Lifelong Learning of Compositional Structures
arXiv:2007.07732
Abstract
A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structurally related problems. Learning such compositional structures has been a significant challenge for artificial systems, due to the combinatorial nature of the underlying search problem. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. We integrate these two lines of work to present a general-purpose framework for lifelong learning of compositional structures that can be used for solving a stream of related tasks. Our framework separates the learning process into two broad stages: learning how to best combine existing components in order to assimilate a novel problem, and learning how to adapt the set of existing components to accommodate the new problem. This separation explicitly handles the trade-off between the stability required to remember how to solve earlier tasks and the flexibility required to solve new tasks, as we show empirically in an extensive evaluation.
arXiv commentICLR-2021. Code: https://github.com/Lifelong-ML/Mendez2020Compositional.git
References in corpus (18)
- Overcoming catastrophic forgetting in neural networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Neural Architecture Search: A Survey
- Continual Learning Through Synaptic Intelligence
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Learning Task Grouping and Overlap in Multi-task Learning
- Continual Learning with Deep Generative Replay
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
- Making Neural Programming Architectures Generalize via Recursion
- Programming with a Differentiable Forth Interpreter
- Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
- Learning Sparse Networks Using Targeted Dropout
- Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
- Automatically Composing Representation Transformations as a Means for Generalization
- Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
- Modular Networks: Learning to Decompose Neural Computation
- Differentiable Programs with Neural Libraries