Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 33, Issue 6, Pages 2393-2405Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3102609
Keywords
Anomaly detection; Bipartite graph; Task analysis; Feature extraction; Aggregates; Prediction algorithms; Collaboration; Graph anomaly detection; graph neural network (GNN); graph pattern mining; unsupervised learning
Categories
Funding
- Snap Research Fellowship
- National Science Foundation (NSF) [IIS-1849816, CCF-1901059]
Ask authors/readers for more resources
The study proposes a novel synergistic approach that combines pattern mining and feature learning for graph anomaly detection, showing significantly better performance than existing methods.
Detecting anomalies on graph data has two types of methods. One is pattern mining that discovers strange structures globally such as quasi-cliques, bipartite cores, or dense blocks in the graph's adjacency matrix. The other is feature learning that mainly uses graph neural networks (GNNs) to aggregate information from local neighborhood into node representations. However, there is a lack of study that utilizes both the global and local information for graph anomaly detection. In this article, we propose a synergistic approach that leverages pattern mining to inform the GNN algorithms on how to aggregate local information through connections to capture the global patterns. Specifically, it uses a GNN encoder to perform feature aggregation, and the pattern mining algorithms supervise the GNN training process through a novel loss function. We provide theoretical analysis on the effectiveness of the loss function, as well as empirical analysis on the proposed approach across a variety of GNN algorithms and pattern mining methods. Experiments on real-world data show that the synergistic approach performs significantly better than existing graph anomaly detection methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available