mlsanityData to 14 Oct 2026

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification

arXiv 2410.02267 ↗First posted 3 Oct 2024cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Meta-learning has been widely used in recent years in areas such as few-shot learning and reinforcement learning. However, the questions of why and when it is better than other algorithms in few-shot classification remain to be explored. In this paper, we perform pre-experiments by adjusting the proportion of label noise and the degree of task heterogeneity in the dataset. We use the metric of Singular Vector Canonical Correlation Analysis to quantify the representation stability of the neural network and thus to compare the behavior of meta-learning and classical learning algorithms. We find that benefiting from the bi-level optimization strategy, the meta-learning algorithm has better robustness to label noise and heterogeneous tasks. Based on the above conclusion, we argue a promising future for meta-learning in the unsupervised area, and thus propose DHM-UHT, a dynamic head meta-learning algorithm with unsupervised heterogeneous task construction. The core idea of DHM-UHT is to use DBSCAN and dynamic head to achieve heterogeneous task construction and meta-learn the whole process of unsupervised heterogeneous task construction. On several unsupervised zero-shot and few-shot datasets, DHM-UHT obtains state-of-the-art performance. The code is released at https://github.com/tuantuange/DHM-UHT.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 34 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

25 of 34 references.

References · 25

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  6. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  7. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  8. 2019A Closer Look at Few-shot Classificationcited by 684
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  10. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  12. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
13 more
  1. 2016Adversarial Feature Learningcited by 350
  2. 2018Meta-Learning: A Surveycited by 256
  3. 2019Meta-Learning without Memorizationcited by 92
  4. 2018Unsupervised Learning via Meta-Learningcited by 82
  5. 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 75
  6. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  7. 2023A Closer Look at Few-shot Classification Againcited by 46
  8. 2020Information-Theoretic Generalization Bounds for Meta-Learning and Applicationscited by 32
  9. 2020Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Modelscited by 26
  10. 2023Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learningcited by 15
  11. 2020Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Taskscited by 12
  12. 2021An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-Learningcited by 10
  13. 2022Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
  2. 2024Learn To Learn More Precisely
  3. 2024Dynamics of Meta-learning Representation in the Teacher-student Scenario
  4. 2025Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning
  5. 2025TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments
  6. 2023MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning
  7. 2023Understanding the Overfitting of the Episodic Meta-training
  8. 2025Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning