報告題目：Towards Graph-level Anomaly Detection via Deep Evolutionary Mapping

報告時間：2023年12月12日上午10:00

報告地點：437bwin必贏國際官網大樓B404會議室

報告人：吳佳

報告人國籍：中國

報告人單位：麥考瑞大學

報告人簡介：吳佳，澳大利亞麥考瑞大學人工智能中心研究主管(Research Director) 、國際數據挖掘頂級期刊ACM Transactions on Knowledge Discovery Data（TKDD）副主編。2019 Heidelberg Laureate Forum Fellowship – 澳洲科學院 (Australian Academy of Science)。澳大利亞麥考瑞大學437bwin必贏國際官網教授、副院長分管博士研究生。主要研究領域為數據挖掘、機器學習、人工智能，及其在商業、工業、生物信息學、醫療信息學等領域的應用。迄今，在國際學術期刊和會議上共發表論文100多篇, 包括IEEE TPAMI、IEEE TKDE、IEEE TNNLS、IEEE TCYB、ACM TKDD、NeurIPS、WWW、ACM KDD、IEEE ICDM、ACM WSDM、IJCAI、AAAI、ACM CIKM等。指導學生獲得2022年頂級信息檢索領大會ACM CIKM最佳論文獎Runner-Up、2021年頂級數據挖掘大會IEEE ICDM最佳學生論文獎、2018頂級國際數據挖掘大會SIAM SDM最佳論文獎-Applied Data Science Track、2017頂級國際神經網絡大會IEEE IJCNN最佳學生論文獎。

報告摘要：Graph-level anomaly detection aims at capturing anomalous individual graphs in a graph set. Due to its significance in various real-world application fields, e.g., identifying rare molecules in chemistry and detecting potential frauds in online social networks, graph-level anomaly detection has received great attention recently. Although deep graph representation learning shows effectiveness in fusing high-level representations and capturing characters of individual graphs, most of the existing works are defective in graph-level anomaly detection because of their limited capability in exploring information across graphs, the imbalanced data distribution of anomalies, and low interpretability of the black-box graph neural networks (GNNs). To overcome these limitations, we propose a novel deep evolutionary graph mapping framework named GmapAD, which can adaptively map each graph into a new feature space based on its similarity to a set of representative nodes chosen from the graph set. Through our extensive experiments on nine real-world datasets, we demonstrate that our method has achieved statistically significant improvements compared to the state of the art in terms of precision, recall, F1 score, and AUC.

邀請人：杜博