Papers › Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

31 Jul 2017arXiv:1707.09835archive 2025-07-28

Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li

Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial. In this paper, we develop Meta-SGD, an SGD-like, easily trainable meta-learner that can initialize and adapt any differentiable learner in just one step, on both supervised learning and reinforcement learning. Compared to the popular meta-learner LSTM, Meta-SGD is conceptually simpler, easier to implement, and can be learned more efficiently. Compared to the latest meta-learner MAML, Meta-SGD has a much higher capacity by learning to learn not just the learner initialization, but also the learner update direction and learning rate, all in a single meta-learning process. Meta-SGD shows highly competitive performance for few-shot learning on regression, classification, and reinforcement learning.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

BBDrive/Meta-SGD-RL mentioned on GitHubpytorch report
ash3n/Meta-Gradients mentioned on GitHubtf report
ash3n/Meta-SGD mentioned on GitHubtf report
ash3n/Meta-SGD-TF mentioned on GitHubtf report
foolyc/Meta-SGD mentioned on GitHubtf report
llan-ml/tesp mentioned on GitHubtfNOASSERTION report
myungsub/meta-interpolation mentioned on GitHubpytorch report
tobiasvanderwerff/MetaHTR mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot LearningMeta-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Meta SGD Accuracy 17.56 #3 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Matching Nets, (from ) Accuracy 17.31 #4 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Meta LSTM, (from ) Accuracy 16.70 #5 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) MAML, (from ) Accuracy 16.49 #6 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Meta SGD Accuracy 28.92 #3 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Meta LSTM, (from ) Accuracy 26.06 #4 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Matching Nets, (from ) Accuracy 22.69 #5 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) MAML, (from ) Accuracy 19.29 #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMMAMLSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections