# Meta-learning with an Adaptive Task Scheduler

arXiv: https://arxiv.org/abs/2110.14057 · HTML: https://mlsanity.com/paper/2110.14057/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples](https://mlsanity.com/paper/1704.07433/) (2017)
- [Learning with Symmetric Label Noise: The Importance of Being Unhinged](https://mlsanity.com/paper/1505.07634/) (2015)
- [Meta-Learning without Memorization](https://mlsanity.com/paper/1912.03820/) (2019)
- [Stochastic Optimization with Importance Sampling](https://mlsanity.com/paper/1401.2753/) (2014)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)
- [Unsupervised Curricula for Visual Meta-Reinforcement Learning](https://mlsanity.com/paper/1912.04226/) (2019)
- [Adaptive Task Sampling for Meta-Learning](https://mlsanity.com/paper/2007.08735/) (2020)
- [Difficulty-aware Meta-learning for Rare Disease Diagnosis](https://mlsanity.com/paper/1907.00354/) (2019)
- [Probabilistic Active Meta-Learning](https://mlsanity.com/paper/2007.08949/) (2020)
- [Information-theoretic Task Selection for Meta-Reinforcement Learning](https://mlsanity.com/paper/2011.01054/) (2020)

## Built on by (most cited first, 27 of 27)

- [PaCo: Parameter-Compositional Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2210.11653/) (2022)
- [MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild](https://mlsanity.com/paper/2603.17187/) (2026)
- [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)
- [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)
- [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)
- [MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation](https://mlsanity.com/paper/2202.03851/) (2022)
- [FREE: Faster and Better Data-Free Meta-Learning](https://mlsanity.com/paper/2405.00984/) (2024)
- [Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios](https://mlsanity.com/paper/2211.05980/) (2022)
- [Task-Distributionally Robust Data-Free Meta-Learning](https://mlsanity.com/paper/2311.14756/) (2023)
- [Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation](https://mlsanity.com/paper/2302.14640/) (2023)
- [Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts](https://mlsanity.com/paper/2403.08477/) (2024)
- [Continual Optimization with Symmetry Teleportation for Multi-Task Learning](https://mlsanity.com/paper/2503.04046/) (2025)
- [Knowledge-Driven New Drug Recommendation](https://mlsanity.com/paper/2210.05572/) (2022)
- [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)
- [Learning to generate imaginary tasks for improving generalization in meta-learning](https://mlsanity.com/paper/2206.04335/) (2022)
- [Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning](https://mlsanity.com/paper/2303.10966/) (2023)
- [Label Denoising through Cross-Model Agreement](https://mlsanity.com/paper/2308.13976/) (2023)
- [BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise](https://mlsanity.com/paper/2309.06046/) (2023)
- [Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosis](https://mlsanity.com/paper/2311.02300/) (2023)
- [Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning](https://mlsanity.com/paper/2409.19075/) (2024)
- [AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery](https://mlsanity.com/paper/2505.11878/) (2025)

## Abstract (arXiv)

To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability, under the assumption that tasks are of equal importance. However, it is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks. To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS) for the meta-training process. In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks. We identify two meta-model-related factors as the input of the neural scheduler, which characterize the difficulty of a candidate task to the meta-model. Theoretically, we show that a scheduler taking the two factors into account improves the meta-training loss and also the optimization landscape. Under the setting of meta-learning with noise and limited budgets, ATS improves the performance on both miniImageNet and a real-world drug discovery benchmark by up to 13% and 18%, respectively, compared to state-of-the-art task schedulers.