16 citations · 60 across the 13 of their papers we have counts for
7 papers · 1 filter
Trap of Feature Diversity in the Learning of MLPs
Dongrui Liu, Shaobo Wang, Jie Ren +4
In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity…
A Unified Game-Theoretic Interpretation of Adversarial Robustness
Jie Ren, Die Zhang, Yisen Wang +8
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. B…
Discovering and Explaining the Representation Bottleneck of DNNs
Huiqi Deng, Qihan Ren, Hao Zhang +1
This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded…
Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
Quanshi Zhang, Tian Han, Lixin Fan +5
This is the Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. Deep neural networks (DNNs) have undoubtedly brought grea…
A Game-Theoretic Taxonomy of Visual Concepts in DNNs
Xu Cheng, Chuntung Chu, Yi Zheng +2
In this paper, we rethink how a DNN encodes visual concepts of different complexities from a new perspective, i.e. the game-theoretic multi-order interactions between pixels in an…
Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
Jie Ren, Yewen Li, Zihan Ding +2
Deep reinforcement learning (DRL) has successfully solved various problems recently, typically with a unimodal policy representation. However, grasping distinguishable skills for s…
A Unified Game-Theoretic Interpretation of Adversarial Robustness
Jie Ren, Die Zhang, Yisen Wang +8
This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on…