@article{chen2025enhancedurbanregionprofiling,author={Chen, Weiliang and Ren, Qianqian and Liu, Yong and Sun, Jianguo and Lin, Feng},journal={IEEE Transactions on Information Forensics and Security},title={Adversarial Self-Supervised Learning for Secure and Robust Urban Region Profiling},year={2025},volume={20},number={},pages={8124-8138},keywords={Contrastive learning;Robustness;Perturbation methods;Forecasting;Training;Generators;Soft sensors;Semantics;Security;Resilience;Urban Region Profiling;Adversarial Contrastive Learning;Robust Forecasting;Adversarial Attacks;Smart City Security},doi={10.1109/TIFS.2025.3594165}}
IOTJ
Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction With Blockchain
Weiliang Chen, Li Jia, Yang Zhou†, and Qianqian Ren†
@article{10750313,author={Chen, Weiliang and Jia, Li and Zhou, Yang and Ren, Qianqian},journal={IEEE Internet of Things Journal},title={Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction With Blockchain},year={2025},volume={12},number={6},pages={7405-7420},keywords={Trajectory;Vehicle dynamics;Data models;Blockchains;Computational modeling;Federated learning;Servers;Accuracy;Predictive models;Decision making;Asynchronous federated learning (AFL);data sharing;deep reinforcement learning (DRL);differential privacy (DP);graph convolutional network;trajectory prediction},doi={10.1109/JIOT.2024.3495693},}
2024
arxiv
Attentive Graph Enhanced Region Representation Learning
Weiliang Chen, Qianqian Ren†, and Jinbao Li
2024
2023
CIKM
Region-Wise Attentive Multi-View Representation Learning For Urban Region Embedding
Weiliang Chen and Qianqian Ren†
In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, Birmingham, United Kingdom, 2023
Urban region embedding is an important and yet highly challenging issue due to the complexity and constantly changing nature of urban data. To address the challenges, we propose a Region-Wise Multi-View Representation Learning (ROMER) to capture multi-view dependencies and learn expressive representations of urban regions without the constraints of rigid neighbourhood region conditions. Our model focuses on learn urban region representation from multi-source urban data. First, we capture the multi-view correlations from mobility flow patterns, POI semantics and check-in dynamics. Then, we adopt global graph attention networks to learn similarity of any two vertices in graphs. To comprehensively consider and share features of multiple views, a two-stage fusion module is further proposed to learn weights with external attention to fuse multi-view embeddings. Extensive experiments for two downstream tasks on real-world datasets demonstrate that our model outperforms state-of-the-art methods by up to 17% improvement.
@inproceedings{10.1145/3583780.3615194,author={Chen, Weiliang and Ren, Qianqian},title={Region-Wise Attentive Multi-View Representation Learning For Urban Region Embedding},year={2023},isbn={9798400701245},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3583780.3615194},doi={10.1145/3583780.3615194},booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},pages={3763–3767},numpages={5},keywords={graph attention, graph neural network, multi-feature fusion, urban region embedding},location={Birmingham, United Kingdom},series={CIKM '23}}
Attentive Graph Enhanced Region Representation Learning2024