Timezone: »

Structured Prediction for Conditional Meta-Learning
Ruohan Wang · Yiannis Demiris · Carlo Ciliberto

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1202

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.

Author Information

Ruohan Wang (Imperial College London)
Yiannis Demiris (Imperial College London)
Carlo Ciliberto (Imperial College London)

More from the Same Authors