Continual Learning via Inter-Task Synaptic Mapping
arXiv:2106.13954 · doi:10.1016/j.knosys.2021.106947
Abstract
Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks from changing when accepting new concepts, these approaches do not exploit common information of each task which can be shared to existing neurons. As a result, they do not scale well to large-scale problems since the parameter importance variables quickly explode. An Inter-Task Synaptic Mapping (ISYANA) is proposed here to underpin knowledge retention for continual learning. ISYANA combines task-to-neuron relationship as well as concept-to-concept relationship such that it prevents a neuron to embrace distinct concepts while merely accepting relevant concept. Numerical study in the benchmark continual learning problems has been carried out followed by comparison against prominent continual learning algorithms. ISYANA exhibits competitive performance compared to state of the arts. Codes of ISYANA is made available in \url{https://github.com/ContinualAL/ISYANAKBS}.
arXiv commentThis paper has been published in Knowledge-based Systems
References in corpus (13)
- Overcoming catastrophic forgetting in neural networks
- Progressive Neural Networks
- Continual Learning Through Synaptic Intelligence
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
- Efficient Lifelong Learning with A-GEM
- Three scenarios for continual learning
- Progress & Compress: A scalable framework for continual learning
- Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Continual Learning with Deep Generative Replay
- Generative replay with feedback connections as a general strategy for continual learning
- Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting