.png){kind=icon}
返回
Multi-Level Graph Knowledge Contrastive Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2024.3466530.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 (GCL) stands as a potent framework for unsupervised graph representation learning that has gained traction across numerous graph learning applications. The effectiveness of GCL relies on generating high-quality contrasting samples, enhancing the model's ability to discern graph semantics. However, the prevailing GCL methods face two key challenges: 1) introducing noise during graph augmentations and 2) requiring additional storage for generated samples, which degrade the model performance. In this paper, we propose novel approaches, GKCL (i.e., Graph Knowledge Contrastive Learning) and DGKCL (i.e., Distilled Graph Knowledge Contrastive Learning), that leverage multi-level graph knowledge to create noise-free contrasting pairs. This framework not only addresses the noise-related challenges but also circumvents excessive storage demands. Furthermore, our method incorporates a knowledge distillation component to optimize the trained embedding tables, reducing the model's scale while ensuring superior performance, particularly for the scenarios with smaller embedding sizes. Comprehensive experimental evaluations on three public benchmark datasets underscore the merits of our proposed method and elucidate its properties, which primarily reflect the performance of the proposed method equipped with different embedding sizes and how the distillation weight affects the overall performance.
Keyword:
Contrastive learning
Semantics
Noise
Computational modeling
Training
Computer science
Australia
Representation learning
Perturbation methods
Learning (artificial intelligence)
Graph representation learning
graph contrastive learning
knowledge distillation
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏Self-supervised Graph-level Representation Learning with Adversarial Contrastive Learning基于对抗性对比学习的自监督图级表示学习
OAAI
OAAI分享收藏Improving seizure control in dogs with refractory epilepsy using gabapentin as an adjunctive agent
PREAI
分享收藏分享收藏
查看更多内容