Ye Yuan

A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series

2019 · arXiv (Cornell University)

This paper proposes a novel fault diagnosis approach based on generative adversarial networks (GAN) for imbalanced industrial time series where normal samples are much larger than failure cases. We combine a well-designed feature extractor with …

Scalable Graph Neural Networks via Bidirectional Propagation

2020 · arXiv (Cornell University)

Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most existing methods use "graph sampling" or "layer-wise …

Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks

2022 · 2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)

With the development of blockchain technology, a cryptocurrency based on blockchain technology is becoming more and more popular. The huge cryptocurrency transaction network has therefore received widespread attention. The link prediction learning structure of the …

NO-GAT: Neighbor Overlay-Induced Graph Attention Network

2024

Graph neural networks (GNNs) have garnered significant attention due to their ability to represent graph data. Among various GNN variants, graph attention network (GAT) stands out since it is able to dynamically learn the importance …