# Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

arXiv: https://arxiv.org/abs/1910.13616 · HTML: https://mlsanity.com/paper/1910.13616/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2019.

## Built on by (most cited first, 30 of 103)

- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder](https://mlsanity.com/paper/2108.05028/) (2021)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Hypernetworks in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.11348/) (2022)
- [Skill-based Meta-Reinforcement Learning](https://mlsanity.com/paper/2204.11828/) (2022)
- [Leveraging Language for Accelerated Learning of Tool Manipulation](https://mlsanity.com/paper/2206.13074/) (2022)
- [Gradient-based Bi-level Optimization for Deep Learning: A Survey](https://mlsanity.com/paper/2207.11719/) (2022)
- [FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation](https://mlsanity.com/paper/2206.00050/) (2022)
- [Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization](https://mlsanity.com/paper/2106.04335/) (2021)
- [Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches](https://mlsanity.com/paper/2203.14843/) (2022)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning](https://mlsanity.com/paper/2110.14202/) (2021)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset](https://mlsanity.com/paper/2110.00715/) (2021)
- [What Matters For Meta-Learning Vision Regression Tasks?](https://mlsanity.com/paper/2203.04905/) (2022)
- [Recurrent Hypernetworks are Surprisingly Strong in Meta-RL](https://mlsanity.com/paper/2309.14970/) (2023)
- [Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design](https://mlsanity.com/paper/2310.02782/) (2023)
- [Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology](https://mlsanity.com/paper/2109.06429/) (2021)
- [Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions](https://mlsanity.com/paper/2209.01501/) (2022)
- [A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness](https://mlsanity.com/paper/2312.01082/) (2023)
- [Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?](https://mlsanity.com/paper/2203.03059/) (2022)
- [Conditional Meta-Learning of Linear Representations](https://mlsanity.com/paper/2103.16277/) (2021)
- [Few-Shot Action Recognition with Compromised Metric via Optimal Transport](https://mlsanity.com/paper/2104.03737/) (2021)
- [Federated Learning and Meta Learning: Approaches, Applications, and Directions](https://mlsanity.com/paper/2210.13111/) (2022)
- [Multimodality in Meta-Learning: A Comprehensive Survey](https://mlsanity.com/paper/2109.13576/) (2021)
- [A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm](https://mlsanity.com/paper/2310.00708/) (2023)
- [Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks](https://mlsanity.com/paper/2107.02378/) (2021)
- [Multidimensional Belief Quantification for Label-Efficient Meta-Learning](https://mlsanity.com/paper/2203.12768/) (2022)

## Abstract (arXiv)

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate appealing performance on a variety of domains such as few-shot image classification and reinforcement learning. However, one important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify the mode of tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior parameters according to the identified mode, allowing more efficient fast adaptation. We evaluate the proposed model on a diverse set of few-shot learning tasks, including regression, image classification, and reinforcement learning. The results not only demonstrate the effectiveness of our model in modulating the meta-learned prior in response to the characteristics of tasks but also show that training on a multimodal distribution can produce an improvement over unimodal training.