Auto-Meta: Automated Gradient Based Meta Learner Search
원문 초록
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that automated architecture search synergizes with the effect of gradient-based meta learning. We adopt the progressive neural architecture search \cite{liu:pnas_google:DBLP:journals/corr/abs-1712-00559} to find optimal architectures for meta-learners. The gradient based meta-learner whose architecture was automatically found achieved state-of-the-art results on the 5-shot 5-way Mini-ImageNet classification problem with $74.65\%$ accuracy, which is $11.54\%$ improvement over the result obtained by the first gradient-based meta-learner called MAML \cite{finn:maml:DBLP:conf/icml/FinnAL17}. To our best knowledge, this work is the first successful neural architecture search implementation in the context of meta learning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Meta knowledge assisted Evolutionary Neural Architecture Search
Federated Neural Architecture Search with Model-Agnostic Meta Learning
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing
From Tiny Machine Learning to Tiny Deep Learning: A Survey
토론
이 논문과 연결된 포럼 글이 아직 없습니다.