2026-09-21T05:17:58Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/124244 2024-09-16 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Tong, Hanghang 2024-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms The student, Ishika Agarwal, accepted the attached license on 2024-04-09 at 11:08. The student, Ishika Agarwal, submitted this Thesis for approval on 2024-04-09 at 11:15. This Thesis was approved for publication on 2024-04-09 at 14:24. DSpace SAF Submission Ingestion Package generated from Vireo submission #20339 on 2024-09-16 at 00:33:53 Graph Anomaly Detection Machine Learning Reinforcement Learning Active Learning Recently, detecting anomalies in attributed networks has gained a lot of attention from research communities due to the numerous real-world use cases in the financial, social media, medical, and agricultural domains. This thesis aims to explore node anomaly detection in two different aspects: soft-labeling, and multi-armed bandits. The environment in both settings is constrained to an active learning scenario where there is no direct access to ground truth labels but access to an oracle. This thesis comprises of three works: one using soft-labeling, another with multi-armed bandits, and a third that explores a combination of both. We present experimental results for each work to justify the algorithmic decisions that were made. Future work is also discussed to build on top of these methods. Text eng https://hdl.handle.net/2142/124244 Copyright 2024 Ishika Agarwal Active graph anomaly detection Agarwal, Ishika 2024-04-09 M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science