649 citations · 1.7k across the 57 of their papers we have counts for
7 papers · 1 filter
Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows
Junchi Yu, Tingyang Xu, Ran He
As Graph Neural Networks (GNNs) are widely adopted in digital pathology, there is increasing attention to developing explanation models (explainers) of GNNs for improved transparen…
Local Augmentation for Graph Neural Networks
Songtao Liu, Rex Ying, Hanze Dong +6
Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating informatio…
Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions
Xuefeng Du, Tian Bian, Yu Rong +6
Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently u…
Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning
Yatao Bian, Yu Rong, Tingyang Xu +3
Valuation problems, such as feature interpretation, data valuation and model valuation for ensembles, become increasingly more important in many machine learning applications. Such…
Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
Heng Chang, Yu Rong, Tingyang Xu +6
With the success of the graph embedding model in both academic and industry areas, the robustness of graph embedding against adversarial attack inevitably becomes a crucial problem…
Recognizing Predictive Substructures with Subgraph Information Bottleneck
Junchi Yu, Tingyang Xu, Yu Rong +3
The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack…
Diversified Multiscale Graph Learning with Graph Self-Correction
Yuzhao Chen, Yatao Bian, Jiying Zhang +4
Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, the classic ensemble strategy may show inferior performance while encountering…