most citedGraph Information Vanishing Phenomenon inImplicit Graph Neural Networks

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV20229 cited

TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning

Chao Tao, Ji Qia, Guo Zhang +3

Do we on the right way for remote sensing image understanding (RSIU) by training models via supervised data-dependent and task-dependent way, instead of human vision in a label-fre…

cs.LG2021

Curvature Graph Neural Network

Haifeng Li, Jun Cao, Jiawei Zhu +3

Graph neural networks (GNNs) have achieved great success in many graph-based tasks. Much work is dedicated to empowering GNNs with the adaptive locality ability, which enables meas…

cs.LG20211 cited

Graph Information Vanishing Phenomenon inImplicit Graph Neural Networks

Haifeng Li, Jun Cao, Jiawei Zhu +2

One of the key problems of GNNs is how to describe the importance of neighbor nodes in the aggregation process for learning node representations. A class of GNNs solves this proble…

cs.LG2018

Overcoming Catastrophic Forgetting by Soft Parameter Pruning

Jian Peng, Jiang Hao, Zhuo Li +5

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks…

cs.CV2018

Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection

Enqiang Guo, Xinsha Fu, Jiawei Zhu +4

A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to…

cs.SI2018

Measuring Road Network Topology Vulnerability by Ricci Curvature

Lei Gao, Xingquan Liu, Yu Liu +4

Describing the basic properties of road network systems, such as their robustness, vulnerability, and reliability, has been a very important research topic in the field of urban tr…