Home

Motif-aware temporal GCN for fraud detection in signed...

Author
Chong Mo, Song Li, Geoffrey K. F. Tso, Jiandong Zhou, Yiyan Qi, Mingjie Zhu
Date Updated
2022/11/23
Category
cs.LG
Date Published
2022/11/22
Date Retrieved
2022/11/24
Description
Graph convolutional networks (GCNs) is a class of artificial neural networks for processing data that can be represented as graphs. Since financial transactions can naturally be constructed as graphs, GCNs are widely applied in the financial industry, especially for financial fraud detection. In this paper, we focus on fraud detection on cryptocurrency truct networks. In the literature, most works focus on static networks. Whereas in this study, we consider the evolving nature of cryptocurrency networks, and use local structural as well as the balance theory to guide the training process. More specifically, we compute motif matrices to capture the local topological information, then use them in the GCN aggregation process. The generated embedding at each snapshot is a weighted average of embeddings within a time window, where the weights are learnable parameters. Since the trust networks is signed on each edge, balance theory is used to guide the training process. Experimental results on bitcoin-alpha and bitcoin-otc datasets show that the proposed model outperforms those in the literature.
Image
Posts
3
Readers
0
Score
1
Tweeters
3
URL
https://arxiv.org/abs/2211.13123
Property
TOP