Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In many scenarios where CML is seen as the solution to privacy issues, such as health-related applications, safety is also a primary concern. To ensure that CML processes produce models that output correct and reliable decisions \emph{even in the presence of potentially untrusted participants}, researchers propose to use \textit{robust aggregators} to filter out malicious contributions that negatively influence the training process. In this work, we formalize the two prevalent forms of robust aggregators in the literature. We then show that neither can provide the intended protection: either they use distance-based metrics that cannot reliably identify malicious inputs to training; or use metrics based on the behavior of the loss function which create a conflict with the ability of CML participants to learn, i.e., they cannot eliminate the risk of compromise without preventing learning.
Conflict-Aware Client Selection for Multi-Server Federated Learning
1 School of Computer;Information Engineering, Xiamen University of Technology, Xiamen, China;2 Department of Electrical;Electronic Engineering, The University of Hong Kong, Hong Kong, China;3 Department of Computer Science, City University of Hong Kong, Hong Kong, China;4 School of Software \& Microelectronics, Peking University, Beijing, China;5 Institute for Imaging, Data;Communications, University of Edinburgh, UK
Collaboration! Towards Robust Neural Methods for Routing Problems
Nanyang Technological University(南洋理工大学);Eindhoven University of Technology(埃因霍温理工大学);Singapore Management University(新加坡管理大学);Shandong University(山东大学)
SVD-AE: Simple Autoencoders for Collaborative Filtering
Boeing Korea Engineering and Technology Center (BKETC)(波音韩国工程技术中心(BKETC));Yonsei University(延世大学);Ulsan National Institute of Science and Technology (UNIST)(蔚山国家科学技术研究院(UNIST));Georgia Institute of Technology(佐治亚理工学院);Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST))
Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing
College of Software, Sichuan University(四川大学软件学院);Department of Radiology, North Sichuan Medical College(北川医学院放射科);School of Electrical and Electronic Engineering, University College Dublin(都柏林大学学院电子与电气工程学院);School of Electronics and Information Engineering, Sichuan University(四川大学电子信息工程学院);College of Computer Science, Sichuan University(四川大学计算机科学学院)