.png){kind=icon}
返回
Adversarial Cluster-Level and Global-Level Graph Contrastive Learning for node representation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2023.110935.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph contrastive learning aims to learn informative and discriminative node representations for downstream tasks by maximizing the mutual information between representations of different augmentation views of the same node. However, according to the multi-view information bottleneck principle, redundant information in learned representations can negatively impact the performance of downstream tasks. To avoid this issue, we propose Adversarial Cluster-Level and Global-Level Graph Contrastive Learning (ACG-GCL) for learning minimal sufficient node representations. ACG-GCL is optimized alternately under an adversarial learning framework with a min-max objective. At the min step, ACG-GCL eliminates redundant information in both the graph structure and feature content of nodes while producing a new graph that provides multi-view information. At the max step, ACG-GCL seeks to preserve shared task-relevant information in the learned representation by maximizing the mutual information of node-cluster level and node-global level representations. We demonstrate the effectiveness of the proposed method on the tasks of node classification and node clustering tasks. Code is available at https://github.com/tangq123/ACG-GCL.(c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Graph representation learning
Graph contrastive learning
Information bottleneck
Node classification
Node clustering
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Improving seizure control in dogs with refractory epilepsy using gabapentin as an adjunctive agent
PREAI
分享收藏Unsupervised graph-level representation learning with hierarchical contrasts具有层次对比的无监督图级表示学习.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Hypergraph Convolution on Nodes-Hyperedges Network for Semi-Supervised Node Classification用于半监督节点分类的节点超图卷积-超边缘网络
PREAI
分享收藏Surpassing the lateral resolution limit by a factor of two using structured illumination microscopy使用结构化照明显微镜将横向分辨率极限超过两倍
OAAI
OAAI分享收藏Graph Barlow Twins: A self-supervised representation learning framework for graphs图Barlow孪生: 图的自监督表示学习框架OAAI
OAAI分享收藏 没有更多内容
没有更多内容