# Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation Source: [Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:54:21.040Z Authors: Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim Published: 2019-10-30T01:35:19.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Few-shot classification on miniImageNet standard (test)](): Few-shot classification; miniImageNet standard (test); 5-way 1-shot Acc: not recorded. ## Original sources and implementation [Original paper]() [PDF]()