A collection of research papers on graph.
这里整理了一些图卷积文章,参考了 pytorch-geometric 和 dgl 中的图卷积函数。
- Semi-Supervised Classification with Graph Convolutional Networks
GCNConv
ICLR 2017
[pdf] [code] - Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
ChebConv
NIPS 2016
[pdf] - Inductive Representation Learning on Large Graphs
SAGEConv
NIPS 2017
[pdf] - Inductive Representation Learning on Large Graphs
CuGraphSAGEConv
NIPS 2017
[pdf] - Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
GraphConv
AAAI 2019
[pdf] - Learning Representations of Irregular Particle-detector Geometry with Distance-weighted Graph Networks
GravNetConv
EPJ C 2019
[pdf] - Gated Graph Sequence Neural Networks
GatedGraphConv
ICLR 2016
[pdf] - Residual Gated Graph ConvNets
ResGateGraphConv
ICLR 2018
[pdf] - Graph Attention Networks
GATConv
ICLR 2018
[pdf] - Graph Attention Networks
CuGraphGATConv
ICLR 2018
[pdf] - Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
FusedGATConv
MLSys 2022
[pdf] - How Powerful are Graph Neural Networks?
GATv2Conv
ICLR 2019
[pdf] - Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
TransformerConv
IJCAI 2021
[pdf] - Attention-based Graph Neural Network for Semi-Supervised Learning
AGNNConv
ICLR 2018
[pdf] - Topology Adaptive Graph Convolutional Networks
TAGConv
arxiv 2017
[pdf] - How Powerful are Graph Neural Networks?
GINConv
ICLR 2019
[pdf] - Strategies for Pre-training Graph Neural Networks
GINEConv
ICLR 2020
[pdf] - Graph Neural Networks with Convolutional ARMA Filters
ARMAConv
IEEE Trans 2022
[pdf] - Simplifying Graph Convolutional Networks
SGConv
ICML 2019
[pdf] - Simple Spectral Graph Convolution
SSGConv
ICLR 2021
[pdf] - Predict then Propagate: Graph Neural Networks meet Personalized PageRank
APPNPConv
ICLR 2019
[pdf] - Convolutional Networks on Graphs for Learning Molecular Fingerprints
MFConv
NIPS 2015
[pdf] - Modeling Relational Data with Graph Convolutional Networks
RGCNConv
ESWC 2018
[pdf] - Modeling Relational Data with Graph Convolutional Networks
FastRGCNConv
ESWC 2018
[pdf] - Modeling Relational Data with Graph Convolutional Networks
CuGraphRGCNConv
ESWC 2018
[pdf] - Relational Graph Attention Networks
RGAConv
arxiv 2019
[pdf] - Signed Graph Convolutional Network
SignedConv
ICDM 2018
[pdf] - Just Jump: Towards Dynamic Neighborhood Aggregation in Graph Neural Networks
DNAConv
arxiv 2019
[pdf] - PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
PointConv
CVPR 2017
[pdf] - Dynamic Graph CNN for Learning on Point Clouds
EdgeConv
ACM Trans 2019
[pdf] - PointCNN: Convolution On X-Transformed Points
XConv
NIPS 2018
[pdf] - PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
PPFConv
CVPR 2018
[pdf] - FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
FeaStConv
CVPR 2018
[pdf] - Point Transformer
PointTransformerConv
ICCV 2021
[pdf] - Hypergraph Convolution and Hypergraph Attention
HyperGraphConv
Pattern Recognit 2021
[pdf] - ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
LEConv
AAAI 2020
[pdf] - Principal Neighbourhood Aggregation for Graph Nets
PNAConv
NeurIPS 2020
[pdf] - Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
ClusterConv
KDD 2019
[pdf] - DeeperGCN: All You Need to Train Deeper GCNs
GENConv
arxiv 2020
[pdf] - Simple and Deep Graph Convolutional Networks
GCN2Conv
ICML 2020
[pdf] - Path Integral Based Convolution and Pooling for Graph Neural Networks
PANConv
NIPS 2020
[pdf] - A Reduction of a Graph to a Canonical Form and an Algebra Arising During this Reduction
WLConv
Nauchno-Technicheskaya Informatsiya 1968
[pdf] - GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
FiLMConv
ICML 2020
[pdf] - How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
SurperGATConv
ICLR 2021
[pdf] - Beyond Low-Frequency Information in Graph Convolutional Networks
FAConv
AAAI 2021
[pdf] - Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
EGConv
arXiv 2021
[pdf] - Pathfinder Discovery Networks for Neural Message Passing
PDNConv
WWW 2021
[pdf] - Design Space for Graph Neural Networks
GeneralConv
NIPS 2020
[pdf] - Heterogeneous Graph Transformer
HGTConv
WWW 2020
[pdf] - Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
HEATConv
arxiv 2021
[pdf] - Heterogenous Graph Attention Network
HANConv
WWW 2019
[pdf] - LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
LGConv
SIGIR 2020
[pdf] - Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
PointGNNConv
CVPR 2020
[pdf] - Recipe for a General, Powerful, Scalable Graph Transformer
GPSConv
NIPS 2022
[pdf] - Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
AntiSymmericConv
ICLR 2023
[pdf] - Edge Directionality Improves Learning on Heterophilic Graphs
DirGNNConv
LoG 2023
[pdf] - MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
MixHopConv
ICML 2019
[pdf] - Geometric Deep Learning on Graphs and Manifolds using Mixture Model CNNs
GMMConv
CVPR 2017
[pdf] - Neural Message Passing for Quantum Chemistry
NNConv
ICML 2017
[pdf]
常用的简单的图池化方法有 SumPooling, AvgPooling 和 MaxPooling,这里列举一些其他的更加复杂的图池化方法,参考了 pytorch-geometric 和 dgl 中的图池化函数。
- An End-to-End Deep Learning Architecture for Graph Classification
SortPooling
AAAI 2018
[pdf] - Graph U-Nets
TopKPooling
ICML 2019
[pdf] - Self-Attention Graph Pooling
SAGPooling
ICML 2019
[pdf] - Gated Graph Sequence Neural Networks
GlobalAttentionPooling
ICLR 2016
[pdf] - Order Matters: Sequence to sequence for sets
Set2SetPooling
ICLR 2016
[pdf] - Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
SetTransformerPooling
ICML 2019
[pdf] - Towards Graph Pooling by Edge Contraction and Edge Contraction Pooling for Graph Neural Networks
EdgePooling
ICML 2019
arxiv 2019
[pdf][pdf] - ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
ASAPooling
AAAI 2020
[pdf] - Path Integral Based Convolution and Pooling for Graph Neural Networks
PANPooling
NIPS 2020
[pdf] - Memory-Based Graph Networks
MemPooling
ICLR 2020
[pdf]