Federated learning (FL) is a collaborative machine learning paradigm which ensures data privacy by training models across distributed datasets without centralizing sensitive information. Vertical Federated Learning (VFL), a kind of FL training method, facilitates collaboration among participants with each client having received a different feature space of a shared user set. VFL thus, proves invaluable in privacy-sensitive domains such as finance and healthcare. Despite its inherent advantages, VFL faced challenges including communication bottlenecks, computational inefficiency, and slow convergence due to non-IID data distributions. This paper introduces FedOptimus, a robust Multi-VFL framework integrating advanced techniques for improved model efficiency and scalability. FedOptimus leverages a Mutual Information (MI)-based client selection to prioritize high-contribution participants, reducing computational overhead. Further, it incorporates server-side momentum techniques like FedAvgM and SLOWMO to stabilize updates and accelerate convergence on heterogeneous data. Additionally, performing K-Step Averaging minimizes communication costs while maintaining model performance. FedOptimus proves to be superior in performance on benchmark datasets such as CIFAR-10, MNIST, and FMNIST, showcasing its scalability and effectiveness in real-world multi-server, multi-client settings. By unifying advanced optimization methods, FedOptimus sets a new standard for efficient and scalable Vertical Federated Learning frameworks, paving the way for broader adoption in complex, privacy-sensitive domains.
Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning
University of Cincinnati(辛辛那提大学);University of Wisconsin Milwaukee(威斯康星大学密尔沃基分校);IBM T. J. Watson Research Center(IBM托马斯·J·沃森研究中心);University of Nebraska-Lincoln(内布拉斯加大学林肯分校);Northeastern University(东北大学)
Low-Latency Cooperative Spectrum Sensing via Truncated Vertical Federated Learning
The Future Network of Intelligence Institute(未来网络智能研究院);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院)
Vertical Federated Learning: Challenges, Methodologies and Experiments
School of Electrical and Optical Engineering, Nanjing University of Science and Technology(南京理工大学电气与光学工程学院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61分部);China Academy of Information and Communication Technology (CAICT)(中国信息通信研究院);Shanghai Jiao Tong University(上海交通大学);Nanjing University(南京大学)
A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT
University of Cambridge(剑桥大学);Real-Time and Embedded Computing Systems Research Centre (CISTER)(实时与嵌入式计算系统研究中心(CISTER));Commonwealth Scientific and Industrial Research Organization (CSIRO)(英联邦科学与工业研究组织(CSIRO));University of New South Wales(新南威尔士大学);Nanyang Technological University(南洋理工大学);Koç University(科克大学)
Vertical Federated Learning: Concepts, Advances and Challenges
Institute for AI Industry Research, Tsinghua University(清华大学人工智能产业研究院);Webank(微众银行);AsiaInfo Technologies(亚信科技);Hong Kong University of Science and Technology(香港科技大学)
Xidian University(西安电子科技大学);JD Tech(京东科技);MBZUAI(穆罕默德·本·扎耶德人工智能大学);JD Finance America Corporation(京东金融美国公司);Simon Fraser University(西蒙弗雷泽大学);University of Pittsburgh(匹兹堡大学)
Communication-efficient Vertical Federated Learning via Compressed Error Feedback
Carnegie Mellon University(卡内基梅隆大学);Institute for Systems and Robotics(系统与机器人研究所);Instituto Superior Técnico(里斯本高等理工学院);NOVA School of Science and Technology(NOVA科学技术学院)
Vertical Federated Learning with Missing Features During Training and Inference
Department of Electrical and Computer Engineering, Carnegie Mellon University(卡内基梅隆大学电气与计算机工程系);Institute for Systems and Robotics, Instituto Superior Técnico(系统与机器人研究所,技术高等学院);IBM T. J. Watson Research Center(IBM沃森研究中心);CMU(卡内基梅隆大学);IBM Research(IBM研究)
Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
Elmore Family School of Electrical and Computer Engineering, Purdue University(电气与计算机工程学院,普渡大学);Department of Computer Science and Engineering, Yonsei University(计算机科学与工程系,延世大学)