# MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

arXiv: https://arxiv.org/abs/2305.10309 · HTML: https://mlsanity.com/paper/2305.10309/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 17 May 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [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)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [Task-Agnostic Meta-Learning for Few-shot Learning](https://mlsanity.com/paper/1805.07722/) (2018)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Cross-Domain Few-Shot Classification via Adversarial Task Augmentation](https://mlsanity.com/paper/2104.14385/) (2021)
- [Improving Generalization in Meta-learning via Task Augmentation](https://mlsanity.com/paper/2007.13040/) (2020)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [Data Augmentation for Meta-Learning](https://mlsanity.com/paper/2010.07092/) (2020)
- [STraTA: Self-Training with Task Augmentation for Better Few-shot Learning](https://mlsanity.com/paper/2109.06270/) (2021)
- [FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning](https://mlsanity.com/paper/2108.06332/) (2021)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification](https://mlsanity.com/paper/2106.05517/) (2021)
- [Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge](https://mlsanity.com/paper/1901.10802/) (2019)
- [Set-based Meta-Interpolation for Few-Task Meta-Learning](https://mlsanity.com/paper/2205.09990/) (2022)

## Built on by (most cited first, 4 of 4)

- [ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion](https://mlsanity.com/paper/2306.14770/) (2023)
- [VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2511.22664/) (2025)
- [Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes](https://mlsanity.com/paper/2607.01297/) (2026)
- [Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis](https://mlsanity.com/paper/2608.03225/) (2026)

## Abstract (arXiv)

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learning with fewer tasks, which we call MetaModulation. The key idea is to use a neural network to increase the density of the meta-training tasks by modulating batch normalization parameters during meta-training. Additionally, we modify parameters at various network levels, rather than just a single layer, to increase task diversity. To account for the uncertainty caused by the limited training tasks, we propose a variational MetaModulation where the modulation parameters are treated as latent variables. We also introduce learning variational feature hierarchies by the variational MetaModulation, which modulates features at all layers and can consider task uncertainty and generate more diverse tasks. The ablation studies illustrate the advantages of utilizing a learnable task modulation at different levels and demonstrate the benefit of incorporating probabilistic variants in few-task meta-learning. Our MetaModulation and its variational variants consistently outperform state-of-the-art alternatives on four few-task meta-learning benchmarks.