16 citations · 59 across the 13 of their papers we have counts for
13 papers
Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification
Quanshi Zhang, Xu Cheng, Yilan Chen +1
Compared to traditional learning from scratch, knowledge distillation sometimes makes the DNN achieve superior performance. This paper provides a new perspective to explain the suc…
Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability
Quanshi Zhang, Xin Wang, Jie Ren +4
Although many methods have been proposed to enhance the transferability of adversarial perturbations, these methods are designed in a heuristic manner, and the essential mechanism…
Why Adversarial Training of ReLU Networks Is Difficult?
Xu Cheng, Hao Zhang, Yue Xin +3
This paper mathematically derives an analytic solution of the adversarial perturbation on a ReLU network, and theoretically explains the difficulty of adversarial training. Specifi…
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…
A Hypothesis for the Aesthetic Appreciation in Neural Networks
Xu Cheng, Xin Wang, Haotian Xue +2
This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order t…
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…
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…
Technical Note: Game-Theoretic Interactions of Different Orders
Hao Zhang, Xu Cheng, Yiting Chen +1
In this study, we define interaction components of different orders between two input variables based on game theory. We further prove that interaction components of different orde…
Building Interpretable Interaction Trees for Deep NLP Models
Die Zhang, Huilin Zhou, Hao Zhang +6
This paper proposes a method to disentangle and quantify interactions among words that are encoded inside a DNN for natural language processing. We construct a tree to encode salie…
Rotation-Equivariant Neural Networks for Privacy Protection
Hao Zhang, Yiting Chen, Haotian Ma +5
In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant…
Explaining Knowledge Distillation by Quantifying the Knowledge
Xu Cheng, Zhefan Rao, Yilan Chen +1
This paper presents a method to interpret the success of knowledge distillation by quantifying and analyzing task-relevant and task-irrelevant visual concepts that are encoded in i…
Learning High-order Structural and Attribute information by Knowledge Graph Attention Networks for Enhancing Knowledge Graph Embedding
Wenqiang Liu, Hongyun Cai, Xu Cheng +3
The goal of representation learning of knowledge graph is to encode both entities and relations into a low-dimensional embedding spaces. Many recent works have demonstrated the ben…
Initialization for Network Embedding: A Graph Partition Approach
Wenqing Lin, Feng He, Faqiang Zhang +2
Network embedding has been intensively studied in the literature and widely used in various applications, such as link prediction and node classification. While previous work focus…