通过对比学习提升异构图异常检测效率，适合嵌入式设备部署。
EAGLE: Contrastive Learning for Efficient Graph Anomaly Detection
- 基于元路径采样构建节点对比对，利用距离差异区分异常与正常节点。
- 在三个异构网络数据集上超越当前最优方法，准确率显著提升。
- 无需标签的自监督学习，适合资源受限场景下的实时异常检测。
图异常检测是众多现实场景中的重要任务，已有数十年研究历史。近年来，基于深度学习的方法表现出更优性能，但现有方法在效率上仍不足，难以应用于嵌入式设备。为此，我们提出一种基于对比学习的高效异构图异常检测模型EAGLE，通过对比异常节点与正常节点到局部上下文的距离来识别异常。该方法首先在元路径层面采样实例对进行对比学习；随后使用图自编码器无监督地学习有信息量的节点嵌入，并结合判别器预测节点异常得分。实验表明，EAGLE在三个异构网络数据集上均优于现有最先进方法。
原文摘要 · Abstract (English)
Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly detection. However, existing methods are lack of efficiency that is definitely necessary for embedded devices. Towards this end, we propose an Efficient Anomaly detection model on heterogeneous Graphs via contrastive LEarning (EAGLE) by contrasting abnormal nodes with normal ones in terms of their distances to the local context. The proposed method first samples instance pairs on meta path-level for contrastive learning. Then, a graph autoencoder-based model is applied to learn informative node embeddings in an unsupervised way, which will be further combined with the discriminator to predict the anomaly scores of nodes. Experimental results show that EAGLE outperforms the state-of-the-art methods on three heterogeneous network datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。