Cooperative Learning
Cooperative learning explores methods for multiple agents or data sources to collaboratively train models or solve problems, aiming to improve efficiency, accuracy, and robustness beyond what individual entities could achieve alone. Current research focuses on developing algorithms and architectures that facilitate effective knowledge sharing and data aggregation, including techniques like federated learning, Gaussian processes, and attention mechanisms, often addressing challenges related to data heterogeneity, privacy, and computational cost. This field is significant for advancing machine learning in diverse applications, from improving plant identification AI through crowdsourced data to optimizing fuel economy in vehicle fleets and enhancing cancer survival analysis using multimodal data.
Papers
Cooperative Learning with Gaussian Processes for Euler-Lagrange Systems Tracking Control under Switching Topologies
Zewen Yang, Songbo Dong, Armin Lederer, Xiaobing Dai, Siyu Chen, Stefan Sosnowski, Georges Hattab, Sandra Hirche
Whom to Trust? Elective Learning for Distributed Gaussian Process Regression
Zewen Yang, Xiaobing Dai, Akshat Dubey, Sandra Hirche, Georges Hattab