paper-with-me

Papers

On Modulating the Gradient for Meta-Learning

2020-08-01 · ECCV 2020 8 · Christian Simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi

Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data. Our method, termed ModGrad, is designed to circumvent the noisy nature of the gradients which is prevalent in low-data regimes. Furthermore and having the scalability concern in mind, we formulate ModGrad via low-rank approximations, which in turn enables us to employ ModGrad to adapt hefty neural networks. We thoroughly assess and contrast ModGrad against a large family of meta-learning techniques and observe that the proposed algorithm outperforms baselines comfortably while enjoying faster convergence.

📄 PDF Abstract BibTeX

Code (1)

chrysts/generative_preconditioner 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Meta Gradient Boosting Neural Networks

2021-01-01 · Manqing Dong, Lina Yao, Xianzhi Wang, Xiwei Xu 외

Meta-optimization is an effective approach that learns a shared set of parameters across tasks for parameter initialization in meta-learning. A key challenge for meta-optimization based approaches is to determine whether…

Meta-Learningregression

Toward Multimodal Model-Agnostic Meta-Learning

2018-12-18 · Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is tha…

DiversityFew-Shot Image Classificationimage-classificationImage Classification+3

Model-Agnostic Meta-Learning for Multimodal Task Distributions

2018-09-27 · Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim

Gradient-based meta-learners such as MAML (Finn et al., 2017) are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of su…

DiversityFew-Shot Image Classificationimage-classificationImage Classification+2

Modulating transfer between tasks in gradient-based meta-learning

2019-05-01 · ICLR 2019 5 · Erin Grant, Ghassen Jerfel, Katherine Heller, Thomas L. Griffiths

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not mutually beneficial, for instance, …

DiversityInductive BiasMeta-Learning

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

2019-10-30 · NeurIPS 2019 12 · Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those fra…

Few-Shot Image ClassificationFew-Shot LearningGeneral Classificationimage-classification+5