CHICAGO -- Among the many possible feats on a baseball diamond, there is something satisfying about a cycle. There are more impactful accomplishments, but there is also a bit of magic and wonder that ...

Abstract: Federated Learning (FL) facilitates decentralized model training without the exchange of raw data, thereby guaranteeing privacy. However, due to its distributed nature, this paradigm is ...

This project implements and compares Temporal Graph Neural Networks (TGNNs) for detecting fraudulent transactions in financial networks. We've built a complete end-to-end system including model ...

Abstract: Vertex-frequency analysis (VFA) is a useful technique in graph signal processing to extract the correspondence between frequencies and vertices. VFA can be calculated by the windowed graph ...