Prof. Song Guo
CAE Fellow, IEEE Fellow

Title: Neural-enhanced Edge Perception Systems


Song Guo is a Full Professor leading the Research Group of Networking and Mobile Computing at the Department of Computing, The Hong Kong Polytechnic University. He also holds a Changjiang Chair Professorship awarded by the Ministry of Education of China. Prof. Guo is a Fellow of the Canadian Academy of Engineering (FCAE), Fellow of the IEEE (FIEEE), and ACM Distinguished Member. He is the current Editor-in-Chief of IEEE Open Journal of the Computer Society and Chair of IEEE Communications Society (ComSoc) Space and Satellite Communications Technical Committee (SSCTC).

Prof. Guo is the founding director of the Edge Intelligence Lab at The Hong Kong Polytechnic University (PEIL). His research interests are mainly in edge AI, big data and machine learning, mobile computing, and distributed systems. He published many papers in top venues with wide impact in these areas and was recognized as a Highly Cited Researcher (Clarivate Web of Science).

More information on Prof. Guo’s website:


As to paving the last mile of enabling intelligent applications on ubiquitous edge devices, it is necessary to deploy the entire lifecycle (ecosystem) of data generation, representation extraction and model consumption near the user side, with the support of diverse machine learning techniques. This emerging scenario promotes the rise of Neural-enhanced Edge Perception (NEP) system, which handles the end-to-end processing procedure by synthetically optimizing the key components of large-scale learning paradigm, hardware-adaptive neural architecture and communication-efficient cross-device interaction. As a fundamental infrastructure to bring edge intelligence to the production environment, the NEP system offers great advantages in terms of multi-modality knowledge fusion, lightweight on-device analysis, real-time streaming processing and perfect rate-distortion balance on distributed collaborative devices. This talk gives a comprehensive inspection of implementing high-performance NEP systems, covering the realistic design challenges, possible solutions and promising research opportunities.