A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
Graphs are structured data that models complex relations between real-world entities.
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …
Perfect Alignment May be Poisonous to Graph Contrastive Learning
J Liu, H Tang, Y Liu - arxiv preprint arxiv:2310.03977, 2023 - arxiv.org
Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive
pairs and separating negative ones. However, limited research has been conducted on the …
pairs and separating negative ones. However, limited research has been conducted on the …
Self-pro: A Self-prompt and Tuning Framework for Graph Neural Networks
Graphs have become an important modeling tool for web applications, and Graph Neural
Networks (GNNs) have achieved great success in graph representation learning. However …
Networks (GNNs) have achieved great success in graph representation learning. However …
Contrastive Learning Network for Unsupervised Graph Matching
Y **e, L Luo, T Cao, B Yu, AK Qin - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Graph matching aims to establish node correspondences between graphs, which is a
classic combinatorial optimization problem. In recent years,(deep) learning-based methods …
classic combinatorial optimization problem. In recent years,(deep) learning-based methods …
CausalCD: A Causal Graph Contrastive Learning Framework for Self-Supervised SAR Image Change Detection
H Li, B Zou, L Zhang, J Qin - IEEE Transactions on Geoscience …, 2024 - ieeexplore.ieee.org
In recent years, self-supervised synthetic aperture radar (SAR) image change detection
methods have achieved remarkable results, particularly in reducing dependence on …
methods have achieved remarkable results, particularly in reducing dependence on …
Vision Graph Non-Contrastive Learning for Audio Deepfake Detection with Limited Labels
Recent advancements in audio deepfake detection have leveraged graph neural networks
(GNNs) to model frequency and temporal interdependencies in audio data, effectively …
(GNNs) to model frequency and temporal interdependencies in audio data, effectively …
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning
J Liang, X Wei, M Chen, Y Liu, Z Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Graph contrastive learning (GCL) has become a hot topic in the field of graph representation
learning. In contrast to traditional supervised learning relying on a large number of labels …
learning. In contrast to traditional supervised learning relying on a large number of labels …
Do spectral cues matter in contrast-based graph self-supervised learning?
The recent surge in contrast-based graph self-supervised learning has prominently featured
an intensified exploration of spectral cues. However, an intriguing paradox emerges, as …
an intensified exploration of spectral cues. However, an intriguing paradox emerges, as …
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views
Z Zou, Y Jiang, L Shen, J Liu, X Liu - arxiv preprint arxiv:2501.02969, 2025 - arxiv.org
Spectral Graph Neural Networks effectively handle graphs with different homophily levels,
with low-pass filter mining feature smoothness and high-pass filter capturing differences …
with low-pass filter mining feature smoothness and high-pass filter capturing differences …
Efficient Contrastive Learning for Fast and Accurate Inference on Graphs
Graph contrastive learning has made remarkable advances in settings where there is a
scarcity of task-specific labels. Despite these advances, the significant computational …
scarcity of task-specific labels. Despite these advances, the significant computational …