# Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks

arXiv: https://arxiv.org/abs/2011.14663 · HTML: https://mlsanity.com/paper/2011.14663/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion](https://mlsanity.com/paper/2404.14197/) (2024)
- [STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables](https://mlsanity.com/paper/2303.00918/) (2023)
- [Representation Learning for Tabular Data: A Comprehensive Survey](https://mlsanity.com/paper/2504.16109/) (2025)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels](https://mlsanity.com/paper/2311.11019/) (2023)
- [BECLR: Batch Enhanced Contrastive Few-Shot Learning](https://mlsanity.com/paper/2402.02444/) (2024)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Manipulating the Label Space for In-Context Classification](https://mlsanity.com/paper/2312.00351/) (2023)
- [Self-Attention Message Passing for Contrastive Few-Shot Learning](https://mlsanity.com/paper/2210.06339/) (2022)
- [Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy](https://mlsanity.com/paper/2509.13185/) (2025)
- [MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning](https://mlsanity.com/paper/2408.13385/) (2024)
- [Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification](https://mlsanity.com/paper/2410.02267/) (2024)

## Abstract (arXiv)

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement of base class labels and learn generalizable embeddings via Unsupervised Meta-Learning (UML). Specifically, episodes of tasks are constructed with data augmentations from unlabeled base classes during meta-training, and we apply embedding-based classifiers to novel tasks with labeled few-shot examples during meta-test. We observe two elements play important roles in UML, i.e., the way to sample tasks and measure similarities between instances. Thus we obtain a strong baseline with two simple modifications -- a sufficient sampling strategy constructing multiple tasks per episode efficiently together with a semi-normalized similarity. We then take advantage of the characteristics of tasks from two directions to get further improvements. First, synthesized confusing instances are incorporated to help extract more discriminative embeddings. Second, we utilize an additional task-specific embedding transformation as an auxiliary component during meta-training to promote the generalization ability of the pre-adapted embeddings. Experiments on few-shot learning benchmarks verify that our approaches outperform previous UML methods and achieve comparable or even better performance than its supervised variants.