Negative Sampling with Marginal Node Indicator
- 주제(키워드) Graph contrastive learning , Graph clustering , Negative sampling strategy
- 주제(DDC) 006.31
- 발행기관 아주대학교 일반대학원
- 지도교수 신현정
- 발행년도 2024
- 학위수여년월 2024. 2
- 학위명 석사
- 학과 및 전공 일반대학원 인공지능학과
- 실제URI http://www.dcollection.net/handler/ajou/000000033795
- 본문언어 한국어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
We introduces a novel negative sampling strategy for graph contrastive learning based on a marginal node indicator, designed to enhance learning of the global manifold in various networks. Our approach distinguishes between core and marginal nodes within network clusters, enabling the model to capture both intra-cluster commonalities and inter-cluster distinctions. By extending the sampling scope from subgraphs to clusters, our methodology facilitates comprehensive manifold learning, a capability substantiated through fine-tuning experiments with minimal labels. The flexibility of our strategy is further demonstrated through its adaptability to both homophily and heterophily networks, achieved by adjusting the number of clusters. Experimental results on synthetic and benchmark datasets, including variations of the MNIST and several social/citation benchmark networks, exhibit an average performance improvement of 2.7% in node classification tasks. This improvement is particularly pronounced in networks with higher levels of heterophily, underscoring the efficacy of our approach in complex network structures. Our method's applicability extends beyond specific models to a broader range of graph contrastive learning frameworks.
more목차
1. Introduction· 1
2. Fundamentals· 5
2.1 Graph Notations 5
2.2 Graphical Mutual Information · 6
2.3 Local Dependency 7
3. Proposed Method 8
3.1 Graph Clustering 9
3.2 Core & Marginal Node Definitions 10
3.3 Marginal Node Indication-based Negative Sampling · 14
4. Experiments· 17
4.1 Synthetic Datasets & Benchmark Datasets 17
4.2 Experimental Setups 25
4.3 Experiment results 29
5. Conclusion· 37
References 38
