[PDF][PDF] Resisting Over-Smoothing in Graph Neural Networks via Dual-Dimensional Decoupling
Abstract Graph Neural Networks (GNNs) are widely employed to derive meaningful node
representations from graphs. Despite their success, deep GNNs frequently grapple with the …
representations from graphs. Despite their success, deep GNNs frequently grapple with the …
Improving Graph Contrastive Learning via Adaptive Positive Sampling
J Zhuo, F Qin, C Cui, K Fu, B Niu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Graph Contrastive Learning (GCL) a Self-Supervised Learning (SSL) architecture
tailored for graphs has shown notable potential for mitigating label scarcity. Its core idea is to …
tailored for graphs has shown notable potential for mitigating label scarcity. Its core idea is to …
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
Semi-supervised image classification, leveraging pseudo supervision and consistency
regularization, has demonstrated remarkable success. However, the ongoing challenge lies …
regularization, has demonstrated remarkable success. However, the ongoing challenge lies …
UMCGL: Universal Multi-view Consensus Graph Learning with Consistency and Diversity
Existing multi-view graph learning methods often rely on consistent information for similar
nodes within and across views, however they may lack adaptability when facing diversity …
nodes within and across views, however they may lack adaptability when facing diversity …
Structure-Aware Consensus Network on Graphs with Few Labeled Nodes
Graph node classification with few labeled nodes presents significant challenges due to
limited supervision. Conventional methods often exploit the graph in a transductive learning …
limited supervision. Conventional methods often exploit the graph in a transductive learning …
Pre-training Graph Neural Networks via Weighted Meta Learning
Y Dai, M Sun, X Wang - 2024 International Joint Conference on …, 2024 - ieeexplore.ieee.org
Recent researches have demonstrated pre-training Graph Neural Networks (GNNs) via
meta learning can enhance their performance on learning representations from unlabeled …
meta learning can enhance their performance on learning representations from unlabeled …
Learning Graph Representation via Graph Entropy Maximization
Graph representation learning aims to represent graphs as vectors that can be utilized in
downstream tasks such as graph classification. In this work, we focus on learning diverse …
downstream tasks such as graph classification. In this work, we focus on learning diverse …
Gaussian Mutual Information Maximization for Efficient Graph Self-Supervised Learning: Bridging Contrastive-based to Decorrelation-based
J Wen - ACM Multimedia 2024 - openreview.net
Enlightened by the InfoMax principle, Graph Contrastive Learning (GCL) has achieved
remarkable performance in processing large amounts of unlabeled graph data. Due to the …
remarkable performance in processing large amounts of unlabeled graph data. Due to the …