# Adaptive Task Sampling for Meta-Learning

arXiv: https://arxiv.org/abs/2007.08735 · HTML: https://mlsanity.com/paper/2007.08735/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 29 of 29)

- [Auto-Lambda: Disentangling Dynamic Task Relationships](https://mlsanity.com/paper/2202.03091/) (2022)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [Meta-learning with an Adaptive Task Scheduler](https://mlsanity.com/paper/2110.14057/) (2021)
- [Model Predictive Task Sampling for Efficient and Robust Adaptation](https://mlsanity.com/paper/2501.11039/) (2025)
- [Learning to Learn from APIs: Black-Box Data-Free Meta-Learning](https://mlsanity.com/paper/2305.18413/) (2023)
- [The Effect of Diversity in Meta-Learning](https://mlsanity.com/paper/2201.11775/) (2022)
- [Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation](https://mlsanity.com/paper/2407.19523/) (2024)
- [Towards Task Sampler Learning for Meta-Learning](https://mlsanity.com/paper/2307.08924/) (2023)
- [On the Statistical Benefits of Curriculum Learning](https://mlsanity.com/paper/2111.07126/) (2021)
- [Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning](https://mlsanity.com/paper/2303.11183/) (2023)
- [Graph Sampling-based Meta-Learning for Molecular Property Prediction](https://mlsanity.com/paper/2306.16780/) (2023)
- [Multidimensional Belief Quantification for Label-Efficient Meta-Learning](https://mlsanity.com/paper/2203.12768/) (2022)
- [Uniform Sampling over Episode Difficulty](https://mlsanity.com/paper/2108.01662/) (2021)
- [Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios](https://mlsanity.com/paper/2211.05980/) (2022)
- [Learning to Learn with Contrastive Meta-Objective](https://mlsanity.com/paper/2410.05975/) (2024)
- [L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning](https://mlsanity.com/paper/2305.13741/) (2023)
- [Data-Efficient and Robust Task Selection for Meta-Learning](https://mlsanity.com/paper/2405.07083/) (2024)
- [Meta-Learning with Heterogeneous Tasks](https://mlsanity.com/paper/2410.18894/) (2024)
- [Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective](https://mlsanity.com/paper/2505.19815/) (2025)
- [Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling](https://mlsanity.com/paper/2205.05155/) (2022)
- [Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications](https://mlsanity.com/paper/2403.03535/) (2024)
- [Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework](https://mlsanity.com/paper/2601.10779/) (2026)
- [Concept Discovery for Fast Adapatation](https://mlsanity.com/paper/2301.07850/) (2023)
- [AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design Anywhere](https://mlsanity.com/paper/2304.12921/) (2023)
- [CPT: Competence-progressive Training Strategy for Few-shot Node Classification](https://mlsanity.com/paper/2402.00450/) (2024)
- [Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning](https://mlsanity.com/paper/2409.02850/) (2024)
- [AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery](https://mlsanity.com/paper/2505.11878/) (2025)
- [Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios](https://mlsanity.com/paper/2606.23758/) (2026)

## Abstract (arXiv)

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time by randomly sampling classes in meta-training data to construct few-shot tasks for episodic training. While a rich line of work focuses solely on how to extract meta-knowledge across tasks, we exploit the complementary problem on how to generate informative tasks. We argue that the randomly sampled tasks could be sub-optimal and uninformative (e.g., the task of classifying "dog" from "laptop" is often trivial) to the meta-learner. In this paper, we propose an adaptive task sampling method to improve the generalization performance. Unlike instance based sampling, task based sampling is much more challenging due to the implicit definition of the task in each episode. Therefore, we accordingly propose a greedy class-pair based sampling method, which selects difficult tasks according to class-pair potentials. We evaluate our adaptive task sampling method on two few-shot classification benchmarks, and it achieves consistent improvements across different feature backbones, meta-learning algorithms and datasets.