Meta-Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 1,408 papers with code (3,569 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
  9 Mar 2017 85 repositories listed Syntology ran 86 of 154 samples · 68 unverified · 57 pointer-only (licence)
  We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including…
• Prototypical Networks for Few-shot Learning
  15 Mar 2017 43 repositories listed Syntology ran 49 of 64 samples · 15 unverified · 18 pointer-only (licence)
  We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
  7 Mar 2019 15 repositories listed Syntology ran 4 of 11 samples · 7 unverified
  Few-shot classification refers to learning a classifier for new classes given only a few examples.
• On First-Order Meta-Learning Algorithms
  8 Mar 2018 13 repositories listed Syntology ran 24 of 42 samples · 18 unverified · 13 pointer-only (licence)
  This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.
• Learning to Compare: Relation Network for Few-Shot Learning
  16 Nov 2017 13 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.
• Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
  9 Mar 2020 10 repositories listed Syntology ran 8 of 12 samples · 4 unverified · 1 pointer-only (licence)
  The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear.
• How to train your MAML
  22 Oct 2018 10 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The field of few-shot learning has recently seen substantial advancements.
• Meta-Learning for Semi-Supervised Few-Shot Classification
  2 Mar 2018 10 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes.
• Meta Pseudo Labels
  23 Mar 2020 9 repositories listed Syntology ran 5 of 14 samples · 9 unverified
  We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
  24 Oct 2019 9 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors.
• Learning to Reweight Examples for Robust Deep Learning
  24 Mar 2018 9 repositories listed
  Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns.
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
  31 Jul 2017 9 repositories listed
  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.
• Learning to reinforcement learn
  17 Nov 2016 9 repositories listed Syntology ran 3 of 15 samples · 12 unverified · 12 pointer-only (licence)
  We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
• Learning Meta Face Recognition in Unseen Domains
  17 Mar 2020 8 repositories listed
  Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization.
• Learning to learn by gradient descent by gradient descent
  14 Jun 2016 8 repositories listed Syntology ran 4 of 13 samples · 9 unverified
  The move from hand-designed features to learned features in machine learning has been wildly successful.
• TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
  5 Jul 2022 7 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 1 pointer-only (licence)
  We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification…
• Meta-Learning with Differentiable Convex Optimization
  7 Apr 2019 7 repositories listed
  We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition…
• LEAF: A Benchmark for Federated Settings
  3 Dec 2018 7 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day.
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
  12 Nov 2019 6 repositories listed Syntology ran 3 of 9 samples · 6 unverified
  Few-shot learners aim to recognize new object classes based on a small number of labeled training examples.
• Meta-Learning with Implicit Gradients
  10 Sep 2019 6 repositories listed Syntology ran 27 of 36 samples · 9 unverified · 10 pointer-only (licence)
  By drawing upon implicit differentiation, we develop the implicit MAML algorithm, which depends only on the solution to the inner level optimization and not the path taken by the inner loop optimizer.
• Meta-Learning Representations for Continual Learning
  29 May 2019 6 repositories listed
  We show that it is possible to learn naturally sparse representations that are more effective for online updating.
• Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
  20 May 2019 6 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.
• ProMP: Proximal Meta-Policy Search
  16 Oct 2018 6 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood.
• DevFormer: A Symmetric Transformer for Context-Aware Device Placement
  26 May 2022 5 repositories listed Syntology ran 13 of 23 samples · 10 unverified
  In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization.
• Towards mental time travel: a hierarchical memory for reinforcement learning agents
  28 May 2021 5 repositories listed Syntology ran 3 of 6 samples · 3 unverified
  Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to recall the details of a single timestep that is followed by distractor tasks.
• Evolving Reinforcement Learning Algorithms
  8 Jan 2021 5 repositories listed
  Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm.
• Transfer Graph Neural Networks for Pandemic Forecasting
  10 Sep 2020 5 repositories listed
  Furthermore, to account for the limited amount of training data, we capitalize on the pandemic's asynchronous outbreaks across countries and use a model-agnostic meta-learning based method to transfer knowledge from one…
• Learning with AMIGo: Adversarially Motivated Intrinsic Goals
  22 Jun 2020 5 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  A key challenge for reinforcement learning (RL) consists of learning in environments with sparse extrinsic rewards.
• Frustratingly Simple Few-Shot Object Detection
  16 Mar 2020 5 repositories listed Syntology ran 3 of 11 samples · 8 unverified · 11 pointer-only (licence)
  Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.
• Learning to Continually Learn
  21 Feb 2020 5 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it.

Syntology lines on 23 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.