mlsanityData to 14 Oct 2026

ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning

arXiv 2109.13305 ↗First posted 27 Sep 2021cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning can model. Handling tasks from multiple different distributions is challenging for meta-learning due to a so-called task ambiguity issue. This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions. ST-MAML encodes tasks using a stochastic neural network module, that summarizes every task with a stochastic representation. The proposed Stochastic Task (ST) strategy allows a meta-model to get tailored for the current task and enables us to learn a distribution of solutions for an ambiguous task. ST-MAML also propagates the task representation to revise the encoding of input variables. Empirically, we demonstrate that ST-MAML matches or outperforms the state-of-the-art on two few-shot image classification tasks, one curve regression benchmark, one image completion problem, and a real-world temperature prediction application. To the best of authors' knowledge, this is the first time optimization-based meta-learning method being applied on a large-scale real-world task.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

27 of 41 references.

References · 27

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017Deep Setscited by 1,421
  5. 2019A Closer Look at Few-shot Classificationcited by 684
  6. 2016Learning to learn by gradient descent by gradient descentcited by 620
  7. 2019Meta-Learning with Implicit Gradientscited by 525
  8. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2018Conditional Neural Processescited by 426
  11. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  12. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
15 more
  1. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  2. 2018Neural Processescited by 311
  3. 2019Attentive Neural Processescited by 283
  4. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  5. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  6. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  7. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  8. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  9. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  10. 2019Hierarchically Structured Meta-learningcited by 68
  11. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  12. 2019The Functional Neural Processcited by 43
  13. 2020Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variablescited by 33
  14. 2020Automated Relational Meta-learningcited by 25
  15. 2020Information Theoretic Meta Learning with Gaussian Processescited by 11

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidancecited by 3
  2. 2025Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspectivecited by 2
  3. 2025A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learningcited by 0
  4. 2025Domain-Generalization to Improve Learning in Meta-Learning Algorithmscited by 0