Graph Convolutional

Graph Convolutional Networks (GCNs) leverage graph structures to process data with complex relationships, aiming to improve the accuracy and efficiency of machine learning models across various domains. Current research focuses on enhancing GCN robustness against noisy data and attacks, developing more efficient training methods (e.g., post-training convolution, sparse attention mechanisms), and addressing limitations like over-smoothing in deep GCNs through techniques such as residual connections and adaptive adjacency matrices. GCNs are proving impactful in diverse applications, including recommendation systems, human pose estimation, traffic flow prediction, and drug discovery, by effectively capturing intricate relationships within data.

Papers

July 4, 2022

Back to MLP: A Simple Baseline for Human Motion Prediction
Wen Guo, Yuming Du, Xi Shen, Vincent Lepetit, Xavier Alameda-Pineda, Francesc Moreno-Noguer
Recurrent Neural Network Human Motion Prediction Graph Convolutional Single Scene Specific MLP Future Human Pose

June 10, 2022

Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition
Nafees Ahmad, Savio Ho-Chit Chow, Ho-fung Leung
Graph Neural Network Activity Recognition Content Based Feature Graph Convolutional Neural Network Temporal Fusion Euclidean Space Graph Convolutional Attention Based Graph Neural Network

April 6, 2022

Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
Shaoxian Xu, Zhiyuan Shao, Ci Yang, Xiaofei Liao, Hai Jin
Graph Convolutional Network Single GPU Graph Convolutional Chain of Instruction Efficient Aggregation Active Directed Graph

March 7, 2022

HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
Abduallah Mohamed, Fernando Lejarza, Stephanie Cahail, Christian Claudel, Edison Thomaz
Activity Recognition Sensor Data Temporal Relation Graph Convolutional M2m GNN Activity Label

March 3, 2022

Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction
Chongyang Zhong, Lei Hu, Zihao Zhang, Yongjing Ye, Shihong Xia
Spatio Temporal Temporal Dependency Human Motion Prediction Adjacency Matrix Graph Convolutional

February 28, 2022

Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks
Jin Zeng, Yang Liu, Gene Cheung, Wei Hu
Deep Convolutional Neural Network Sparse Graph Graph Kernel Graph Convolutional Graph Spectrum Structure Spectrum Relationship

January 18, 2022

Deep Graph Convolutional Network and LSTM based approach for predicting drug-target binding affinity
Shrimon Mukherjee, Madhusudan Ghosh, Partha Basuchowdhuri
Constructive Approach LSTM Network Drug Target Graph Convolutional New Drug Drug Labeling

December 22, 2021

SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks
Weigang Lu, Yibing Zhan, Binbin Lin, Ziyu Guan, Liu Liu, Baosheng Yu, Wei Zhao, Yaming Yang, Dacheng Tao
Convolution Layer Undisciplined Over Smoothing Graph Convolutional Performance Degradation Smoothing Problem Skip List

November 23, 2021

Hierarchical Graph Networks for 3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai, Yabo Chen, Botao Wang, Yu Sun, Min Guo, Chenlin Li, Junni Zou, Hongkai Xiong
3D Human Pose Estimation Hierarchical Representation Graph Network Sparse Subnetworks Graph Convolutional

November 20, 2021

Quaternion-Based Graph Convolution Network for Recommendation
Yaxing Fang, Pengpeng Zhao, Guanfeng Liu, Yanchi Liu, Victor S. Sheng, Lei Zhao, Xiaofang Zhou
Effective Recommendation Recommendation Model Graph Convolutional Item Embeddings

Graph Convolutional

Papers

Back to MLP: A Simple Baseline for Human Motion Prediction

Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition

Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs

HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data

Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction

Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks

Deep Graph Convolutional Network and LSTM based approach for predicting drug-target binding affinity

SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

Hierarchical Graph Networks for 3D Human Pose Estimation

Quaternion-Based Graph Convolution Network for Recommendation