Online Structured Meta-learning

Abstract

Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously updating the model with the learned prior. However, current online meta-learning algorithms are limited to learn a globally-shared meta-learner, which may lead to sub-optimal results when the tasks contain heterogeneous information that are distinct by nature and difficult to share. We overcome this limitation by proposing an online structured meta-learning (OSML) framework. Inspired by the knowledge organization of human and hierarchical feature representation, OSML explicitly disentangles the meta-learner as a meta-hierarchical graph with different knowledge blocks. When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks. Through the meta-knowledge pathway, the model is able to quickly adapt to the new task. In addition, new knowledge is further incorporated into the selected blocks. Experiments on three datasets demonstrate the effectiveness and interpretability of our proposed framework in the context of both homogeneous and heterogeneous tasks.

arXiv commentAccepted by NeurIPS 2020

References in corpus (27)

• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Efficient Lifelong Learning with A-GEM
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Few-Shot Learning with Graph Neural Networks
• Frustratingly Simple Few-Shot Object Detection
• Meta-Learning with Implicit Gradients
• Meta-Learning with Latent Embedding Optimization
• Lifelong Learning with Dynamically Expandable Networks
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Hierarchically Structured Meta-learning
• Online Meta-Learning
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
• Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
• TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
• Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
• Continual Learning with Adaptive Weights (CLAW)
• Probabilistic Model-Agnostic Meta-Learning
• Out-of-Domain Detection for Low-Resource Text Classification Tasks