[2603.25614] Social Hippocampus Memory Learning

Computer Science > Machine Learning arXiv:2603.25614 (cs) [Submitted on 26 Mar 2026] Title:Social Hippocampus Memory Learning Authors:Liping Yi, Zhiming Zhao, Qinghua Hu View a PDF of the paper titled Social Hippocampus Memory Learning, by Liping Yi and 2 other authors View PDF HTML (experimental) Abstract:Social learning highlights that learning agents improve not in isolation, but through interaction and structured knowledge exchange with others. When introduced into machine learning, this principle gives rise to social machine learning (SML), where multiple agents collaboratively learn by sharing abstracted knowledge. Federated learning (FL) provides a natural collaboration substrate for this paradigm, yet existing heterogeneous FL approaches often rely on sharing model parameters or intermediate representations, which may expose sensitive information and incur additional overhead. In this work, we propose SoHip (Social Hippocampus Memory Learning), a memory-centric social machine learning framework that enables collaboration among heterogeneous agents via memory sharing rather than model sharing. SoHip abstracts each agent's individual short-term memory from local representations, consolidates it into individual long-term memory through a hippocampus-inspired mechanism, and fuses it with collectively aggregated long-term memory to enhance local prediction. Throughout the process, raw data and local models remain on-device, while only lightweight memory are exchanged. W...