Steve Weipeng Zhuo (卓伟鹏)

I am an assistant professor in the Department of Computer Science at BNU-HKBU United Internation College . Previously, I obtained my Ph.D. degree in Computer Science and Engineering from The Hong Kong University of Science and Technology (HKUST), under the supervision of Prof. Shueng-Han Gary Chan. Prior to that, I was an early founder in Pipe of Insight, a startup focused on online education using mobile devices, which raised angel round funding and series A financing. I obtained my BSc degree (double majored in Computer Science and Applied Math) and Master of Philosophy (MPhil) degree from HKUST. During my MPhil study, I was a visiting scholar in the Department of Electrical Engineering at Princeton University.

My research focuses on the design and application of graph neural networks (GNNs) on the internet of things (IoT) devices, including

Radio frequency signal analytics in smart city applications.
Graph neural networks and distributed training.
User behavior study in indoor localization.

Email / Google Scholar / Github

I have Ph.D. (co-supervised with Prof. Weifeng Su) and MPhil openings available. Successful applicants can get corresponding degrees conferred from Hong Kong Baptist University upon completion. Please feel free to contact me if you are interested.

Publications

	CATGNN: Cost-Efficient and Scalable Distributed Training for Graph Neural Networks Xin Huang, Weipeng Zhuo, Minh Phu Vuong, Shiju Li, Jongryool Kim, Bradley Rees, Chul-Ho Lee arXiv Preprint paper We design a distributed GNN training framework that leverages high-degree neighbors of each node to partition the graph efficiently.
	A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis Shuhan Zhong, Sizhe Song, Weipeng Zhuo, Guanyao Li, Yang Liu, S.-H. Gary Chan International Conference on Very Large Databases (VLDB), 2024 paper / code We propose an MLP-mixer with novel patching technique and residual loss to process multivariate time series data and make forecasting accurately.
	FIS-ONE: Floor Identification System with One Label for Crowdsourced RF Signals Weipeng Zhuo, Ka Ho Chiu, Jierun Chen, Ziqi Zhao, S.-H. Gary Chan, Sangtae Ha, Chul-Ho Lee IEEE International Conference on Distributed Computing Systems (ICDCS), 2023 paper / code We design a floor identification system for crowdsourced RF signals in a building using only one labeled data sample from the bottom floor.
	Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks Jierun Chen, Shiu-hong Kao, Hao He, Weipeng Zhuo, Song Wen, Chul-Ho Lee, S.-H. Gary Chan IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 paper / code We propose a simple yet fast and effective partial convolution (PConv), as well as a latency-efficient family of architectures called FasterNet.
	Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services Weipeng Zhuo, Ka Ho Chiu, Jierun Chen, Jiajie Tan, Edmund Sumpena, S.-H. Gary Chan, Sangtae Ha, Chul-Ho Lee, IEEE International Conference on Data Engineering (ICDE), 2023 paper / code We propose an efficient bipartite graph sample and aggregate mechanism (BiSAGE) to process ambient RF signals for geofencing applications such as elderly care and pandemic control, etc.
	TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing Jierun Chen, Tianlang He, Weipeng Zhuo, Li Ma, Sangtae Ha, S.-H. Gary Chan IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 paper / video / code TVConv works more computation-efficient than regular convolution when dealing with layout-specific tasks, e.g., face recognition.
	GRAFICS: Graph Embedding-based Floor Identification Using Crowdsourced RF Signals Weipeng Zhuo, Ziqi Zhao, Ka Ho Chiu, Shiju Li, Sangtae Ha, Chul-Ho Lee, S.-H. Gary Chan IEEE International Conference on Distributed Computing Systems (ICDCS), 2022 paper / code We model the RF signals crowdsourced within a building as a bipartite graph and process the graph with an extended version of LINE (E-LINE) for floor identification tasks.
	Tackling Multipath and Biased Training Data for IMU-assisted BLE Proximity Detection Tianlang He, Jiajie Tan, Weipeng Zhuo, Maximilian Printz, S-H Gary Chan IEEE International Conference on Computer Communications (INFOCOM), 2022 paper We propose PRID and PRID-lite to enable proximity detection using Bluetooth low energy (BLE) signals on commercial hardware and edge devices.
	IoT Geofencing for COVID-19 Home Quarantine Enforcement Jiajie Tan, Edmund Sumpena, Weipeng Zhuo, Ziqi Zhao, Mengyun Liu, S-H Gary Chan IEEE Internet of Things Magazine, 2020 paper SignatureHome is the prototype system for home quarantine of COVID-19 in Hong Kong. It mainly relies on the associated IP address and ambient WiFi signals.
	Error Modeling and Estimation Fusion for Indoor Localization Weipeng Zhuo, Bo Zhang, S-H Gary Chan, Edward Y Chang IEEE International Conference on Multimedia and Expo (ICME), 2012 paper We analyse location errors for different localization systems theoretically and propose an optimized fusion scheme for different systems.