Core Concepts
Generative Pre-Training Framework GPD enhances spatio-temporal few-shot learning by addressing data scarcity and heterogeneity in smart city applications.
Abstract
The content introduces a novel generative pre-training framework, GPD, for spatio-temporal few-shot learning. It addresses challenges of data scarcity and heterogeneity in smart city applications. The framework leverages pre-training in the parameter space to facilitate knowledge transfer across different cities. By optimizing neural network parameters and utilizing a Transformer-based denoising diffusion model, GPD generates tailored neural networks guided by prompts for accurate predictions. Extensive experiments on real-world datasets demonstrate superior performance compared to state-of-the-art baselines.
Directory:
Abstract
Introduction
Related Works
Proposed Method
Experiments
Results
Conclusion
Stats
"Our framework consistently outperforms state-of-the-art baselines on multiple real-world datasets."
"GPD achieves an average improvement of 7.87% over the best baseline on four datasets."