Skip to content

guixianjin/GNNpapers

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 

Repository files navigation

GNNpapers

Optimizing Graph Topology (edge weights)

  • CVPR-19 Semi-supervised Learning with Graph Learning-Convolutional Networks
  • ICDM-19 Learning Robust Representations with Graph Denoising Policy Network
  • IJCAI-19 Topology Optimization based Graph Convolutional Network (TO-GNN)
  • ICML-19 Learning Discrete Structures for Graph Neural Networks (LDS)
  • AAAI-20 Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View (AdaEdge)
  • IJCAI-20 When Do GNNs Work: Understanding and Improving Neighborhood Aggregation
  • ICML-20 Robust Graph Representation Learning via Neural Sparsification
  • ICML-20 Continuous Graph Neural Networks (CGNN)
  • KDD-20 Graph Structure Learning for Robust Graph Neural Networks (ProGNN)
  • NIPS-20 Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
  • ICLR-21-submit VEM-GCN: Topology Optimization with Variational EM for Graph Convolutional Networks
  • ICLR-21-submit Unifying Graph Convolutional Neural Networks and Label Propagation
  • ICLR-21-submit Learning Discrete Adaptive Receptive Fields for Graph Convolutional Networks

Over-Smoothing problem

  • AAAI-18 Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
  • ICML-18 Representation Learning on Graphs with Jumping Knowledge Network
  • AAAI-20 Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
  • IJCAI-20 When Do GNNs Work: Understanding and Improving Neighborhood Aggregation
  • ICLR-20 Measuring and Improving the Use of Graph Information in Graph Neural Networks
  • ICLR-20 DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
  • ICLR-20 PairNorm: Tackling Oversmoothing in GNNs
  • ICLR-20 Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
  • ICLR-20-workshop A Note on Over-Smoothing for Graph Neural Networks
  • ICML-20 Simple and Deep Graph Convolutional Networks
  • KDD-20 Towards Deeper Graph Neural Networks
  • NIPS-20 Towards Deeper Graph Neural Networks with Differentiable Group Normalization
  • NIPS-20 Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
  • NIPS-20 Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Consistency regularization on unlabeled node

  • NIPS-20-submit GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning
  • NIPS-20 Graph Random Neural Network for Semi-Supervised Learning on Graphs
  • ICML-19-Workshop Batch Virtual Adversarial Training for Graph Convolutional Networks
  • NIPS-19 Graph Agreement Models for Semi-Supervised Learning
  • SIGIR-20 Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification

Inter-discipline

  • AAAI-20 Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning
  • AAAI-20 Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodesa
  • IJCAI-20 Multi-Class Imbalanced Graph Convolutional Network Learning
  • ICML-20 When Does Self-Supervision Help Graph Convolutional Networks?
  • ICLR-21-submit Towards Robust Graph Neural Networks against Label Noise

Recommender system

  • KDD-18 Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba
  • KDD-18 Graph convolutional neural networks for web-scale recommender systems (pinsage)
  • WWW-19 Graph Neural Networks for Social Recommendation
  • SIGIR-19 Neural Graph Collaborative Filtering
  • SIGIR-20 LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
  • AAAI-20 Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
  • AAAI-20 Multi-Component Graph Convolutional Collaborative Filtering
  • ICML-20 Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published