基于扩散神经网络生成的时空少样本学习
Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
AI总结：
针对城市时空数据稀缺问题，提出基于扩散模型的生成式预训练框架 GPD，通过引导生成定制神经网络实现跨城市知识迁移，在多项时空预测任务上优于基线。
摘要：
时空建模是智慧城市应用的基础，但常常受到许多城市和地区数据稀缺的阻碍。为了弥合这一差距，我们提出了一种新颖的生成式预训练框架 GPD，用于城市知识迁移的时空少样本学习。与严重依赖通用特征提取或复杂少样本学习设计的传统方法不同，我们的解决方案采用了一种新颖的方法，对使用源城市数据优化的一组神经网络参数进行生成式预训练。我们将时空少样本学习重新构建为预训练一个生成式扩散模型，该模型在提示的引导下生成定制的神经网络，从而能够适应不同的数据分布和特定城市的特征。GPD 采用基于 Transformer 的去噪扩散模型，该模型与模型无关，可以与强大的时空神经网络集成。通过解决数据差距和跨城市知识泛化复杂性带来的挑战，我们的框架在多个真实世界数据集上的交通速度预测和人群流量预测等任务中始终优于最先进的基线。我们的方法实现已公开：https://github.com/tsinghua-fib-lab/GPD。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
