SC²I Seminar | Enabling Real-Time Deep Graph Inference with Edge Computing
Graph Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures. To render GNN-based service for IoT-driven smart applications, the traditional model serving paradigm resorts to the cloud by fully uploading the geo-distributed input data to the remote datacenter. However, our empirical measurements reveal the significant communication overhead of such cloud-based serving and highlight the profound potential in applying the emerging edge computing. To maximize the architectural benefits brought by edge computing, in this talk we present Fograph, a novel distributed real-time GNN inference framework that leverages diverse resources of multiple edge nodes in proximity to IoT data sources. By introducing heterogeneity-aware execution planning and GNN-specific compression techniques, Fograph tailors its design to well accommodate the unique characteristics of GNN serving in edge environments.
Dr. Xu Chen is currently a Full Professor and Assistant Dean at School of Computer Science and Engineering, and the Director of Institute of Advanced Networking and Computing Systems and Vice Director of National Engineering Research Laboratory of Digital Homes, Sun Yat-sen University, Guangzhou, China, He obtained the Ph.D. degree in Information Engineering from The Chinese University of Hong Kong and worked as a Postdoctoral Fellow with Arizona State University in USA and then a Humboldt Scholar Fellow with University of Goettingen in Germany.
Dr. Chen has published over 200 scientific papers in leading international conferences and journals, many of which appear in top-tier conferences such as MOBIHOC, ICDCS and INFOCOM and top-tier journals such as IEEE JSAC, IEEE TON and IEEE TMC. His research results have been highly visible, with multiple publications being selected as 1‰ ESI Hot Papers by Web of Science. For his high-quality research works, Dr. Chen received the prestigious Humboldt research fellowship awarded by Alexander von Humboldt Foundation, 2014 Hong Kong Young Scientist Runner-up Award, 2022 IEEE Communications Society Asia Pacific Outstanding Paper Award, 2022 IEEE Internet of Things Journal Best Paper Runner-Up Award, 2022 IEEE Computer Society Best Paper Awards Runner-up , 2017 IEEE Communication Society Asia-Pacific Outstanding Young Researcher Award, 2017 IEEE ComSoc Young Professional Best Paper Award, Best Paper Runner-up Award of 2014 IEEE International Conference on Computer Communications (INFOCOM), and Best Paper Award of 2017 IEEE International Conference on Communications (ICC).
Dr. Chen is an IEEE ComSoc Distinguished Lecturer (2023-2024), and serves as an area editor (IoT/Edge/Cloud areas) for IEEE Open Journal of the Communications Society, and associate editors for IEEE Transactions on Wireless Communications, IEEE Transactions on Vehicular Technology, IEEE Internet of Things Journal, and IEEE Journal on Selected Areas in Communications (JSAC) Series on Network Softwarization and Enablers. He also serves as TPC members for a series of top tier conferences including MOBIHOC and INFOCOM.