# MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

arXiv: https://arxiv.org/abs/2307.16424 · HTML: https://mlsanity.com/paper/2307.16424/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 39 of its 44 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [Low Data Drug Discovery with One-shot Learning](https://mlsanity.com/paper/1611.03199/) (2016)
- [Meta-Learning with Adaptive Hyperparameters](https://mlsanity.com/paper/2011.00209/) (2020)
- [Meta-Curvature](https://mlsanity.com/paper/1902.03356/) (2019)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [Prototype Completion with Primitive Knowledge for Few-Shot Learning](https://mlsanity.com/paper/2009.04960/) (2020)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition](https://mlsanity.com/paper/2101.02833/) (2021)
- [Learning to Forget for Meta-Learning](https://mlsanity.com/paper/1906.05895/) (2019)
- [Learning where to learn: Gradient sparsity in meta and continual learning](https://mlsanity.com/paper/2110.14402/) (2021)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning](https://mlsanity.com/paper/1905.06331/) (2019)
- [ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion](https://mlsanity.com/paper/2306.14770/) (2023)

## Built on by (most cited first, 30 of 40)

- [Neural Network Diffusion](https://mlsanity.com/paper/2402.13144/) (2024)
- [Diffusion-Based Neural Network Weights Generation](https://mlsanity.com/paper/2402.18153/) (2024)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion](https://mlsanity.com/paper/2407.10973/) (2024)
- [Unsupervised Model Tree Heritage Recovery](https://mlsanity.com/paper/2405.18432/) (2024)
- [ElastoGen: 4D Generative Elastodynamics](https://mlsanity.com/paper/2405.15056/) (2024)
- [VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning](https://mlsanity.com/paper/2509.25033/) (2025)
- [Few-shot Online Anomaly Detection and Segmentation](https://mlsanity.com/paper/2403.18201/) (2024)
- [Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance](https://mlsanity.com/paper/2511.00543/) (2025)
- [DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights](https://mlsanity.com/paper/2601.05052/) (2026)
- [Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems](https://mlsanity.com/paper/2311.03488/) (2023)
- [Learning to Learn Weight Generation via Local Consistency Diffusion](https://mlsanity.com/paper/2502.01117/) (2025)
- [Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2603.13341/) (2026)
- [KNN Transformer with Pyramid Prompts for Few-Shot Learning](https://mlsanity.com/paper/2410.10227/) (2024)
- [Flow to Learn: Flow Matching on Neural Network Parameters](https://mlsanity.com/paper/2503.19371/) (2025)
- [Heterogeneous Adversarial Play in Interactive Environments](https://mlsanity.com/paper/2510.18407/) (2025)
- [Unleash Graph Neural Networks from Heavy Tuning](https://mlsanity.com/paper/2405.12521/) (2024)
- [RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks](https://mlsanity.com/paper/2411.16870/) (2024)
- [HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning](https://mlsanity.com/paper/2504.15323/) (2025)
- [Diffusion Models for Hyperspectral Image Analysis: A Comprehensive Review](https://mlsanity.com/paper/2505.11158/) (2025)
- [RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction](https://mlsanity.com/paper/2603.18865/) (2026)
- [Meta ControlNet: Enhancing Task Adaptation via Meta Learning](https://mlsanity.com/paper/2312.01255/) (2023)
- [Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning](https://mlsanity.com/paper/2410.05697/) (2024)
- [SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement](https://mlsanity.com/paper/2412.06352/) (2024)
- [AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2412.17601/) (2024)
- [State Combinatorial Generalization In Decision Making With Conditional Diffusion Models](https://mlsanity.com/paper/2501.13241/) (2025)
- [Flows and Diffusions on the Neural Manifold](https://mlsanity.com/paper/2507.10623/) (2025)
- [Semantic-guided LoRA Parameters Generation](https://mlsanity.com/paper/2509.10535/) (2025)
- [Actor-Critic without Actor](https://mlsanity.com/paper/2509.21022/) (2025)
- [GPN: Generative Point-based NeRF](https://mlsanity.com/paper/2404.08312/) (2024)

## Abstract (arXiv)

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning how to learn novel tasks. Its key idea is learning a deep model in a bi-level optimization manner, where the outer-loop process learns a shared gradient descent algorithm (i.e., its hyperparameters), while the inner-loop process leverage it to optimize a task-specific model by using only few labeled data. Although these existing methods have shown superior performance, the outer-loop process requires calculating second-order derivatives along the inner optimization path, which imposes considerable memory burdens and the risk of vanishing gradients. Drawing inspiration from recent progress of diffusion models, we find that the inner-loop gradient descent process can be actually viewed as a reverse process (i.e., denoising) of diffusion where the target of denoising is model weights but the origin data. Based on this fact, in this paper, we propose to model the gradient descent optimizer as a diffusion model and then present a novel task-conditional diffusion-based meta-learning, called MetaDiff, that effectively models the optimization process of model weights from Gaussion noises to target weights in a denoising manner. Thanks to the training efficiency of diffusion models, our MetaDiff do not need to differentiate through the inner-loop path such that the memory burdens and the risk of vanishing gradients can be effectvely alleviated. Experiment results show that our MetaDiff outperforms the state-of-the-art gradient-based meta-learning family in few-shot learning tasks.