讲座主题： 联邦学习-数据不平衡处理技术

主 讲 人：Prof. Ligang He

时   间：2021年12月7日（星期二）下午4:00

讲座方式与地点：网络视频，腾讯会议 ID：662 608 005

腾讯会议链接https://meeting.tencent.com/dm/plYdBJgANcRg

欢迎广大师生踊跃参加！

讲座简介：

Title: Federated Learning – Part II Dealing with Data Imbalance

Abstract: Machine learning typically assume that the samples in the training dataset are well balanced in terms of the embedded features and sample values. However, it may not be the case in realistic scenarios. Especially in the scenario of federated learning, the clients may collect data in different locations and at different times, the data may well be imbalanced. In this talk, we will first discuss the impact of data imbalance on learning and then introduce the existing approaches on dealing with data imbalance. Next, we will present our work in dealing with the data imbalance for regression tasks. In our work, we propose a method to measure the uniqueness in terms of the samples’ feature space and the level of abnormality in terms of the samples’ values. We then associate the samples’ uniqueness and abnormality with the samples’ learning value and integrate them into the loss function. We will also present the evaluation results in the talk.

主讲人简介：Dr. Ligang He现为英国华威大学（University of Warwick ）计算机系终身教授，在学术界具有较高的声誉，在国际著名期刊（例如IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Computers，EEE Transactions on Network Science and Engineering、IEEE Transactions on Cloud Computing. IEEE Transactions on Services Computing, ACM Transactions on Computer Systems等）和重要会议上(例如VLDB，IPDPS, SC, HPCA, ICPP, ICSOC等)发表上述领域的论文150余篇。得到来自英国EPRSC、Leverhulme，欧盟及工业界的多项科研资助。研究方向包括大数据分析、并行分布式计算和云计算等。

此讲座对于研究联邦学习和边缘计算等相关领域研究有较好的启发意义，欢迎广大师生参加！