Online Structured Meta-learning

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.

[1]  Sung Whan Yoon,et al.  TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning , 2019, ICML.

[2]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[3]  Thomas L. Griffiths,et al.  Recasting Gradient-Based Meta-Learning as Hierarchical Bayes , 2018, ICLR.

[4]  Sergey Levine,et al.  Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL , 2018, ICLR.

[5]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[6]  Sergey Levine,et al.  Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm , 2017, ICLR.

[7]  Richard Socher,et al.  Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting , 2019, ICML.

[8]  Hugo Larochelle,et al.  Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples , 2019, ICLR.

[9]  Yang Yu,et al.  Out-of-Domain Detection for Low-Resource Text Classification Tasks , 2019, EMNLP.

[10]  Ying Wei,et al.  Hierarchically Structured Meta-learning , 2019, ICML.

[11]  Seungjin Choi,et al.  Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace , 2018, ICML.

[12]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[13]  Pieter Abbeel,et al.  Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments , 2017, ICLR.

[14]  Pieter Abbeel,et al.  A Simple Neural Attentive Meta-Learner , 2017, ICLR.

[15]  J. Schulman,et al.  Reptile: a Scalable Metalearning Algorithm , 2018 .

[16]  Hang Li,et al.  Meta-SGD: Learning to Learn Quickly for Few Shot Learning , 2017, ArXiv.

[17]  Alexandre Lacoste,et al.  TADAM: Task dependent adaptive metric for improved few-shot learning , 2018, NeurIPS.

[18]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[20]  Sung Ju Hwang,et al.  Lifelong Learning with Dynamically Expandable Networks , 2017, ICLR.

[21]  Yong Wang,et al.  Meta-Learning for Low-Resource Neural Machine Translation , 2018, EMNLP.

[22]  Sergey Levine,et al.  Online Meta-Learning , 2019, ICML.

[23]  Joseph J. Lim,et al.  Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation , 2019, NeurIPS.

[24]  Yee Whye Teh,et al.  Progress & Compress: A scalable framework for continual learning , 2018, ICML.

[25]  Yi Yang,et al.  Transductive Propagation Network for Few-shot Learning , 2018, ArXiv.

[26]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Sergey Levine,et al.  Probabilistic Model-Agnostic Meta-Learning , 2018, NeurIPS.

[28]  Joan Bruna,et al.  Few-Shot Learning with Graph Neural Networks , 2017, ICLR.

[29]  Trevor Darrell,et al.  Frustratingly Simple Few-Shot Object Detection , 2020, ICML.

[30]  Marc'Aurelio Ranzato,et al.  Efficient Lifelong Learning with A-GEM , 2018, ICLR.

[31]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[32]  Chrisantha Fernando,et al.  PathNet: Evolution Channels Gradient Descent in Super Neural Networks , 2017, ArXiv.

[33]  Xian Wu,et al.  Automated Relational Meta-learning , 2020, ICLR.

[34]  Razvan Pascanu,et al.  Meta-Learning with Warped Gradient Descent , 2020, ICLR.

[35]  Richard E. Turner,et al.  Continual Learning with Adaptive Weights (CLAW) , 2019, ICLR.

[36]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[37]  Razvan Pascanu,et al.  Meta-Learning with Latent Embedding Optimization , 2018, ICLR.

[38]  Philip H. S. Torr,et al.  Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence , 2018, ECCV.

[39]  Thomas L. Griffiths,et al.  Reconciling meta-learning and continual learning with online mixtures of tasks , 2018, NeurIPS.

[40]  Leslie Pack Kaelbling,et al.  Modular meta-learning , 2018, CoRL.

[41]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[42]  Marc'Aurelio Ranzato,et al.  Gradient Episodic Memory for Continual Learning , 2017, NIPS.

[43]  Sergey Levine,et al.  Meta-Learning with Implicit Gradients , 2019, NeurIPS.

[44]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.