GALE: Active Adversarial Learning for Erroneous Node Detection in Graphs
GALE: Active Adversarial Learning for Erroneous Node Detection in Graphs
复制标题
DOI：
10.1109/icde55515.2023.00134
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Sheng Guan;Hanchao Ma;Mengying Wang;Yinghui Wu
中科院分区：
文献类型：
--
作者：
Sheng Guan;Hanchao Ma;Mengying Wang;Yinghui Wu
我们引入了一种主动对抗学习框架GALE来检测属性图中存在错误信息的节点。GALE由一个新的对抗性主动错误检测框架授权，该框架将主动学习与图生成对抗模型交互，以最好地利用错误节点的有限标记示例。它根据节点的典型性，以有限的大小批量动态确定多样化的查询节点，以丰富样本池，从而提供代表性的样本，以最好地训练对抗分类器来捕获不同类型的错误。此外，GALE还提供了一种注释算法来建议可能正确的属性值和错误类型的上下文，以方便对查询节点进行标记。我们表明，在使用有限的查询和示例时，GALE显著改进了基于约束的检测、离群点检测和图神经网络（例如GCNs）等竞争方法，平均F-1分数提高了32%、31%和17%，并且在大型图的学习成本方面是可行的。
We introduce GALE, an active adversarial learning framework to detect nodes with erroneous information in attributed graphs. GALE is empowered by a new adversarial active error detection framework, which interacts active learning with a graph generative adversarial model to best exploit limited labeled examples of erroneous nodes. It dynamically determines diversified query nodes in batches with bounded size in terms of node typicality to enrich a pool of examples, which in turn provides representative examples to best train an adversarial classifier to capture different types of errors. Moreover, GALE provides an annotation algorithm to suggest a context of possible correct attribute values and error types, to facilitate the labeling of query nodes. We show that using limited queries and examples, GALE significantly improves competing methods such as constraint-based detection, outlier detection, and Graph Neural Networks (e.g. GCNs), with 32%, 31%, and 17% gain in F-1 score on average, and is feasible in learning cost for large graphs.