Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current methods in this line posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of two novel modules, adaptive frequency response filters (AdaFreq) and graph normality alignment (GNA). AdaFreq learns a set of adaptive spectral filters that capture different frequency components of the labeled normal nodes with varying homophily in the channel-wise and cross-channel views of node attributes. GNA is introduced to enforce consistency between the channel-wise and cross-channel homophily representations to robustify the normality learned by the filters in the two views. Experiments on eight real-world GAD datasets show that RHO can effectively learn varying, often under-represented, homophily in the small normal node set and substantially outperforms state-of-the-art competing methods. Code is available at https://github.com/mala-lab/RHO.

翻译：半监督图异常检测（GAD）利用少量标记的正常节点，从图中的大量未标记节点中识别异常节点。当前方法通常假设：1）正常节点具有相似的同质性水平；2）标记的正常节点能充分代表正常类别的同质性模式。然而，由于真实世界GAD数据集中正常节点可能表现出多样化的同质性，这一假设往往难以成立。本文提出RHO（鲁棒同质性学习）方法，以自适应学习此类同质性模式。RHO包含两个创新模块：自适应频率响应滤波器（AdaFreq）和图正态性对齐（GNA）。AdaFreq通过学习一组自适应谱滤波器，在节点属性的通道内与跨通道视图中，捕获具有不同同质性的标记正常节点的各频率分量。GNA模块用于增强通道内与跨通道同质性表征的一致性，从而强化两个视图中滤波器学习到的正态性的鲁棒性。在八个真实世界GAD数据集上的实验表明，RHO能有效学习少量正常节点集中多样化且常被低估的同质性，并显著优于当前最先进的竞争方法。代码发布于 https://github.com/mala-lab/RHO。