Publications
You can learn more about my papers through Google Scholar.
Privacy-preserving Machine Learning
Hengyuan Xu, Liyao Xiang, Hangyu Ye, Dixi Yao, Pengzhi Chu, Baochun Li. “Permutation Equivariance of Transformers and Its Applications” in Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 (CVPR), Seattle, USA, Jun 17 - Jun 21, 2024.
Dixi Yao, Liyao Xiang, Hengyuan Xu, Hangyu Ye, Yingqi Chen. “Privacy-Preserving Split Learning via Patch Shuffling over Transformers” in Proceedings of the 22nd IEEE International Conference on Data Mining (ICDM), Orlando, USA, November 28 - December 1, 2022. [Slides].[Code].
Dixi Yao, Baochun Li. “Is Split Learning Privacy-Preserving for Fine-Tuning Large Language Models?” in Special Issue on Pre-Trained Large Language Models of Transactions on Big Data (TBD). (To be appeared soon).
Hengyuan Xu, Liyao Xiang, Hangyu Ye, Dixi Yao, Pengzhi Chu, Baochun Li. “Shuffled Transformer for Privacy-Preserving Split Learning” arXiv 2304.07735, 2023.
Dixi Yao. “Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights” arXiv 2409.08482, 2024.
Dixi Yao. “Towards Privacy-Preserving Split Learning for ControlNet” in Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, Arizona, USA, Feburary 28 March 4, 2024.
Federated Learning
Dixi Yao, Baochun Li. “PerFedRLNAS: One-for-all Personalized Federated Neural Architecture Search” in Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, February 20-27, 2024. [Paper].[Supplementary].[Code].
Dixi Yao *, Lingdong Wang *, Jiayu Xu, Liyao Xiang, Shuo Shao, Yingqi Chen, Yanjun Tong. “Federated Model Search via Reinforcement Learning,” in Proceedings of the 41st IEEE International Conference on Distributed Computing Systems (ICDCS), Virtual, July 7 –10, 2021. [Slides]. [Code]
Dixi Yao “Survey on Personalized Federated Learning” in Proceedings of University of Toronto Engineering Research Conference (UTERC), Toronto, Canada, August 2, 2023.
Dixi Yao. “Revisiting System-Heterogeneous Federated Learning through Dynamic Model Search” in Proceedings of Special Session on Federated Learning on IEEE Internation Conference on Big Data 2024, Washington DC, USA, December 15-18, 2024.
Edge and Cloud Computing
Dixi Yao, Liyao Xiang, Zifan Wang, Jiayu Xu, Chao Li, Xinbing Wang. “Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud” in Proceedings of ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 5, Issue 4, December 2021. [Code].
Lingdong Wang, Liyao Xiang, Jiayu Xu, Jiaju Chen, Xing Zhao, Dixi Yao, Xinbing Wang, Baochun Li. “Context-Aware Deep Model Compression for Edge Cloud Computing,” in Proceedings of the 40th IEEE International Conference on Distributed Computing Systems (ICDCS), Singapore, July 8–10, 2020.