Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

We propose a meta-learning approach that learns from multiple tasks in a transductive setting, by leveraging the unlabeled query set in addition to the support set to generate a more powerful model for each task. To develop our framework, we revisit the empirical Bayes formulation for multi-task learning. The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task. We derive a novel amortized variational inference that couples all the variational posteriors via a meta-model, which consists of a synthetic gradient network and an initialization network. Each variational posterior is derived from synthetic gradient descent to approximate the true posterior on the query set, although where we do not have access to the true gradient. Our results on the Mini-ImageNet and CIFAR-FS benchmarks for episodic few-shot classification outperform previous state-of-the-art methods. Besides, we conduct two zero-shot learning experiments to further explore the potential of the synthetic gradient.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) SIB Accuracy 80.0 # 11
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) SIB Accuracy 85.3 # 27
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) SIB Accuracy 70.0 # 28
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) SIB Accuracy 79.2 # 45

Methods


No methods listed for this paper. Add relevant methods here