科研团队
范晓亮
高级工程师、硕士生导师
fanxiaoliang@xmu.edu.cn

范晓亮,厦门大学信息学院高级工程师、硕士生导师。福建省智慧城市感知与计算重点实验室党支部书记、数字福建城市交通大数据研究所(厦门大学)常务副所长、联合国教科文组织国际自然与文化遗产空间技术中心HIST厦门分中心副主任、数字福建健康医疗大数据研究所副所长。厦门市高层次人才。法国巴黎六大计算机科学博士(2012),兰州大学计算机科学学士(2004)。研究兴趣:可信联邦学习、时空数据挖掘、图神经网络、服务计算主持和完成3项国家自然科学基金项目(2面上+1青年),以及百度、腾讯、厦门轨道集团等产学研项目。牵头高等教育领域隐私计算团体标准1项。编制厦门市集美区、同安区智慧城市建设”十四五“规划。在AAAI/IJCAI/WWW/UbiComp等会议和IEEE TSC/TKDE/TMC/TITS等期刊发表论文70+篇,1篇入选AAAI-2020最具影响力论文榜单(Google引用700+次)。授权发明专利13项(含专利权转让2项)、公开发明专利15项,出版译著1部。担任ICML/NeurIPS/AAAI/IJCAI等会议PC和TSC/TKDE/TMC/TITS/TII/TIST/TBD等期刊审稿人。CCF服务计算青年才俊奖(2022)、厦门大学龙胜达奖教金(2022)、2018年福建省科技进步一等奖(排名5/10)、CSC-IBM中国优秀教师奖教金、法国埃菲尔卓越博士奖学金(2010)、第十六届全国计算机支持的协同工作与社会计算学术会议最佳论文奖(2021)、第十四届全国普适计算学术会议最佳论文奖(2018)等。IEEE高级会员,IEEE教育数据挖掘工作组副主席,中国计算机学会CCF高级会员,CCF服务计算专委会执行委员、CCF普适计算专委会执行委员。

论文、代码:https://fanxlxmu.github.io


【主持项目列表(部分)】

1.  面向时空图的高效安全联邦学习关键问题研究,国家自然科学基金面上基金项目(62272403),范晓亮(主持),2023年1月-2026年12月,54万元(直接经费)

2.  大规模人群出行的不确定性分析与城市级别人流预测研究,国家自然科学基金面上基金项目(61872306),范晓亮(主持),2019年1月-2022年12月,64万元(直接经费)

3.  基于飞桨平台的时空图联邦学习模型高效优化研究,CCF-百度松果基金CCF-BAIDU OF2022016),范晓亮 (主持)20229—20238月,10万元

4.  联邦学习的模型训练方法,专利转让项目,范晓亮(主持),专利号: ZL202110150143.0,转让日期:202284日,转让金额:15万元

5.  城轨云、大数据应用关键指标研究项目,企事业委托项目(厦门轨道交通集团有限公司),范晓亮 (主持)20212-20222月,40万元

6.    智慧同安建设总体规划(2021—2025年),企事业委托项目(腾讯云计算(厦门)有限责任公司),范晓亮(主持),20219-20229月,9.725万元

7.  交通数据分析应用(2018),厦门市科技局产学研协同创新及科技合作项目(3502Z20193017),范晓亮(主持),20181-202012月,12.5万元

8.  集美区智慧城市建设十四五规划,企事业委托项目(集美区工信局),范晓亮(主持),20201-202012月,10万元

9.  交通数据分析应用(2018),企事业委托项目(卫星定位公司),范晓亮(主持),20181-201812月,25万元

10.  交通大数据智能分析应用算法,企事业委托项目(卫星定位公司),范晓亮(主持),20191-201912月,20.2万元


【发表论文】

Google Scholar完整列表:https://scholar.google.com/citations?user=gR7VT-4AAAAJ&hl=zh-CN&oi=ao

论文、代码:https://fanxlxmu.github.io 

五篇代表作(2023年6月更新)

1. [AAAI-23] Zheng Wang, Xiaoliang Fan*, Jianzhong Qi, Haibing Jin, Peizhen Yang, Siqi Chen, Cheng Wang, FedGS: Federated Graph-based Sampling with Arbitrary Client Availability, Proceedings of the Thirty-Seven AAAI Conference on Artificial Intelligence (AAAI-23), February 7-14, 2023, Washington, DC, USA.[CCF A类会议]

2. [IJCAI-22] Shangbin Wu, Xu Yan, Xiaoliang Fan*, Shirui Pan, Shichao Zhu, Chuanpan Zheng, Ming Cheng, Cheng Wang, Multi-Graph Fusion Networks for Urban Region Embedding, International Joint Conference on Artificial Intelligence (IJCAI-22), pp. 2312-2318, July 23-29, 2022 Messe Wien, Vienna, Austria. [CCF A类会议]. 

3. [IJCAI-21] Zheng Wang, Xiaoliang Fan*, Jianzhong Qi, Cheng Wang, Rongshan Yu, Chenglu Wen, Federated Learning with Fair Averaging, 30th International Joint Conference on Artificial Intelligence (IJCAI-21), pp.1615-1623, August 21-26, 2021, Montreal-themed virtual reality.[CCF A类会议]

4. [AAAI-20] Chuanpan Zheng, Xiaoliang Fan*, Jianzhong Qi, Cheng Wang, GMAN: A Graph Multi-Attention Network for Traffic Prediction, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 2020, 34(01): 1234-1241. [CCF A类会议,Google引用700+次Github网站:300+ stars, AAAI最具影响力论文]

5. [TKDE 2023] Chuanpan Zheng, Xiaoliang Fan*, Shirui Pan, Haibing Jin, Zhaopeng Peng, Zonghan Wu, Cheng Wang, Philip S. Yu, Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting, IEEE Transactions on Knowledge and Data Engineering, (accepted on June 1st, 2023). [CCF A类期刊]




研究方向 Research
发表的数据集 Datasets
GMAN多注意力图神经网络的城市交通预测方法
厦门大学范晓亮团队提出的“多注意力图神经网络的城市交通预测方法GMAN” 被AAAI-20录用,Google学术引用580+次、Github 300+ stars,获评AAAI-2020最具影响力论文。 GMAN特点:1)提出了三种图注意力机制(时间、空间和转移),缓解了时空误差传播; 2)实验验证(两个数据集:厦门交通流预测、美国PeMS交通流速预测),15/30/60分钟后预测精度达到SOTA,且1个小时以上的长时预测优势尤其显著;3)有效降低了attention算法的时间复杂度;4)在交通态势感知、疫情数据分析等领域落地应用:2020年3月为厦门市疫情回流风险预估和复工复产风险预判提供支撑,市领导批示,市交通局、市卫健委感谢信,学习强国、福建日报等报道。
FedSTgraph时空图联邦学习基准和评测开源平台
FedSTgraph是一个面向城市多任务服务的时空图联邦学习基准和评测开源平台。旨在通过该开源平台从鲁棒性、安全性、公平性、有效性等多个视角,对现有的图联邦学习的算法、基准开展实验验证和效果评测。FedSTgraph可为城市时空图智能应用和服务的落地应用提供方法指南。
FLGo轻量级联邦学习算法和基准开源平台
团队开源了主要面向学术界的轻量级联邦学习开源基准平台FLGo(280+ stars on Github,flgo-xmu.github.io),集成主流的FL算法和benchmarks(40+)、已与百度安全BFL平台、百度飞桨等适配。FLGo已受到百度、腾讯、字节、洞见等关注。
部分论文列表 Selected Publications
2023
Chuanpan Zheng, Xiaoliang Fan*, Shirui Pan, Haibing Jin, Zhaopeng Peng, Zonghan Wu, Cheng Wang, Philip S. Yu
Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
IEEE Transactions on Knowledge and Data Engineering
@article{zheng2021spatio, title={Spatio-temporal joint graph convolutional networks for traffic forecasting}, author={Zheng, Chuanpan and Fan, Xiaoliang and Pan, Shirui and Wu, Zonghan and Wang, Cheng and Yu, Philip S}, journal={arXiv preprint arXiv:2111.13684}, year={2021} }
Chuanpan Zheng, Xiaoliang Fan, Cheng Wang*, Jianzhong Qi, Chaochao Chen, Longbiao Chen
INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
(WWW-23)
@article{zheng2023increase, title={INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging}, author={Zheng, Chuanpan and Fan, Xiaoliang and Wang, Cheng and Qi, Jianzhong and Chen, Chaochao and Chen, Longbiao}, journal={arXiv preprint arXiv:2302.02738}, year={2023} }
Zheng Wang, Xiaoliang Fan*, Jianzhong Qi, Haibing Jin, Peizhen Yang, Siqi Shen, Cheng Wang
FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
Proceedings of the Thirty-Seven AAAI Conference on Artificial Intelligence (AAAI-23)
@article{wang2022federated, title={Federated Graph-based Sampling with Arbitrary Client Availability}, author={Wang, Zheng and Fan, Xiaoliang and Qi, Jianzhong and Jin, Haibing and Yang, Peizhen and Shen, Siqi and Wang, Cheng}, journal={arXiv preprint arXiv:2211.13975}, year={2022} }
2022
Liang Chen, Xiaoliang Fan*, Haibing Jin, Xiaotian Sun, Ming Cheng, Cheng Wang
FedRME: Federated Road Markings Extraction from Mobile LiDAR Point Clouds
The 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (IEEE CSCWD 2022)
FedRME: Federated Road Markings Extraction from Mobile LiDAR Point Clouds
Shangbin Wu, Xu Yan. Xiaoliang Fan*, Shirui Pan, Shichao Zhu, Chuanpan Zheng, Ming Cheng, Cheng Wang
Multi-Graph Fusion Networks for Urban Region Embedding
International Joint Conference on Artificial Intelligence (IJCAI-22)
@article{wu2022multi, title={Multi-Graph Fusion Networks for Urban Region Embedding}, author={Wu, Shangbin and Yan, Xu and Fan, Xiaoliang and Pan, Shirui and Zhu, Shichao and Zheng, Chuanpan and Cheng, Ming and Wang, Cheng}, journal={arXiv preprint arXiv:2201.09760}, year={2022} }
2021
Chuanpan Zheng, Cheng Wang*, Xiaoliang Fan, Jianzhong Qi, Xu Yan
STPC-Net: Learn Massive Geo-sensory Data as Spatio-Temporal Point Clouds
IEEE Transactions on Intelligent Transportation Systems
@article{zheng2021stpc, title={STPC-Net: Learn Massive Geo-Sensory Data as Spatio-Temporal Point Clouds}, author={Zheng, Chuanpan and Wang, Cheng and Fan, Xiaoliang and Qi, Jianzhong and Yan, Xu}, journal={IEEE Transactions on Intelligent Transportation Systems}, year={2021}, publisher={IEEE} }
Xiaoliang Fan, Yakun Hu, Zibin Zheng*, Yujie Wang, Patrick Brezillon, Wenbo Chen
CASR-TSE: Context-Aware Web Services Recommendation for Modeling Weighted Temporal-Spatial Effectiveness
IEEE Transactions on Services Computing
@article{fan2017casr, title={CASR-TSE: context-aware web services recommendation for modeling weighted temporal-spatial effectiveness}, author={Fan, Xiaoliang and Hu, Yakun and Zheng, Zibin and Wang, Yujie and Br{\'e}zillon, Patrick and Chen, Wenbo}, journal={IEEE Transactions on Services Computing}, volume={14}, number={1}, pages={58--70}, year={2017}, publisher={IEEE} }
Zheng Wang#, Xiaoliang Fan*, Jianzhong Qi, Cheng Wang, Rongshan Yu, Chenglu Wen
Federated Learning with Fair Averaging
30th International Joint Conference on Artificial Intelligence (IJCAI-21)
@article{wang2021federated, title={Federated Learning with Fair Averaging}, author={Wang, Zheng and Fan, Xiaoliang and Qi, Jianzhong and Wen, Chenglu and Wang, Cheng and Yu, Rongshan}, journal={arXiv preprint arXiv:2104.14937}, year={2021} }
2020
闫旭#,范晓亮*,郑传潘,臧彧,王程,程明,陈龙彪
基于图卷积神经网络的城市交通态势预测算法
浙江大学学报(工学版)
@article{闫旭2020基于图卷积神经网络的城市交通态势预测算法, title={基于图卷积神经网络的城市交通态势预测算法}, author={闫旭 and 范晓亮 and 郑传潘 and 臧彧 and 王程 and 程明 and 陈龙彪}, journal={浙江大学学报 (工学版)}, volume={54}, number={6}, pages={1147--1155}, year={2020} }
Chuanpan Zheng#, Xiaoliang Fan*, Jianzhong Qi, Cheng Wang
GMAN: A Graph Multi-Attention Network for Traffic Prediction
34th AAAI Conference on Artificial Intelligence (AAAI-20)
@inproceedings{zheng2020gman, title={Gman: A graph multi-attention network for traffic prediction}, author={Zheng, Chuanpan and Fan, Xiaoliang and Wang, Cheng and Qi, Jianzhong}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={34}, number={01}, pages={1234--1241}, year={2020} }
2019
Chuanpan Zheng#, Xiaoliang Fan*, Chenglu Wen, Cheng Wang
DeepSTD: Mining Spatio-Temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction
IEEE Transactions on Intelligent Transportation Systems (TITS)
@article{zheng2019deepstd, title={Deepstd: Mining spatio-temporal disturbances of multiple context factors for citywide traffic flow prediction}, author={Zheng, Chuanpan and Fan, Xiaoliang and Wen, Chenglu and Chen, Longbiao and Wang, Cheng and Li, Jonathan}, journal={IEEE Transactions on Intelligent Transportation Systems}, volume={21}, number={9}, pages={3744--3755}, year={2019}, publisher={IEEE} }