联邦学习（Federated Learning）是人工智能领域的一项前沿研究方向，旨在解决多个参与方拥有分布式数据，又不方便集中存储或共享数据的问题。在联邦学习中，每个参与方（如移动设备、边缘服务器、个人设备等）都持有自己的本地数据，而模型的训练在本地进行，仅通过交换模型参数的方式进行信息共享，从而实现全局模型的训练。

其中，联邦学习中的数据异构指的是在同一问题领域内，不同数据之间在特征分布、数据结构、性质等方面存在显著差异的情况。换句话说，数据异构问题出现在不同数据源、不同数据集或不同时间点收集的数据之间存在差异，这些差异可能会影响数据的处理、分析和建模过程。

相关成果：

[1] Xinyi Shang, Yang Lu*, Gang Huang, and Hanzi Wang, “Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features,” in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), pp.2218-2224, Vienna, Austria, July 23-29, 2022. (CCF A)

[2] Xinyi Shang, Yang Lu*, Yiu-ming Cheung, and Hanzi Wang, “FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), pp.1-6, Taipei, Taiwan, July 18-22, 2022. (CCF B)

[3] Yang Lu, Pinxin Qian, Gang Huang, and Hanzi Wang,  “Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Greece, June 4-10, 2023. (CCF B)

[4] Pinxin Qian, Yang Lu*, and Hanzi Wang, “Long-Tailed Federated Learning via Aggregated Meta Mapping” in Proceedings of IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, October 8-11, 2023. (CCF C)