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

January 22, 2024

LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
Xunkai Li, Meihao Liao, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
Deep Learning Architecture Graph Convolution Directed Graph Effective Approach Graph Signal Denoising

January 17, 2024

Understanding Heterophily for Graph Neural Networks
Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
Graph Neural Network Graph Convolution Heterophilic Graph Stochastic Block Model

December 24, 2023

Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training
Charles Dickens, Eddie Huang, Aishwarya Reganti, Jiong Zhu, Karthik Subbian, Danai Koutra
Graph Convolution Graph Coarsening Graph Summarization Scalable Graph Neural Network Node Classification Datasets

December 19, 2023

December 14, 2023

A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction
Lingqiang Chen, Qinglin Zhao, Guanghui Li, Mengchu Zhou, Chenglong Dai, Yiming Feng
Many Sparse Graph Convolutional Network Graph Convolution Traffic Forecasting Traffic Flow Prediction Graph Convolutional GCN Based Auxiliary Information

December 7, 2023

Graph Convolutions Enrich the Self-Attention in Transformers!
Jeongwhan Choi, Hyowon Wi, Jayoung Kim, Yehjin Shin, Kookjin Lee, Nathaniel Trask, Noseong Park
Transformer Megatron Decepticons Self Attention Graph Convolution Graph Signal Processing Transformer Based Deep

November 16, 2023

Algebraic Topological Networks via the Persistent Local Homology Sheaf
Gabriele Cesa, Arash Behboodi
Graph Convolution Node Embeddings Local Homology

November 13, 2023

Classification of developmental and brain disorders via graph convolutional aggregation
Ibrahim Salim, A. Ben Hamza
Convolutional Neural Network Classification Code Graph Drawing Deep Convolutional Neural Network Graph Representation Learning Graph Convolution Aggregation Network Brain Disorder Subgraph Aggregation

November 9, 2023

Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation
Jialin Chen, Yuelin Wang, Cristian Bodnar, Rex Ying, Pietro Lio, Yu Guang Wang
Graph Neural Network Graph Representation Graph Convolution Framelet Transform Dirichlet Energy

October 25, 2023

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
Haotian Tang, Shang Yang, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han
Graph Convolution Single GPU Efficient Training Inference Framework Sparse Convolution Sparse Kernel

October 20, 2023

InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution
Xiangru Jian, Yimu Wang
Graph Convolution Cross Modal Retrieval Multi Modal Representation Cross Modal Benchmark

September 30, 2023

Learning State-Augmented Policies for Information Routing in Communication Networks
Sourajit Das, Navid NaderiAlizadeh, Alejandro Ribeiro
LeArning Abstract Graph Neural Network Graph Convolution Prior Policy Large Scale Network Computer Network State Augmentation Communication Network

September 29, 2023

On the Equivalence of Graph Convolution and Mixup
Xiaotian Han, Hanqing Zeng, Yu Chen, Shaoliang Nie, Jingzhou Liu, Kanika Narang, Zahra Shakeri, Karthik Abinav Sankararaman, Song Jiang, Madian Khabsa, Qifan Wang, Xia Hu
Data Augmentation Graph Convolution Spatio Temporal Mixup Mechanism Graph Convolution Network

September 24, 2023

From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
Zheng Wang, Hongming Ding, Li Pan, Jianhua Li, Zhiguo Gong, Philip S. Yu
Convolutional Neural Network Semi Supervised Graph Convolution Supervised Machine Learning New Event Cluster

September 22, 2023

ARRQP: Anomaly Resilient Real-time QoS Prediction Framework with Graph Convolution
Suraj Kumar, Soumi Chattopadhyay
Graph Convolution Quality of Service Prediction Real World Benchmark

September 13, 2023

Attention-based Dynamic Graph Convolutional Recurrent Neural Network for Traffic Flow Prediction in Highway Transportation
Tianpu Zhang, Weilong Ding, Mengda Xing
Graph Convolution Traffic Flow Prediction Locality Sensitive Highway Driving

September 11, 2023

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, Xiaoli Li, Lihua Xie, Zhenghua Chen
Multivariate Time Series Graph Convolution Temporal Graph Neural Network Temporal Correlation Multivariate Time Series Data Spatial Temporal Graph

September 1, 2023

A Locality-based Neural Solver for Optical Motion Capture
Xiaoyu Pan, Bowen Zheng, Xinwei Jiang, Guanglong Xu, Xianli Gu, Jingxiang Li, Qilong Kou, He Wang, Tianjia Shao, Kun Zhou, Xiaogang Jin
Graph Convolution Locality Sensitive Outlier Data Optical Motion Capture Marker Selection

August 20, 2023

Enhancing Spatiotemporal Traffic Prediction through Urban Human Activity Analysis
Sumin Han, Youngjun Park, Minji Lee, Jisun An, Dongman Lee
Graph Convolution Traffic Prediction Traffic Pattern Spatiotemporal Traffic

Graph Convolution

Papers

LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning

Understanding Heterophily for Graph Neural Networks

Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training

Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting

GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction

A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction

Graph Convolutions Enrich the Self-Attention in Transformers!

Algebraic Topological Networks via the Persistent Local Homology Sheaf

Classification of developmental and brain disorders via graph convolutional aggregation

Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs

InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution

Learning State-Augmented Policies for Information Routing in Communication Networks

On the Equivalence of Graph Convolution and Mixup

From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited

ARRQP: Anomaly Resilient Real-time QoS Prediction Framework with Graph Convolution

Attention-based Dynamic Graph Convolutional Recurrent Neural Network for Traffic Flow Prediction in Highway Transportation

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

A Locality-based Neural Solver for Optical Motion Capture

Enhancing Spatiotemporal Traffic Prediction through Urban Human Activity Analysis