Papers › Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

19 Sep 2019ICLR 2020 1arXiv:1909.09157archive 2025-07-28

Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals

An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-Learning (MAML), a method that consists of two optimization loops, with the outer loop finding a meta-initialization, from which the inner loop can efficiently learn new tasks. Despite MAML's popularity, a fundamental open question remains -- is the effectiveness of MAML due to the meta-initialization being primed for rapid learning (large, efficient changes in the representations) or due to feature reuse, with the meta initialization already containing high quality features? We investigate this question, via ablation studies and analysis of the latent representations, finding that feature reuse is the dominant factor. This leads to the ANIL (Almost No Inner Loop) algorithm, a simplification of MAML where we remove the inner loop for all but the (task-specific) head of a MAML-trained network. ANIL matches MAML's performance on benchmark few-shot image classification and RL and offers computational improvements over MAML. We further study the precise contributions of the head and body of the network, showing that performance on the test tasks is entirely determined by the quality of the learned features, and we can remove even the head of the network (the NIL algorithm). We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

fmu2/PyTorch-MAML mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
learnables/learn2learn pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified), Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified), On First-Order Meta-Learning Algorithms (arXiv:1803.02999; that paper's own run record: 27 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 18 where Syntology's instrument failed) · 15 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Few-Shot Image ClassificationFew-Shot LearningImage ClassificationMeta-LearningOpen-Ended Question Answeringimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MAML

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