Semi Supervised Node Classification

Semi-supervised node classification aims to predict the labels of nodes in a graph using a limited number of labeled nodes and a wealth of unlabeled ones. Current research focuses on improving Graph Neural Networks (GNNs), including variations like Graph Transformers and hypergraph neural networks, by addressing challenges such as over-smoothing, heterophily (nodes with dissimilar labels being connected), and the impact of graph noise. These advancements aim to enhance accuracy, efficiency, and robustness, particularly in handling large graphs and diverse data distributions. The field's impact spans various applications, including social network analysis, recommendation systems, and knowledge graph reasoning.

Papers

November 1, 2022

Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces
Ashish Tiwari, Sresth Tosniwal, Shanmuganathan Raman
Graph Representation Heterogeneous Graph Node Representation Feature Space Semi Supervised Node Classification Graph Convolution Network Topological Representation

October 27, 2022

Beyond Homophily with Graph Echo State Networks
Domenico Tortorella, Alessio Micheli
Node Classification Graph Classification Semi Supervised Node Classification Homophilous Graph Graph Echo State Network

October 15, 2022

Improving Your Graph Neural Networks: A High-Frequency Booster
Jiaqi Sun, Lin Zhang, Shenglin Zhao, Yujiu Yang
Graph Neural Network Graph Structured Data Semi Supervised Node Classification GNN Framework Low Pas Laplacian Regularization

October 12, 2022

JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
Jian Kang, Qinghai Zhou, Hanghang Tong
Uncertainty Quantification Graph Convolutional Network High Uncertainty Value Semi Supervised Node Classification Trustworthy Graph

October 8, 2022

Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining
Jaemin Yoo, Meng-Chieh Lee, Shubhranshu Shekhar, Christos Faloutsos
Graph Neural Network Real World Graph Semi Supervised Node Classification Graph Mining Task Graph Neural Network Attribution

August 26, 2022

Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity
Kaize Ding, Elnaz Nouri, Guoqing Zheng, Huan Liu, Ryen White
Semi Supervised Learning Semi Supervised Data Scarcity Semi Supervised Node Classification Graph Data Augmentation Limited Labeled Data Graph Self Training

July 12, 2022

From Spectral Graph Convolutions to Large Scale Graph Convolutional Networks
Matteo Bunino
Graph Convolutional Network Large Graph Semi Supervised Node Classification Spectral Graph Convolution Minibatch Stochastic Quater GCN

July 7, 2022

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
Hongkang Li, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Convolutional Neural Network Graph Structured Data Graph Convolutional Neural Network Semi Supervised Node Classification Generalization Guarantee Graph Topology Graph Sampling

July 5, 2022

What Do Graph Convolutional Neural Networks Learn?
Sannat Singh Bhasin, Vaibhav Holani, Divij Sanjanwala
Graph Convolutional Network Graph Structure Node Embeddings Heterophilic Graph Graph Convolutional Neural Network Semi Supervised Node Classification

June 30, 2022

Modularity Optimization as a Training Criterion for Graph Neural Networks
Tsuyoshi Murata, Naveed Afzal
Graph Neural Network Deep Convolutional Neural Network Graph Convolution Semi Supervised Node Classification Convolutional Architecture Modularity Maximization

June 8, 2022

Alternately Optimized Graph Neural Networks
Haoyu Han, Xiaorui Liu, Haitao Mao, MohamadAli Torkamani, Feng Shi, Victor Lee, Jiliang Tang
Graph Neural Network Optimization Purpose Semi Supervised Learning Semi Supervised Node Classification Bi Level Optimization

June 6, 2022

Mixed Graph Contrastive Network for Semi-Supervised Node Classification
Xihong Yang, Yue Liu, Sihang Zhou, Xinwang Liu, En Zhu
Graph Neural Network Contrastive Learning Latent Representation Semi Supervised Node Classification

May 31, 2022

Label-Enhanced Graph Neural Network for Semi-supervised Node Classification
Le Yu, Leilei Sun, Bowen Du, Tongyu Zhu, Weifeng Lv
Graph Neural Network Semi Supervised Node Classification Unlabeled Node Node Selection

May 19, 2022

Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation
Zhiqiang Zhong, Sergey Ivanov, Jun Pang
Graph Neural Network Node Classification Heterophilic Graph Label Propagation Graph Learning Task Semi Supervised Node Classification Known Algorithm

May 6, 2022

Optimal Propagation for Graph Neural Networks
Beidi Zhao, Boxin Du, Zhe Xu, Liangyue Li, Hanghang Tong
Graph Neural Network Low Rank Approximation Semi Supervised Node Classification Personalized Pagerank Optimal Graph Structure Optimal Propagation

April 19, 2022

Label Efficient Regularization and Propagation for Graph Node Classification
Tian Xie, Rajgopal Kannan, C. -C. Jay Kuo
Label Smoothing Label Propagation Semi Supervised Node Classification Fast Propagation Label Regularization Unlabeled Node Graph Node Classification

April 4, 2022

GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment
Junseok Lee, Yunhak Oh, Yeonjun In, Namkyeong Lee, Dongmin Hyun, Chanyoung Park
Graph Neural Network Graph Drawing Node Classification Node Representation Self Supervised Method Semi Supervised Node Classification Distribution Matching

January 28, 2022

FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks
Yuhang Yao, Weizhao Jin, Srivatsan Ravi, Carlee Joe-Wong
Semi Supervised Node Classification Federated Training Convergence Performance Federated Graph Neural Network

December 14, 2021

Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks
Aneesh Komanduri, Justin Zhan
Graph Neural Network Graph Based Semi Supervised Node Classification Graph Sampling Graph Inference

November 14, 2021

$p$-Laplacian Based Graph Neural Networks
Guoji Fu, Peilin Zhao, Yatao Bian
Graph Neural Network State of the Art Heterophilic Graph Semi Supervised Node Classification M2m GNN Polynomial Graph Filter