Back to Search
Start Over
Structured prediction for conditional meta-learning
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing conditional methods are difficult to generalize and lack theoretical guarantees. In this work, we propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions by weighing meta-training data on target tasks. Our non-parametric approach is model-agnostic and can be combined with existing meta-learning methods to achieve conditioning. Empirically, we show that TASML improves the performance of existing meta-learning models, and outperforms the state-of-the-art on benchmark datasets.
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.od......1032..411262b03b1340e32e072e84a289c59c