publications

2024

1. arxiv

   Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback

   Jingwei Sun, Zhixu Du, and Yiran Chen

   arXiv preprint arXiv:2405.19686, 2024

   PDF
2. ICML

   FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

   Best Paper Award in Federated Learning on the Edge, 2024 AAAI Spring Series Symposium

   Jingwei Sun, Ziyue Xu, Hongxu Yin, and 6 more authors

   Proceedings of the 41th International Conference on Machine Learning, 2024

   Bib PDF Website

   @article{sun2023fedbpt,
     title = {FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models},
     author = {Sun, Jingwei and Xu, Ziyue and Yin, Hongxu and Yang, Dong and Xu, Daguang and Liu, Yudong and Du, Zhixu and Chen, Yiran and Roth, Holger R},
     journal = {Proceedings of the 41th International Conference on Machine Learning},
     year = {2024},
     award = {Best Paper Award in Federated Learning on the Edge, 2024 AAAI Spring Series Symposium},
   }

3. MLSys

   SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models

   Zhixu Du, Shiyu Li, Yuhao Wu, and 8 more authors

   MLSys2024, 2024

   Bib

   @article{du2023sida,
     title = {SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models},
     author = {Du, Zhixu and Li, Shiyu and Wu, Yuhao and Jiang, Xiangyu and Sun, Jingwei and Zheng, Qilin and Wu, Yongkai and Li, Ang and Li, Hai and Chen, Yiran and others},
     journal = {MLSys2024},
     year = {2024}
   }

4. NeurIPS

   Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference

   Lin Duan*, Jingwei Sun*, Yiran Chen, and 1 more author

   NeurIPS, 2024

   PDF

2023

1. arxiv

   Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties

   Jingwei Sun, Zhixu Du, Anna Dai, and 4 more authors

   arXiv preprint arXiv:2303.18178, 2023

   PDF
2. ICCV

   Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples

   Jingwei Sun, Ziyue Xu, Dong Yang, and 6 more authors

   2023

   Bib PDF

   @article{sun2023communication,
     title = {Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples},
     author = {Sun, Jingwei and Xu, Ziyue and Yang, Dong and Nath, Vishwesh and Li, Wenqi and Zhao, Can and Xu, Daguang and Chen, Yiran and Roth, Holger R},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     year = {2023},
   }

3. ICML

   Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

   Jianyi Zhang, Ang Li, Minxue Tang, and 6 more authors

   arXiv preprint arXiv:2209.15245, 2023

   PDF

2022

1. SenSys

   FedSEA: A Semi-Asynchronous Federated Learning Framework for Extremely Heterogeneous Devices

   Jingwei Sun, Ang Li, Lin Duan, and 8 more authors

   2022

   Abs Bib HTML PDF

   Federated learning (FL) has attracted increasing attention as a promising technique to drive a vast number of edge devices with artificial intelligence. However, it is very challenging to guarantee the efficiency of a FL system in practice due to the heterogeneous computation resources on different devices. To improve the efficiency of FL systems in the real world, asynchronous FL (AFL) and semi-asynchronous FL (SAFL) methods are proposed such that the server does not need to wait for stragglers. However, existing AFL and SAFL systems suffer from poor accuracy and low efficiency in realistic settings where the data is non-IID distributed across devices and the on-device resources are extremely heterogeneous. In this work, we propose FedSEA - a semi-asynchronous FL framework for extremely heterogeneous devices. We theoretically disclose that the unbalanced aggregation frequency is a root cause of accuracy drop in SAFL. Based on this analysis, we design a training configuration scheduler to balance the aggregation frequency of devices such that the accuracy can be improved. To improve the efficiency of the system in realistic settings where the devices have dynamic on-device resource availability, we design a scheduler that can efficiently predict the arriving time of local updates from devices and adjust the synchronization time point according to the devices’ predicted arriving time. We also consider the extremely heterogeneous settings where there exist extremely lagging devices that take hundreds of times as long as the training time of the other devices. In the real world, there might be even some extreme stragglers which are not capable of training the global model. To enable these devices to join in training without impairing the systematic efficiency, Fed-SEA enables these extreme stragglers to conduct local training on much smaller models. Our experiments show that compared with status quo approaches, FedSEA improves the inference accuracy by 44.34% and reduces the systematic time cost and local training time cost by 87.02X and 792.9X. FedSEA also reduces the energy consumption of the devices with extremely limited resources by 752.9X.

   @article{sun2022fedsea,
     title = {FedSEA: A Semi-Asynchronous Federated Learning Framework for Extremely Heterogeneous Devices},
     author = {Sun, Jingwei and Li, Ang and Duan, Lin and Alam, Samiul and Deng, Xuliang and Guo, Xin and Wang, Haiming and Gorlatova, Maria and Zhang, Mi and Li, Hai and others},
     booktitle = {Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems},
     year = {2022},
   }

2. DistributedML

   Rethinking normalization methods in federated learning

   Zhixu Du*, Jingwei Sun*, Ang Li, and 4 more authors

   In Proceedings of the 3rd International Workshop on Distributed Machine Learning, 2022

   PDF
3. CIC

   Next Generation Federated Learning for Edge Devices: An Overview

   Jianyi Zhang, Zhixu Du, Jingwei Sun, and 7 more authors

   In 2022 IEEE 8th International Conference on Collaboration and Internet Computing (CIC), 2022

   Bib

   @inproceedings{zhang2022next,
     title = {Next Generation Federated Learning for Edge Devices: An Overview},
     author = {Zhang, Jianyi and Du, Zhixu and Sun, Jingwei and Li, Ang and Tang, Minxue and Wu, Yuhao and Gao, Zhihui and Kuo, Martin and Li, Hai-Helen and Chen, Yiran},
     booktitle = {2022 IEEE 8th International Conference on Collaboration and Internet Computing (CIC)},
     pages = {10--15},
     year = {2022},
     organization = {IEEE},
   }

2021

1. SEC

   LotteryFL: empower edge intelligence with personalized and communication-efficient federated learning

   Ang Li, Jingwei Sun, Binghui Wang, and 4 more authors

   In 2021 IEEE/ACM Symposium on Edge Computing (SEC), 2021

   arXiv Bib HTML Code

   @inproceedings{li2021lotteryfl,
     title = {LotteryFL: empower edge intelligence with personalized and communication-efficient federated learning},
     author = {Li, Ang and Sun, Jingwei and Wang, Binghui and Duan, Lin and Li, Sicheng and Chen, Yiran and Li, Hai},
     booktitle = {2021 IEEE/ACM Symposium on Edge Computing (SEC)},
     pages = {68--79},
     year = {2021},
     organization = {IEEE},
   }

2. CVPR

   Soteria: Provable defense against privacy leakage in federated learning from representation perspective

   Jingwei Sun, Ang Li, Binghui Wang, and 3 more authors

   In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021

   Bib PDF Code

   @inproceedings{sun2021soteria,
     title = {Soteria: Provable defense against privacy leakage in federated learning from representation perspective},
     author = {Sun, Jingwei and Li, Ang and Wang, Binghui and Yang, Huanrui and Li, Hai and Chen, Yiran},
     booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
     pages = {9311--9319},
     year = {2021},
   }

3. MobiCom

   Hermes: an efficient federated learning framework for heterogeneous mobile clients

   Ang Li, Jingwei Sun, Pengcheng Li, and 3 more authors

   In Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, 2021

   Bib PDF

   @inproceedings{li2021hermes,
     title = {Hermes: an efficient federated learning framework for heterogeneous mobile clients},
     author = {Li, Ang and Sun, Jingwei and Li, Pengcheng and Pu, Yu and Li, Hai and Chen, Yiran},
     booktitle = {Proceedings of the 27th Annual International Conference on Mobile Computing and Networking},
     pages = {420--437},
     year = {2021},
   }

4. NeurIPS

   Fl-wbc: Enhancing robustness against model poisoning attacks in federated learning from a client perspective

   Jingwei Sun, Ang Li, Louis DiValentin, and 3 more authors

   Advances in Neural Information Processing Systems, 2021

   Bib PDF Code

   @article{sun2021fl,
     title = {Fl-wbc: Enhancing robustness against model poisoning attacks in federated learning from a client perspective},
     author = {Sun, Jingwei and Li, Ang and DiValentin, Louis and Hassanzadeh, Amin and Chen, Yiran and Li, Hai},
     journal = {Advances in Neural Information Processing Systems},
     volume = {34},
     pages = {12613--12624},
     year = {2021},
   }

5. SenSys

   Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking

   Ang Li, Jingwei Sun, Xiao Zeng, and 3 more authors

   In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, 2021

   Bib HTML PDF

   @inproceedings{li2021fedmask,
     title = {Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking},
     author = {Li, Ang and Sun, Jingwei and Zeng, Xiao and Zhang, Mi and Li, Hai and Chen, Yiran},
     booktitle = {Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems},
     pages = {42--55},
     year = {2021},
   }