On Data Efficiency of Meta-learning
원문 초록
Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks. Motivated by use-cases in personalized federated learning, we study the often overlooked aspect of the modern meta-learning algorithms -- their data efficiency. To shed more light on which methods are more efficient, we use techniques from algorithmic stability to derive bounds on the transfer risk that have important practical implications, indicating how much supervision is needed and how it must be allocated for each method to attain the desired level of generalization. Further, we introduce a new simple framework for evaluating meta-learning methods under a limit on the available supervision, conduct an empirical study of MAML, Reptile, and Protonets, and demonstrate the differences in the behavior of these methods on few-shot and federated learning benchmarks. Finally, we propose active meta-learning, which incorporates active data selection into learning-to-learn, leading to better performance of all methods in the limited supervision regime.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion
Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning
Dual‑detector Re‑optimization for Federated Weakly Supervised Video Anomaly Detection Via Adaptive Dynamic Recursive Mapping
Intelligent Travel Activity Monitoring: Generalized Distributed Acoustic Sensing Approaches
토론
이 논문과 연결된 포럼 글이 아직 없습니다.