# Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

arXiv: https://arxiv.org/abs/2402.11922 · HTML: https://mlsanity.com/paper/2402.11922/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 42 of its 61 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [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)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale](https://mlsanity.com/paper/2303.06555/) (2023)
- [HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion](https://mlsanity.com/paper/2303.17015/) (2023)
- [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2208.05233/) (2022)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2206.09113/) (2022)
- [Learning to Learn with Generative Models of Neural Network Checkpoints](https://mlsanity.com/paper/2209.12892/) (2022)

## Built on by (most cited first, 15 of 15)

- [Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey](https://mlsanity.com/paper/2503.13502/) (2025)
- [Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization](https://mlsanity.com/paper/2405.14132/) (2024)
- [Diffusion Transformers as Open-World Spatiotemporal Foundation Models](https://mlsanity.com/paper/2411.12164/) (2024)
- [Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting](https://mlsanity.com/paper/2506.00635/) (2025)
- [UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Prediction](https://mlsanity.com/paper/2411.12972/) (2024)
- [Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Prediction](https://mlsanity.com/paper/2501.13794/) (2025)
- [TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamics](https://mlsanity.com/paper/2408.09825/) (2024)
- [ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting](https://mlsanity.com/paper/2409.06282/) (2024)
- [Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios](https://mlsanity.com/paper/2506.24063/) (2025)
- [Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding](https://mlsanity.com/paper/2510.18360/) (2025)
- [Meta-Transfer Learning Powered Temporal Graph Networks for Cross-City Real Estate Appraisal](https://mlsanity.com/paper/2410.08947/) (2024)
- [Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need](https://mlsanity.com/paper/2503.22193/) (2025)
- [Beyond the Next Port: A Multi-Task Transformer for Forecasting Future Voyage Segment Durations](https://mlsanity.com/paper/2601.08013/) (2026)
- [Continuous Cross-Domain Traffic State Prediction via Memory-Augmented Graph Liquid Time-Constant Networks](https://mlsanity.com/paper/2606.15807/) (2026)
- [Image Synthesis as an Intermediate for Controllable Time Series Generation](https://mlsanity.com/paper/2610.05211/) (2026)

## Abstract (arXiv)

Spatio-temporal modeling is foundational for smart city applications, yet it is often hindered by data scarcity in many cities and regions. To bridge this gap, we propose a novel generative pre-training framework, GPD, for spatio-temporal few-shot learning with urban knowledge transfer. Unlike conventional approaches that heavily rely on common feature extraction or intricate few-shot learning designs, our solution takes a novel approach by performing generative pre-training on a collection of neural network parameters optimized with data from source cities. We recast spatio-temporal few-shot learning as pre-training a generative diffusion model, which generates tailored neural networks guided by prompts, allowing for adaptability to diverse data distributions and city-specific characteristics. GPD employs a Transformer-based denoising diffusion model, which is model-agnostic to integrate with powerful spatio-temporal neural networks. By addressing challenges arising from data gaps and the complexity of generalizing knowledge across cities, our framework consistently outperforms state-of-the-art baselines on multiple real-world datasets for tasks such as traffic speed prediction and crowd flow prediction. The implementation of our approach is available: https://github.com/tsinghua-fib-lab/GPD.