Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 33, Issue 6, Pages 2378-2392Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3068344
Keywords
Anomaly detection; Task analysis; Graph neural networks; Unsupervised learning; Predictive models; Pattern matching; Training; Anomaly detection; attributed networks; contrastive self-supervised learning; graph neural networks (GNNs); unsupervised learning
Categories
Funding
- National Natural Science Foundation (NSF) of China [61973162, 61872360]
- Fundamental Research Funds for the Central Universities [30920032202]
- China Computer Federation (CCF)-Tencent Open Fund [RAGR20200101]
- Hong Kong Scholars Program [XJ2019036]
Ask authors/readers for more resources
This article introduces a novel Contrastive self-supervised Learning framework for Anomaly detection on attributed networks (CoLA). The framework fully utilizes local information from network data by sampling a new type of contrastive instance pair, capturing the relationship between each node and its neighboring substructure in an unsupervised manner. A well-designed graph neural network (GNN)-based contrastive learning model is proposed to learn informative embeddings from high-dimensional attributes and local structures, measuring the agreement of each instance pair with its outputted scores.
Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. Recently, the deep learning-based anomaly detection methods have shown promising results over shallow approaches, especially on networks with high-dimensional attributes and complex structures. However, existing approaches, which employ graph autoencoder as their backbone, do not fully exploit the rich information of the network, resulting in suboptimal performance. Furthermore, these methods do not directly target anomaly detection in their learning objective and fail to scale to large networks due to the full graph training mechanism. To overcome these limitations, in this article, we present a novel Contrastive self-supervised Learning framework for Anomaly detection on attributed networks (CoLA for abbreviation). Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way. Meanwhile, a well-designed graph neural network (GNN)-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure and measure the agreement of each instance pairs with its outputted scores. The multiround predicted scores by the contrastive learning model are further used to evaluate the abnormality of each node with statistical estimation. In this way, the learning model is trained by a specific anomaly detection-aware target. Furthermore, since the input of the GNN module is batches of instance pairs instead of the full network, our framework can adapt to large networks flexibly. Experimental results show that our proposed framework outperforms the state-of-the-art baseline methods on all seven benchmark data sets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available