Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
arXiv:2110.02399
Abstract
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartite matching algorithm and utilizes the Fisher Information matrix. We provide theoretical analyses demonstrating that the proposed score is mathematically well-defined, and subsequently use the affinity score to propose a novel algorithm for the few-shot learning problem. In particular, using this score, we find relevant training data labels to the test data and leverage the discovered relevant data for episodically fine-tuning a few-shot model. Results on various few-shot benchmark datasets demonstrate the efficacy of the proposed approach by improving the classification accuracy over the state-of-the-art methods even when using smaller models.
arXiv commentAccepted as a conference paper at ICLR 2022
References in corpus (15)
- Overcoming catastrophic forgetting in neural networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- A Simple Neural Attentive Meta-Learner
- Meta-Learning for Semi-Supervised Few-Shot Classification
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- On First-Order Meta-Learning Algorithms
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Which Tasks Should Be Learned Together in Multi-task Learning?
- Meta-Learning with Latent Embedding Optimization
- TADAM: Task dependent adaptive metric for improved few-shot learning
- A Closer Look at Few-shot Classification
- Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
- Self-supervised Label Augmentation via Input Transformations
- Optimal non-asymptotic bound of the Ruppert-Polyak averaging without strong convexity