Graph Learning Enhancement Experiments Keywords: Contrastive Learning, GNNs, Self-supervised Learning https://browse.arxiv.org/pdf/2401.17580.pdfbrowse.arxiv.org/pdf/2401.17580.pdf Introduction 一般的对比学习包括两种增强类型,拓扑结构和特征增强。本文关注拓扑增强,因其可以应用于属性图或非属性图。随机...
Subsequently, we utilize graph neural networks to separately extract the topological embedding representations of transaction subgraphs and associated address representations of transaction nodes. Lastly, supervised contrastive learning is introduced to reduce the effect of noise, which pulls together ...
论文标题是《Graph Contrastive Learning with Cohesive Subgraph Awareness》,这是一篇图对比学习领域的研究,由北京大学、上海财经大学、以及南京大学的四位作者共同完成,被 The Web Conference 2024 接收。 论文链接:arxiv.org/abs/2401.1758 代码链接:github.com/wuyucheng200 一、背景和动机 1、图对比学习 图对比学...
Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses stochastic graph topology augmentation, such as uniform node dropping, to generate augmented graphs. However, such ...
based on anchor node label. Experiments show that AdaGCL can scale up to graphs with millions of nodes, and delivers the consistent improvement than the existing methods on various benchmark datasets. Furthermore, AdaGCL has comparable running time with the state-of-the-art contrastive learning ...
Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph representation learning to eliminate the dependence of la... Jian Feng,Tian Liu,Cailing Du - Tech Science Press 被引量: 0发表: 2024年 Traffic Forecasting Based on Integration of Adaptive Subgraph Refor...
Dual Perspective Contrastive Learning Based Subgraph Anomaly Detection onAttributed Networksdoi:10.1007/978-3-031-15931-2_40Network anomaly detection is widely used to discover the anomalies of complex attributed networks in reality. Existing approaches can detect independent abnormal nodes by comparing the...
To address the above problems, a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs. Firstly, the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph, and the random ...
The framework employs self-supervised contrastive learning techniques to pre-train the Transformer Encoder, enabling the model to learn high-quality representations of samples without requiring labels. Specifically, we propose the Node-Subgraph-Node method, which adequately expresses the context information ...
In this work, we propose a structure-aware graph contrastive learning model called PASCAL which considers the subgraph-level embedding. PASCAL adaptively constructs and encodes subgraphs based on the nodes’ motif information, and further uses them as the input of the GNN encoder to capture rich se...