paper-with-me

Papers

Accelerating Meta-Learning by Sharing Gradients

2023-12-13 · Oscar Chang, Hod Lipson

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%.

📄 PDF Abstract BibTeX arXiv:2312.08398

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningMulti-Task Learning

Similar Papers 제목 키워드 기반

Model agnostic meta-learning on trees

2021-01-01 · Jezabel Garcia, Federica Freddi, Jamie McGowan, Tim Nieradzik 외

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-Learningmodel

Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning

2024-06-01 · Mina Rafiei, Mohammadmahdi Maheri, Hamid R. Rabiee

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-Learning

Directed-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation

2025-09-30 · Yang Zhang, Huiwen Yan, Mushuang Liu arxiv

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 Learning

A Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization

2024-10-18 · Min Wen, Chengchang Liu, Ahmed Abdelmoniem, Yipeng Zhou 외

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-Learning

Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradients

2024-03-25 · Ping Luo, Xiaoge Deng, Ziqing Wen, Tao Sun 외

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