SCALA: Sparsification-based Contrastive Learning for Anomaly Detection on Attributed Networks (2401.01625v2)
Abstract: Anomaly detection on attributed networks aims to find the nodes whose behaviors are significantly different from other majority nodes. Generally, network data contains information about relationships between entities, and the anomaly is usually embodied in these relationships. Therefore, how to comprehensively model complex interaction patterns in networks is still a major focus. It can be observed that anomalies in networks violate the homophily assumption. However, most existing studies only considered this phenomenon obliquely rather than explicitly. Besides, the node representation of normal entities can be perturbed easily by the noise relationships introduced by anomalous nodes. To address the above issues, we present a novel contrastive learning framework for anomaly detection on attributed networks, \textbf{SCALA}, aiming to improve the embedding quality of the network and provide a new measurement of qualifying the anomaly score for each node by introducing sparsification into the conventional method. Extensive experiments are conducted on five benchmark real-world datasets and the results show that SCALA consistently outperforms all baseline methods significantly.
- Lof: identifying density-based local outliers. In SIGMOD, 2000.
- Deep anomaly detection on attributed networks. In SDM, 2019.
- Graph anomaly detection via multi-scale contrastive learning networks with augmented view. In AAAI, 2023.
- Arise: Graph anomaly detection on attributed networks via substructure awareness. IEEE transactions on neural networks and learning systems, 2023.
- Normality learning-based graph anomaly detection via multi-scale contrastive learning. In ACM MM, 2023.
- Contrastive multi-view representation learning on graphs. In PMLR, 2020.
- Anemone: Graph anomaly detection with multi-scale contrastive learning. In CIKM, 2021.
- Graph anomaly detection with graph neural networks: Current status and challenges. IEEE Access, 2022.
- Radar: Residual analysis for anomaly detection in attributed networks. In IJCAI, 2017.
- Leveraging sparsity for efficient submodular data summarization. Advances in Neural Information Processing Systems, 2016.
- Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE transactions on neural networks and learning systems, 2021.
- Comga: Community-aware attributed graph anomaly detection. In WSDM, 2022.
- Birds of a feather: Homophily in social networks. Annual review of sociology, 2001.
- Anomalous: A joint modeling approach for anomaly detection on attributed networks. In IJCAI, 2018.
- Scalable anomaly ranking of attributed neighborhoods. In SDM, 2016.
- Gcc: Graph contrastive coding for graph neural network pre-training. In SIGKDD, 2020.
- Collective classification in network data. AI magazine, 2008.
- David B Skillicorn. Detecting anomalies in graphs. In ISI, 2007.
- Conditional anomaly detection. IEEE Transactions on knowledge and Data Engineering, 2007.
- Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In ICLR, 2020.
- Deep representation learning for social network analysis. FRONTIERS IN BIG DATA, 2019.
- Arnetminer: extraction and mining of academic social networks. In SIGKDD, 2008.
- Tackling higher-order relations and heterogeneity: Dynamic heterogeneous hypergraph network for spatiotemporal activity prediction. Neural Networks, 2023.
- Deep graph infomax. In ICLR, 2019.
- One-class graph neural networks for anomaly detection in attributed networks. Neural computing and applications, 2021.
- A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021.
- Scan: a structural clustering algorithm for networks. In SIGKDD, 2007.
- Graph contrastive learning with augmentations. In NIPS, 2020.
- Higher-order structure based anomaly detection on attributed networks. In Big Data, 2021.
- Reconstruction enhanced multi-view contrastive learning for anomaly detection on attributed networks. In IJCAI, 2022.
- Generative and contrastive self-supervised learning for graph anomaly detection. IEEE Transactions on Knowledge and Data Engineering, 2021.
- Subtractive aggregation for attributed network anomaly detection. In CIKM, 2021.