Eigenvector-based Graph Neural Network Embeddings and Trust Rating Prediction in Bitcoin Networks

Abstract

Given their strong performance on a variety of graph learning tasks, Graph Neural Networks (GNNs) are increasingly used to model financial networks. Traditional GNNs, however, are not able to capture higher-order topological information, and their performance is known to degrade with the presence of negative edges that may arise in many common financial applications. Considering the rich semantic inference of negative edges, excluding them as an obvious solution is not elegant. Alternatively, another basic approach is to apply positive normalization, however, this also may lead to information loss. Our work proposes a simple yet effective solution to overcome these two challenges by employing the eigenvectors with top-𝑘 largest eigenvalues of the raw adjacency matrix for preembeddings. These pre-embeddings contain high-order topological knowledge together with the information on negative edges, which are then fed into a GNN with a positively normalized adjacency matrix to compensate for its shortcomings. Through comprehensive experiments and analysis, we empirically demonstrate the superiority of our proposed solution in a Bitcoin user reputation score prediction task. CCS CONCEPTS• Applied computing → Secure online transactions.

Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis

“…In recent years, the development of LMs has revolutionized the field of NLP [1,2], leading to remarkable progress in a range of downstream tasks, including text classification [3,4], information retrieval [5,6,7,8], and multi-modalities [9,10,11]. While LMs have shown impressive performance in many tasks, there has been a debate over the effectiveness of simple data augmentation (DA) techniques, such as back-translation, for improving the FT performance.…”