Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency

作     者：Chen, Yuhong Song, Ailin Yin, Huifeng Zhong, Shuai Chen, Fuhai Xu, Qi Wang, Shiping Xu, Mingkun 

作者机构：College of Computer and Data Science Fuzhou University Fuzhou China Guangdong Institute of Intelligence Science and Technology Hengqin Zhuhai China University of Electronic Science and Technology of China Chengdu China Center for Brain Inspired Computing Research Department of Precision Instrument Tsinghua University Beijing China School of Computer Science and Technology Dalian University of Technology Dalian China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Contrastive Learning 

摘      要：The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain’s adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multiview incremental framework named MVIL aimed at emulating the brain’s fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network’s capacity for generalization. Experimental results on six benchmark datasets show MVIL’s effectiveness over state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.