Accelerating Meta-Learning by Sharing Gradients
The success of gradient-based meta-learning is primarily attributed to its ability to leverage related tasks to learn task-invariant information. However, the absence of interactions between different tasks in the inner loop leads to task-specific over-fitting in the initial phase of meta-training. While this is eventually corrected by the presence of these interactions in the outer loop, it comes at a significant cost of slower meta-learning. To address this limitation, we explicitly encode task relatedness via an inner loop regularization mechanism inspired by multi-task learning. Our algorithm shares gradient information from previously encountered tasks as well as concurrent tasks in the same task batch, and scales their contribution with meta-learned parameters. We show using two popular few-shot classification datasets that gradient sharing enables meta-learning under bigger inner loop learning rates and can accelerate the meta-training process by up to 134%.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningMulti-Task LearningSimilar Papers 제목 키워드 기반
Model agnostic meta-learning on trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related, and sharing information between unrelated tasks might hurt performance. A fruitfu…
Meta-LearningmodelPrivacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning
Meta-learning involves multiple learners, each dedicated to specific tasks, collaborating in a data-constrained setting. In current meta-learning methods, task learners locally learn models from sensitive data, termed su…
Meta-LearningDirected-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation
Model-Agnostic Meta-Learning (MAML) is a versatile meta-learning framework applicable to both supervised learning and reinforcement learning (RL). However, applying MAML to meta-reinforcement learning (meta-RL) presents …
Computational EfficiencyReinforcement LearningA Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization
Bilevel optimization, crucial for hyperparameter tuning, meta-learning and reinforcement learning, remains less explored in the decentralized learning paradigm, such as decentralized federated learning (DFL). Typically, …
Bilevel OptimizationFederated LearningMeta-LearningAccelerating Federated Learning by Selecting Beneficial Herd of Local Gradients
Federated Learning (FL) is a distributed machine learning framework in communication network systems. However, the systems' Non-Independent and Identically Distributed (Non-IID) data negatively affect the convergence eff…
Federated Learning