Fast Context Adaptation via Meta-Learning

2018-10-08 · Luisa M. Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson

We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, only the context parameters are updated, leading to a low-dimensional task representation. We show empirically that CAVIA outperforms MAML for regression, classification, and reinforcement learning. Our experiments also highlight weaknesses in current benchmarks, in that the amount of adaptation needed in some cases is small.

📄 PDF Abstract BibTeX arXiv:1810.03642

Code (1)

lmzintgraf/cavia 공식 구현 pytorch

Tasks

General Classification Meta-Learning regression reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

MAML 설명 없음

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

2025-10-27 · Han Wu, Jie Yin arxiv

Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast…

Meta-Gradients in Non-Stationary Environments

2022-09-13 · Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel 외

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties…

Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing

2019-06-17 · ACL 2019 7 · Daya Guo, Duyu Tang, Nan Duan, Ming Zhou 외

In this paper, we present an approach to incorporate retrieved datapoints as supporting evidence for context-dependent semantic parsing, such as generating source code conditioned on the class environment. Our approach n…

Decoder Meta-Learning Retrieval Semantic Parsing

Offline Meta Reinforcement Learning with In-Distribution Online Adaptation

2023-05-31 · Jianhao Wang, Jin Zhang, Haozhe Jiang, Junyu Zhang 외

Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a multi-task dataset. However, these methods a…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Uncertainty Quantification

CAML: Fast Context Adaptation via Meta-Learning

2018-09-27 · Luisa M Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann 외

We propose CAML, a meta-learning method for fast adaptation that partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and sha…

Meta-Learning