Residual Graph Convolutional Network

Residual Graph Convolutional Networks (ResGCNs) aim to improve the performance and depth of graph neural networks (GNNs) by incorporating residual connections, addressing the common problem of oversmoothing in deep GNN architectures. Current research focuses on mitigating gradient oversmoothing and expansion through novel normalization techniques and dynamic residual mechanisms, as well as exploring applications in diverse fields like brain connectivity prediction, UAV detection, and biomedical interaction discovery. The development of more effective and efficient ResGCNs holds significant promise for advancing various applications requiring analysis of graph-structured data, improving accuracy and scalability in tasks ranging from image segmentation to text classification.

Papers

October 7, 2024

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
MoonJeong Park, Dongwoo Kim
Graph Neural Network Gradient Flow Prompt Expansion Gradient Approximation Squashing Mitigation Approach Residual Graph Convolutional Network

September 30, 2024

Graph Residual Noise Learner Network for Brain Connectivity Graph Prediction
Oytun Demirbilek, Tingying Peng, Alaa Bessadok
Residual Graph Convolutional Network Connectivity Matrix Brain Graph Graph Diffusion Model Brain Imaging to Graph Generation

July 17, 2024

Fusion Flow-enhanced Graph Pooling Residual Networks for Unmanned Aerial Vehicles Surveillance in Day and Night Dual Visions
Alam Noor, Kai Li, Eduardo Tovar, Pei Zhang, Bo Wei
Unmanned Aerial Vehicle UAV Detection Residual Graph Convolutional Network

May 6, 2024

GREEN: Generative Radiology Report Evaluation and Error Notation
Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Edward Michalson, Michael Moseley, Curtis Langlotz, Akshay S Chaudhari, Jean-Benoit Delbrouck
Inherent Interpretability Error Feedback Radiology Report Generation Radiology Report Automatic Evaluation Metric Residual Graph Convolutional Network

December 7, 2023

Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation
Qiuxiao Chen, Xiaojun Qi
Semantic Segmentation Deep Convolutional Neural Network Bird'S Eye View Image Domain Residual Graph Convolutional Network

November 13, 2023

ResMGCN: Residual Message Graph Convolution Network for Fast Biomedical Interactions Discovering
Zecheng Yin
Interaction Prediction Biological Network Biomedical Knowledge Graph Molecular Interaction Residual Graph Convolutional Network

May 9, 2023

Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
Jingbo Zhou, Yixuan Du, Ruqiong Zhang, Jun Xia, Zhizhi Yu, Zelin Zang, Di Jin, Carl Yang, Rui Zhang, Stan Z. Li
Residual Graph Convolutional Network Subgraph Aggregation

February 10, 2023

DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks
Lei Zhang, Xiaodong Yan, Jianshan He, Ruopeng Li, Wei Chu
Convolutional Neural Network Deep Convolutional Neural Network Deeper Network Graph Convolutional Residual Graph Convolutional Network Residual Dynamic

December 26, 2022

Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning
Jiwei Wei, Yang Yang, Zeyu Ma, Jingjing Li, Xing Xu, Heng Tao Shen
Knowledge Graph Residual Graph Convolutional Network Semantic Correlation

October 20, 2022

Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN
Md Nurul Muttakin, Md Iqbal Hossain, Md Saidur Rahman
Community Detection ResNet Based Deep Graph Residual Graph Convolutional Network

June 15, 2022

Region-enhanced Deep Graph Convolutional Networks for Rumor Detection
Ge Wang, Li Tan, Tianbao Song, Wei Wang, Ziliang Shang
Graph Convolutional Network Rumor Detection Residual Graph Convolutional Network

December 30, 2021

TextRGNN: Residual Graph Neural Networks for Text Classification
Jiayuan Chen, Boyu Zhang, Yinfei Xu, Meng Wang
Graph Neural Network Text Classification Graph Convolution Text Classification Model Residual Graph Convolutional Network