Spectrum-based Deep Neural Networks for Fraud Detection

Document Type


Publication Date



fraud detection, spectrum, deep neural networks


In this paper, we focus on fraud detection on a signed graph with only a small set of labeled training data. We propose a novel framework that combines deep neural networks and spectral graph analysis. In particular, we use the node projection (called as spectral coordinate) in the low dimensional spectral space of the graph's adjacency matrix as the input of deep neural networks. Spectral coordinates in the spectral space capture the most useful topology information of the network. Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible. We develop and evaluate two neural networks, deep autoencoder and convolutional neural network, in our fraud detection framework. Experimental results on a real signed graph show that our spectrum based deep neural networks are effective in fraud detection.


Principal Investigator: Xintao Wu

Acknowledgements: The authors acknowledge the support from the 973 Program of China (2014CB340404) to Shuhan Yuan and from National Science Foundation to Xintao Wu (1564250), Jun Li (1564348) and Aidong Lu (1564039). This research was conducted while Shuhan Yuan visited University of Arkansas.