Events

Seminar on "What Contributes More to the Robustness of Heterophilic Graph Neural Networks?" by Mr Junyuan Fang

Date: 8 March 2024, Friday Time: 4:30pm Venue: YEUNG Y5-202, City University of Hong Kong Zoom Meeting ID: 955 7075 2299 Password: 123456 Speaker: Mr Junyuan Fang, City University of Hong Kong What Contributes More to the Robustness of Heterophilic Graph Neural Networks? Mr Junyuan Fang, City University of Hong Kong   Abstract:In recent years, graph neural networks (GNNs) have gained significant attention due to their outstanding performance on graph-related tasks by utilizing neighborhood aggregation. However, traditional GNNs are primarily designed based on the homophily assumption, which means that they show poor performance on heterophilic networks where dissimilar nodes prefer to connect. To address this issue, several heterophilic GNNs have been proposed that employ techniques such as extending local neighbors and improving GNN architectures. From another perspective, recent studies have shown that, unlike homophilic GNNs, heterophilic GNNs exhibit higher robustness against graph adversarial attacks. In these attacks, the attackers try to inject small perturbations into the graph. Therefore, in this study, we delve into the core designs of heterophilic GNNs, including high-order neighbor, potential neighbor, ego-neighbor separation, and inter-layer combination designs. We further analyze the influence of these key designs on the robustness of GNNs. To compare the impact of different designs on baseline and real-world GNN models, we conducted comprehensive experiments. The findings of this work can serve as a reference for future studies aiming to design more robust and universal GNNs.   Speaker’s Bio:Junyuan Fang received the B.Eng. degree in software engineering from the Guangdong University of Technology, Guangzhou, China, in 2018, and the M.Eng. degree in software engineering from Sun Yat-sen University, Guangzhou, in 2020. He is currently pursuing the Ph.D. degree with the Department of Electrical Engineering, City University of Hong Kong. His current research interests include robustness analysis and optimization, applications of network science, and graph mining.   WEBINAR WEBSITE: http://cccn.ee.cityu.edu.hk/webinar/

Seminar on "Integrated electricity-gas-hydrogen systems: Techno-economic modelling, challenges, and opportunities" by Prof Pierluigi Mancarella

Date: 5 March 2024, Tuesday Time: 10:00 am Venue: Room CF617, Department of Electrical and Electronic Engineering, PolyU Speaker: Prof Pierluigi Mancarella, University of Melbourne

Seminar on "Unravel the Complex Interplay in Power Networks" by Miss Jade Li

Date: 1 March 2024, Friday Time: 4:30pm Venue: YEUNG Y5-202, City University of Hong Kong Zoom Meeting ID: 955 7075 2299 Password: 123456 Speaker: Miss Jade Li, City University of Hong Kong   Unravel the Complex Interplay in Power Networks Miss Jade Li, City University of Hong Kong   Abstract: Simplicity lies on the other side of complexity. Analyzing the topology of a static network helps uncover fundamental phenomena in these networks. In engineering practice of power systems, though, a demand arises for dynamic and practical system-level analysis that goes beyond static topological approaches. In this presentation, we further adapt complex network methods to the context of power systems, modifying them to better suit the unique characteristics of power systems. We specifically focus on unraveling those complex nonlinear phenomena, such as synchronization and voltage instability problems. The proposed methods have the potential to inspire future research initiatives in power systems as well as other complex network domains.   Speaker’s Bio: Meixuan Jade LI received the B.Eng. degree in electrical engineering and automation from the Harbin Institute of Technology, Harbin, China, in 2019. She is currently pursuing the Ph.D. degree in electrical engineering with the City University of Hong Kong, Hong Kong. Her current research interests include challenges faced by modern power systems and the application of complex networks.   WEBINAR WEBSITE: http://cccn.ee.cityu.edu.hk/webinar/  

Seminar on "Using AI to Model Business Growth and Its Implications for Business" by Mr Sean Kong

Date: 23 February 2024, Friday Time: 4:30pm Venue: YEUNG G7603, City University of Hong Kong Zoom Meeting ID: 955 7075 2299 Password: 123456 Speaker: Mr Sean Kong, City University of Hong Kong   Using AI to Model Business Growth and Its Implications for Business Mr Sean Kong, City University of Hong Kong   Abstract: Statistical modeling of univariate data like business growth could be complex and would be difficult to make use of growth data. This talk aims to show the simplification of such a process by utilizing network sciences to retrieve a simple differential equation to model growth and artificial intelligence to extract useful information from growth data by estimating the parameters of the differential equation. How business owners can use such info to grow their business will be discussed.   Speaker’s Bio: Sean Kong is an undergraduate student in the Department of Electrical Engineering at CityU. With a remarkable academic record in high school, Sean earned a special admission to the undergraduate program at CityU at the age of 13. His recent interest lies in the practical implementation of AI, computer vision, and reinforcement learning.   WEBINAR WEBSITE: http://cccn.ee.cityu.edu.hk/webinar/

Seminar on "New Energy Science and Digital Energy from Physics First Principle" by Dr. Xiao Yan

Date: 21 February 2024, Wednesday Time: 4:00pm - 5:00pm Venue: Room CF617, Department of Electrical and Electronic Engineering, PolyU Speaker: Dr. Xiao Yan, The Hong Kong Polytechnic University.

Seminar on "Bruce Lee-Inspired Fluid Antenna System for Extreme Massive Connectivity" by Prof. Kai-Kit Wong

Date: 26 January 2024, Friday Time: 4:30pm Venue: Room CD634, Department of Electrical and Electronic Engineering, PolyU Speaker: Prof. Kai-Kit Wong, University College London

Women in Electrical and Electronic Engineering (WiEEE) Gathering 2024

The Women in Electrical and Electronic Engineering (WiEEE) Gathering 2024 was held by the Department at the PolyU Staff Club Restaurant, U.Green, on 18 January 2024 with the support of over 50 participants, including students, teachers and alumni. The event, with the theme “Women's Journey on the Engineering Track: Overcoming Challenges and Achieving Excellence”, brought together a diverse group of women in the engineering field. Nine alumni, including Ms Candice Chow, Ms Catherine Li, Ir Jaimi Siu, Ms So Shuk Mei, Dr Ginny Wong, Ms Gloria Wong, Ms Melody Yang, Ms Gigi Yau and Ir Fiona Yee, generously shared their personal experiences and professional journeys in the industry. The event featured individual sharing, panel discussion, and interactive sessions, providing our female students with valuable insights and networking opportunities to foster a supportive community for women in engineering.  

Seminar on "From Micro To Nano: Manipulating Structure And Function" by Prof Zhang Haixia

Date: 8 January 2024, Monday Time: 10:00 am Venue: Room CF617, Department of Electrical and Electronic Engineering, PolyU Speaker: Prof Zhang Haixia, School of Integrated Circuit, Peking University

Seminar on "High Impact Publishing at Joule" by Dr Andrew Wadsworth

Date: 11 December 2023, Monday Time: 4:30 pm Venue: Room CD634, Department of Electrical and Electronic Engineering, PolyU Speaker: Dr Andrew Wadsworth, Scientific Editor at Joule

Seminar on Reinforcement Learning Approach to Data-Driven Optimal Control of Dynamical Systems with Communication Uncertainties

Date: 8 December 2023, Friday Time: 4:30 pm Venue: YEUNG Y5-203, City University of Hong Kong Zoom Meeting ID: 967 1968 0176 Password: 123456 Speaker: Dr Yi Jiang, City University of Hong Kong   Reinforcement Learning Approach to Data-Driven Optimal Control of Dynamical Systems with Communication Uncertainties Dr Yi Jiang, City University of Hong Kong   Abstract: Data-driven optimal control problem is a focal issue in systems and control engineering, which have attracted considerable attention from the systems and control communities. Notably, in many practical applications, control systems suffer from various uncertainties from modeling, parameter estimation and the environment. In engineering applications, actuator, sensor, controller, and their communication channels are generally contaminated with noise. Moreover, system models and communication networks are subjected to uncertain constraints such as packet dropouts, transmission delays, data quantization errors, and data rate limitation. All such uncertainties typically render the underlying systems to be uncertain, which in turn adversely affects the equipped online algorithms designed and operated based on the advanced reinforcement learning and adaptive/approximate dynamic programming. In this talk, data-driven optimal control problems for both linear and nonlinear systems in presence of packet dropout are investigated. A modified Algebraic Riccati equation and a Bernoulli model-based Hamilton-Jacobi-Bellman equation are developed with known system dynamics and probability models of packet dropouts. Two reinforcement learning-based policy iteration and value iteration algorithms are further developed to obtain the solutions to them, and their convergence analysis is also provided.   Speaker’s Bio: Dr Yi Jiang received the B.Eng. degree in automation, M.S. and Ph.D. degrees in control theory and control engineering from Northeastern University, Shenyang, Liaoning, China in 2014, 2016 and 2020, respectively. From January to July 2017, he was a Visiting Scholar with the UTA Research Institute, University of Texas at Arlington, TX, USA, and from March 2018 to March 2019, he was a Research Assistant with the University of Alberta, Edmonton, Canada. Currently, he is a Postdoc Fellow with the City University of Hong Kong, China. His research interests include networked control systems, industrial process operational control, reinforcement learning and event-triggered control.   WEBINAR WEBSITE: http://cccn.ee.cityu.edu.hk/webinar/