Graph Convolution

Graph convolution is a technique used in graph neural networks (GNNs) to process data represented as graphs, aiming to learn informative representations of nodes and edges by aggregating information from their neighbors. Current research focuses on improving efficiency and scalability, particularly for large graphs, exploring novel architectures like windowed GNNs and post-training methods to reduce computational complexity, and addressing issues like over-smoothing through techniques such as corrected convolutions and adaptive kernel approaches. These advancements are significant for various applications, including recommendation systems, image processing, medical image analysis, and human activity recognition, where graph-structured data is prevalent.

Papers

July 26, 2023

Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras
Kamil Jeziorek, Andrea Pinna, Tomasz Kryjak
Convolutional Neural Network Data Detection Object Detection Event Camera Graph Convolution Object Classification High Temporal Resolution

July 22, 2023

Collaborative Graph Neural Networks for Attributed Network Embedding
Qiaoyu Tan, Xin Zhang, Xiao Huang, Hao Chen, Jundong Li, Xia Hu
Graph Neural Network Graph Convolution GNN Architecture Attributed Network Attribute Aware Network

July 18, 2023

Learning Adaptive Neighborhoods for Graph Neural Networks
Avishkar Saha, Oscar Mendez, Chris Russell, Richard Bowden
Graph Neural Network Node Classification Graph Convolution Graph Structure Latent Graph Adaptive Neighborhood

July 12, 2023

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
Eli Chien, Wei-Ning Chen, Chao Pan, Pan Li, Ayfer Özgür, Olgica Milenkovic
Differential Privacy Graph Convolution Graph Privacy Node Level Privacy

June 24, 2023

Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective
Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki
Convolutional Neural Network Graph Representation Learning Graph Convolution Structural Information Learning Signal Two Layer

May 30, 2023

Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria Recommendation
Jin-Duk Park, Siqing Li, Xin Cao, Won-Yong Shin
Graph Convolution GNN Based Human Rating Preference Representation Likely Criterion Multi Criterion Recommendation

May 29, 2023

Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs
Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro
Neural Network Continuum Limit Graph Convolution Convolutional Filter Graph Filter Discriminative Task

May 28, 2023

Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation
Edoardo D'Amico, Aonghus Lawlor, Neil Hurley
Graph Convolution Item Representation Spectral Embedding Top N Recommendation

May 26, 2023

GC-Flow: A Graph-Based Flow Network for Effective Clustering
Tianchun Wang, Farzaneh Mirzazadeh, Xiang Zhang, Jie Chen
Convolutional Neural Network Generative Model Normalizing Flow Graph Convolution Flow Network

May 19, 2023

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie
Graph Convolution Topological Feature Skeleton Based Action Recognition Skeleton Data Human Topology Topology Reasoning

May 17, 2023

G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks
Anchun Gui, Jinqiang Ye, Han Xiao
Parameter Efficient Fine Tuning Graph Transformer Graph Convolution Downstream Task Parameter Efficient Transfer Learning Large Scale Pre Trained Model BBox Adapter

May 15, 2023

TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation
Matthew Korban, Peter Young, Scott T. Acton
Graph Convolution Age Estimation Adaptive Graph C2p GCN Memory Module

May 5, 2023

Adaptive Graph Convolutional Subspace Clustering
Lai Wei, Zhengwei Chen, Jun Yin, Changming Zhu, Rigui Zhou, Jin Liu
Graph Convolution Deep Subspace Subspace Clustering Deep Graph Clustering

May 2, 2023

April 24, 2023

Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
Soubarna Banik, Patricia Gschoßmann, Alejandro Mendoza Garcia, Alois Knoll
Data Augmentation Graph Convolution Occlusion Aware Occlusion Handling Occlusion Augmentation

April 12, 2023

Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Data
Dominik Klepl, Fei He, Min Wu, Daniel J. Blackburn, Ptolemaios G. Sarrigiannis
Alzheimer'S Disease Graph Convolution Common Disease Brain Network EEG Data Functional Connectivity

March 31, 2023

HD-GCN:A Hybrid Diffusion Graph Convolutional Network
Zhi Yang, Kang Li, Haitao Gan, Zhongwei Huang, Ming Shi
Graph Convolutional Network Graph Convolution Information Diffusion GCN Model Quater GCN Diffusion Graph Convolutional Network

March 28, 2023

Graph Convolution

Papers

Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras

Collaborative Graph Neural Networks for Attributed Network Embedding

Learning Adaptive Neighborhoods for Graph Neural Networks

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection

Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective

Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria Recommendation

Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs

Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation

GC-Flow: A Graph-Based Flow Network for Effective Clustering

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness

G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks

TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation

Adaptive Graph Convolutional Subspace Clustering

Multi-Head Graph Convolutional Network for Structural Connectome Classification

PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling

Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation

Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Data

HD-GCN:A Hybrid Diffusion Graph Convolutional Network

Transformer and Snowball Graph Convolution Learning for Brain functional network Classification

HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation