- HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph . . .
In this work, we propose HeterGCL, a novel graph contrastive learning framework with structural and semantic learning to explore the true potential of GCL on heterophilic graphs
- HeterGCL | Proceedings of the Thirty-Third International Joint . . .
In this work, we propose HeterGCL, a novel graph contrastive learning framework with structural and semantic learning to explore the true potential of GCL on heterophilic graphs
- Graph Contrastive Learning under Heterophily via Graph Filters
In this work, we address this problem by proposing an effective graph CL method, namely HLCL, for learning graph representations under heterophily HLCL first identifies a homophilic and a heterophilic subgraph based on the cosine similarity of node features
- HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph
In this work, we propose HeterGCL, a novel graph contrastive learning framework with structural and semantic learning to explore the true potential of GCL on heterophilic graphs
- www. ijcai. org
@inproceedings{ijcai2024p0265, title = {HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph}, author = {Wang, Chenhao and Liu, Yong and Yang, Yan and Li, Wei}, booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, {IJCAI-24}},
- HeterGCL: Graph Contrastive Learning Framework on Heterophilic . . . - IJCAI
Therefore, we propose a novel framework HeterGCL for graph contrastive learning By incorporating both struc-tural and semantic information, HeterGCL aims to explore the true potential of GCL on heterophilic graphs
- Graph Contrastive Learning under Heterophily via Graph Filters
We proposed HLCL, a contrastive learning framework that finds a homophilic and a heterophilic subgraph in a graph, applies high-pass and low-pass filters to the augmented sub-graph views, and learns node representations by contrasting the filtered augmented views
- dblp: HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph.
dblp: HeterGCL: Graph Contrastive Learning Framework on Heterophilic Graph For some weeks now, the dblp team has been receiving an exceptionally high number of support and error correction requests from the community
|