The present paper develops a graph-based sampling and consensus (GraphSAC) approach to effectively detect anomalous nodes in large-scale graphs. GraphSAC randomly draws subsets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node. These learned nominal distributions are minimally affected by the anomalous nodes, and hence can be directly adopted for anomaly detection. The per-draw complexity grows linearly with the number of edges, which implies efficient SSL, while draws can be run in parallel, thereby ensuring scalability to large graphs. GraphSAC is tested under different anomaly generation models based on random walks, as well as contemporary adversarial attacks for graph data. Experiments with real-world graphs showcase the advantage of GraphSAC relative to state-of-the-art alternatives.
|Original language||English (US)|
|Number of pages||5|
|Journal||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|State||Published - 2021|
|Event||2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada|
Duration: Jun 6 2021 → Jun 11 2021
Bibliographical noteFunding Information:
The work in this paper has been supported by the Doctoral Dissertation Fellowship of the Univ. of Minnesota, the USA NSF grants 171141, 1500713, and 1442686.
© 2021 IEEE