning Theoretic Perspective on Local Explainability
Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
Poster
Thu 17:00 Evaluation of Similarity-based Explanations
Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui
Poster
Thu 17:00 Prototypical Representation Learning for Relation Extraction
Ning Ding, Xiaobin Wang, Yao Fu, Guangwei Xu, Rui Wang, Pengjun Xie, Ying Shen, Fei Huang, Hai-Tao Zheng, Rui Zhang
Poster
Thu 17:00 Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
Mangal Prakash, Alexander Krull, Florian Jug
Poster
Thu 17:00 Convex Regularization behind Neural Reconstruction
Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M Pauly
Workshop
Fri 3:25 Do Input Gradients Highlight Discriminative Features?
Harshay Shah
Workshop
Fri 6:00 AIMOCC -- AI: Modeling Oceans and Climate Change
Luis Martí, Nayat Sánchez-Pi
Workshop
Fri 6:45 Responsible AI (RAI)
Ahmad Beirami, Emily Black, Krishna Gummadi, Hoda Heidari, Baharan Mirzasoleiman, Meisam Razaviyayn, Joshua Williams
Workshop
Fri 7:00 Interpretable Recommender System With Heterogeneous Information: A Geometric Deep Learning Perspective
Yan Leng
Workshop
Fri 10:30 Gal Mishne: Visualizing the PHATE of deep neural networks
Gal Mishne