540 citations · 908 across the 23 of their papers we have counts for
9 papers · 1 filter
Defending from adversarial examples with a two-stream architecture
Hao Ge, Xiaoguang Tu, Mei Xie +1
In recent years, deep learning has shown impressive performance on many tasks. However, recent researches showed that deep learning systems are vulnerable to small, specially craft…
Haar Graph Pooling
Yu Guang Wang, Ming Li, Zheng Ma +3
Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs…
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Yuenan Hou, Zheng Ma, Chunxiao Liu +1
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context…
Fast Haar Transforms for Graph Neural Networks
Ming Li, Zheng Ma, Yu Guang Wang +1
Graph Neural Networks (GNNs) have become a topic of intense research recently due to their powerful capability in high-dimensional classification and regression tasks for graph-str…
Theory of the Frequency Principle for General Deep Neural Networks
Tao Luo, Zheng Ma, Zhi-Qin John Xu +1
Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Princip…
Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks
Yaoyu Zhang, Zhi-Qin John Xu, Tao Luo +1
It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit…
A type of generalization error induced by initialization in deep neural networks
Yaoyu Zhang, Zhi-Qin John Xu, Tao Luo +1
How initialization and loss function affect the learning of a deep neural network (DNN), specifically its generalization error, is an important problem in practice. In this work, b…
PAN: Path Integral Based Convolution for Deep Graph Neural Networks
Zheng Ma, Ming Li, Yuguang Wang
Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic…
Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
Zhi-Qin John Xu, Yaoyu Zhang, Tao Luo +2
We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) -- DNNs often…