Towards Anomaly-resistant Graph Neural Networks via Reinforcement Learning
Towards Anomaly-resistant Graph Neural Networks via Reinforcement Learning
复制标题
DOI：
10.1145/3459637.3482203
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Kaize Ding;Xuan Shan;Huan Liu
中科院分区：
文献类型：
--
作者：
Kaize Ding;Xuan Shan;Huan Liu
通常，图神经网络（GNN）采用消息传递方案来捕获节点的信息（即，节点属性和局部图结构）。然而，最近的研究表明，由于邻域聚合的脆弱性，GNN的性能很容易受到异常或恶意节点的存在的阻碍。因此，有必要在没有地面实况异常的先验知识的情况下学习抗异常的GNN，因为标记异常是昂贵的，并且需要密集的领域知识。虽然通过无监督异常检测方法消除异常可能是一种可能的解决方案，但由于两个学习过程之间的不可微差距，它可能会导致GNN模型在目标任务上的性能不合理。为了保持GNN在异常污染图上的有效性，本文提出了一种新的框架RARE-GNN（增强型异常抵抗图神经网络），它可以从输入图中检测异常并同时学习异常抵抗GNN。在真实数据集上的大量实验证明了该框架的有效性。
In general, graph neural networks (GNNs) adopt the message-passing scheme to capture the information of a node (i.e., nodal attributes, and local graph structure) by iteratively transforming, aggregating the features of its neighbors. Nonetheless, recent studies show that the performance of GNNs can be easily hampered by the existence of abnormal or malicious nodes due to the vulnerability of neighborhood aggregation. Thus it is necessary to learn anomaly-resistant GNNs without the prior knowledge of ground-truth anomalies, given the fact that labeling anomalies is costly and requires intensive domain knowledge. Though removing anomalies through unsupervised anomaly detection methods could be a possible solution, it may render unreasonable GNN model performance on target tasks due to the non-differentiable gap between the two learning procedures. In order to keep the effectiveness of GNNs on anomaly-contaminated graphs, in this paper, we propose a new framework named RARE-GNN (Reinforced Anomaly-REsistant Graph Neural Networks) which can detect anomalies from the input graph and learn anomaly-resistant GNNs simultaneously. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed framework.