Node Classification
Node classification aims to assign labels to nodes within a graph based on their features and relationships with other nodes. Current research heavily utilizes Graph Neural Networks (GNNs), including variations like Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), often incorporating techniques to address challenges like oversmoothing and heterophily. Focus areas include improving robustness to noisy data and adversarial attacks, enhancing efficiency for large-scale graphs, and developing methods for few-shot and open-world scenarios. These advancements have significant implications for various applications, such as social network analysis, recommendation systems, and biological network modeling.
Papers
Large Language Model-based Augmentation for Imbalanced Node Classification on Text-Attributed Graphs
Leyao Wang, Yu Wang, Bo Ni, Yuying Zhao, Tyler Derr
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Yihong Luo, Yuhan Chen, Siya Qiu, Yiwei Wang, Chen Zhang, Yan Zhou, Xiaochun Cao, Jing Tang
ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification
Bishal Thapaliya, Anh Nguyen, Yao Lu, Tian Xie, Igor Grudetskyi, Fudong Lin, Antonios Valkanas, Jingyu Liu, Deepayan Chakraborty, Bilel Fehri
Rethinking Graph Transformer Architecture Design for Node Classification
Jiajun Zhou, Xuanze Chen, Chenxuan Xie, Yu Shanqing, Qi Xuan, Xiaoniu Yang
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Jonas Linkerhägner, Cheng Shi, Ivan Dokmanić
DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
Dongyuan Li, Shiyin Tan, Ying Zhang, Ming Jin, Shirui Pan, Manabu Okumura, Renhe Jiang
RW-NSGCN: A Robust Approach to Structural Attacks via Negative Sampling
Shuqi He, Jun Zhuang, Ding Wang, Jun Song