Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Yuan, Han, Chonghua, Ding, Jingtao, Zhang, Guozhen, Jin, Depeng, Li, Yong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912660207960064
author Yuan, Yuan
Han, Chonghua
Ding, Jingtao
Zhang, Guozhen
Jin, Depeng
Li, Yong
author_facet Yuan, Yuan
Han, Chonghua
Ding, Jingtao
Zhang, Guozhen
Jin, Depeng
Li, Yong
contents The urban environment is characterized by complex spatio-temporal dynamics arising from diverse human activities and interactions. Effectively modeling these dynamics is essential for understanding and optimizing urban systems. In this work, we introduce UrbanDiT, a foundation model for open-world urban spatio-temporal learning that successfully scales up diffusion transformers in this field. UrbanDiT pioneers a unified model that integrates diverse data sources and types while learning universal spatio-temporal patterns across different cities and scenarios. This allows the model to unify both multi-data and multi-task learning, and effectively support a wide range of spatio-temporal applications. Its key innovation lies in the elaborated prompt learning framework, which adaptively generates both data-driven and task-specific prompts, guiding the model to deliver superior performance across various urban applications. UrbanDiT offers three advantages: 1) It unifies diverse data types, such as grid-based and graph-based data, into a sequential format; 2) With task-specific prompts, it supports a wide range of tasks, including bi-directional spatio-temporal prediction, temporal interpolation, spatial extrapolation, and spatio-temporal imputation; and 3) It generalizes effectively to open-world scenarios, with its powerful zero-shot capabilities outperforming nearly all baselines with training data. UrbanDiT sets up a new benchmark for foundation models in the urban spatio-temporal domain. Code and datasets are publicly available at https://github.com/tsinghua-fib-lab/UrbanDiT.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion Transformers as Open-World Spatiotemporal Foundation Models
Yuan, Yuan
Han, Chonghua
Ding, Jingtao
Zhang, Guozhen
Jin, Depeng
Li, Yong
Machine Learning
Artificial Intelligence
The urban environment is characterized by complex spatio-temporal dynamics arising from diverse human activities and interactions. Effectively modeling these dynamics is essential for understanding and optimizing urban systems. In this work, we introduce UrbanDiT, a foundation model for open-world urban spatio-temporal learning that successfully scales up diffusion transformers in this field. UrbanDiT pioneers a unified model that integrates diverse data sources and types while learning universal spatio-temporal patterns across different cities and scenarios. This allows the model to unify both multi-data and multi-task learning, and effectively support a wide range of spatio-temporal applications. Its key innovation lies in the elaborated prompt learning framework, which adaptively generates both data-driven and task-specific prompts, guiding the model to deliver superior performance across various urban applications. UrbanDiT offers three advantages: 1) It unifies diverse data types, such as grid-based and graph-based data, into a sequential format; 2) With task-specific prompts, it supports a wide range of tasks, including bi-directional spatio-temporal prediction, temporal interpolation, spatial extrapolation, and spatio-temporal imputation; and 3) It generalizes effectively to open-world scenarios, with its powerful zero-shot capabilities outperforming nearly all baselines with training data. UrbanDiT sets up a new benchmark for foundation models in the urban spatio-temporal domain. Code and datasets are publicly available at https://github.com/tsinghua-fib-lab/UrbanDiT.
title Diffusion Transformers as Open-World Spatiotemporal Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.12164