Li Xuan, Cheng Dejie, Zhang Luheng, Zhang Chengfang, Feng Ziliang
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China.
Entropy (Basel). 2025 Jan 1;27(1):28. doi: 10.3390/e27010028.
Graph anomaly detection is crucial in many high-impact applications across diverse fields. In anomaly detection tasks, collecting plenty of annotated data tends to be costly and laborious. As a result, few-shot learning has been explored to address the issue by requiring only a few labeled samples to achieve good performance. However, conventional few-shot models may not fully exploit the information within auxiliary sets, leading to suboptimal performance. To tackle these limitations, we propose a dual-level knowledge distillation-based approach for graph anomaly detection, DualKD, which leverages two distinct distillation losses to improve generalization capabilities. In our approach, we initially train a teacher model to generate prediction distributions as soft labels, capturing the entropy of uncertainty in the data. These soft labels are then employed to construct the corresponding loss for training a student model, which can capture more detailed node features. In addition, we introduce two representation distillation losses-short and long representation distillation-to effectively transfer knowledge from the auxiliary set to the target set. Comprehensive experiments conducted on four datasets verify that DualKD remarkably outperforms the advanced baselines, highlighting its effectiveness in enhancing identification performance.
图异常检测在众多不同领域的高影响力应用中至关重要。在异常检测任务中，收集大量带注释的数据往往既昂贵又费力。因此，人们探索了少样本学习来解决这个问题，即只需少量有标签的样本就能实现良好的性能。然而，传统的少样本模型可能无法充分利用辅助集中的信息，导致性能次优。为了解决这些局限性，我们提出了一种基于双层次知识蒸馏的图异常检测方法DualKD，该方法利用两种不同的蒸馏损失来提高泛化能力。在我们的方法中，我们首先训练一个教师模型来生成预测分布作为软标签，捕捉数据中不确定性的熵。然后使用这些软标签来构建用于训练学生模型的相应损失，该学生模型可以捕捉更详细的节点特征。此外，我们引入了两种表示蒸馏损失——短表示蒸馏和长表示蒸馏——以有效地将知识从辅助集转移到目标集。在四个数据集上进行的综合实验验证了DualKD显著优于先进的基线，突出了其在提高识别性能方面的有效性。
