Papers › Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

17 Jan 2018ICML 2018 7arXiv:1801.05558archive 2025-07-28

Yoonho Lee, Seungjin Choi

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an {\em MT-net} performs gradient descent with respect to a meta-learned distance metric, which warps the activation space to be more sensitive to task identity. We demonstrate that the dimension of this learned subspace reflects the complexity of the task-specific learner's adaptation task, and also that our model is less sensitive to the choice of initial learning rates than previous gradient-based meta-learning methods. Our method achieves state-of-the-art or comparable performance on few-shot classification and regression tasks.

PaperPDFConference PDFCode

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

Code

yoonholee/MT-net officialmentioned in papermentioned on GitHubtf 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 Image ClassificationMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MT-Net Accuracy 51.7 #93 of 105 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way MT-net Accuracy 96.2% #9 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way MT-net Accuracy 99.5 #5 of 17 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.

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