Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such restriction, they learn to equally utilize the meta-knowledge across all the tasks, even when the number of instances per task and class largely varies. Moreover, they do not consider distributional difference in unseen tasks, on which the meta-knowledge may have less usefulness depending on the task relatedness. To overcome these limitations, we propose a novel meta-learning model that adaptively balances the effect of the meta-learning and task-specific learning within each task. Through the learning of the balancing variables, we can decide whether to obtain a solution by relying on the meta-knowledge or task-specific learning. We formulate this objective into a Bayesian inference framework and tackle it using variational inference. We validate our Bayesian Task-Adaptive Meta-Learning (Bayesian TAML) on multiple realistic task- and class-imbalanced datasets, on which it significantly outperforms existing meta-learning approaches. Further ablation study confirms the effectiveness of each balancing component and the Bayesian learning framework.

[1]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[2]  Iasonas Kokkinos,et al.  Describing Textures in the Wild , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Alex Beatson,et al.  Amortized Bayesian Meta-Learning , 2018, ICLR.

[4]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[5]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[6]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[7]  Yoshua Bengio,et al.  Bayesian Model-Agnostic Meta-Learning , 2018, NeurIPS.

[8]  Amos J. Storkey,et al.  Towards a Neural Statistician , 2016, ICLR.

[9]  Daan Wierstra,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016, ICML.

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

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

[12]  Joshua Achiam,et al.  On First-Order Meta-Learning Algorithms , 2018, ArXiv.

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

[14]  Sebastian Nowozin,et al.  Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes , 2019, NeurIPS.

[15]  Johannes Stallkamp,et al.  Detection of traffic signs in real-world images: The German traffic sign detection benchmark , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[16]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

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

[18]  Subhransu Maji,et al.  Fine-Grained Visual Classification of Aircraft , 2013, ArXiv.

[19]  Wei Shen,et al.  Few-Shot Image Recognition by Predicting Parameters from Activations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

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

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

[23]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[24]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

[25]  Sebastian Nowozin,et al.  Meta-Learning Probabilistic Inference for Prediction , 2018, ICLR.

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

[27]  C A Nelson,et al.  Learning to Learn , 2017, Encyclopedia of Machine Learning and Data Mining.

[28]  Luca Bertinetto,et al.  Meta-learning with differentiable closed-form solvers , 2018, ICLR.

[29]  Joshua B. Tenenbaum,et al.  Meta-Learning for Semi-Supervised Few-Shot Classification , 2018, ICLR.

[30]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

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

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