Project Grant 2505107

This $599,999 Project Grant award from the National Science Foundation's Computer and Information Science and Engineering program (CFDA 47.070) supports the development of scalable and accurate solutions for temporal graph machine learning (TGML). The project aims to create a robust cyber infrastructure toolkit that enables efficient training and inference of TGML models, allowing researchers and practitioners to analyze large-scale temporal graphs with improved accuracy and scalability. The research leverages distributed heterogeneous computing systems integrating multi-core processors, GPUs, FPGAs, and high-bandwidth memory technologies. Key innovations include adaptive mini-batch and neighbor sampling, hyper node memory for efficient storage, and sparse temporal attention mechanisms. The project builds upon prior research in graph analytics and high-performance computing, and collaborates with industry partners to integrate these optimizations into their AI software ecosystems. The project demonstrates end-to-end applications in domains such as smart grids and social networks, working closely with domain experts to ensure practical relevance and impact.