LGMLMay 24, 2019

Learning to learn via Self-Critique

arXiv:1905.10295v626 citations
Originality Highly original
AI Analysis

This addresses the challenge of limited labeled data in few-shot learning for machine learning practitioners, offering a novel transductive approach to improve generalization.

The paper tackles the problem of few-shot learning by proposing a framework called Self-Critique and Adapt (SCA) that learns a label-free loss function to utilize unlabeled target-set data, resulting in substantially reduced error rates and state-of-the-art performance on benchmarks like Mini-ImageNet and Caltech-UCSD Birds 200.

In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in such tasks, we wish to make use of all the information we can. Usually a model learns task-specific information from a small training-set (support-set) to predict on an unlabelled validation set (target-set). The target-set contains additional task-specific information which is not utilized by existing few-shot learning methods. Making use of the target-set examples via transductive learning requires approaches beyond the current methods; at inference time, the target-set contains only unlabelled input data-points, and so discriminative learning cannot be used. In this paper, we propose a framework called Self-Critique and Adapt or SCA, which learns to learn a label-free loss function, parameterized as a neural network. A base-model learns on a support-set using existing methods (e.g. stochastic gradient descent combined with the cross-entropy loss), and then is updated for the incoming target-task using the learnt loss function. This label-free loss function is itself optimized such that the learnt model achieves higher generalization performance. Experiments demonstrate that SCA offers substantially reduced error-rates compared to baselines which only adapt on the support-set, and results in state of the art benchmark performance on Mini-ImageNet and Caltech-UCSD Birds 200.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes