Awesome-GNN4TS

Awesome-GNN4TS

时间序列分析中图神经网络的研究进展与应用

本项目汇集图神经网络(GNN)在时间序列分析领域的研究进展和资源,涵盖预测、分类、异常检测和插值等任务。内容包括相关论文、数据集和应用概述,以及面向任务和模型的GNN4TS分类方法,为该领域研究和应用提供参考。

GNN时间序列分析图神经网络机器学习深度学习Github开源项目
<div align="center"> <!-- <h1><b> BasicTS </b></h1> --> <!-- <h2><b> BasicTS </b></h2> --> <h2><b> Awesome Graph Neural Networks for Time Series Analysis (GNN4TS) </b></h2> </div> <div align="center">

Awesome License: MIT

</div> <div align="center">

[<a href="https://arxiv.org/abs/2307.03759">Paper Page</a>] [<a href="https://mp.weixin.qq.com/s/_G2WieJPrWcaK8aegXObUA">中文解读1</a>] [<a href="https://mp.weixin.qq.com/s/ZsSj6C_uJd2dqmynXcrOSA">中文解读2</a>] [<a href="https://zhuanlan.zhihu.com/p/643249754">中文解读3</a>] [<a href="https://mp.weixin.qq.com/s?__biz=Mzk0NDE5Nzg1Ng==&mid=2247507893&idx=1&sn=99ef8465c09cbcd3346d2d4019f7b3b5&chksm=c32ac63af45d4f2c1141d31923252ca6bbff123564c9424d452f046ab98854a3219dbd08d01d#rd">中文解读4</a>]

</div> <p align="center"> <img src="./assets/gnn4ts.png" width="350"> </p>

🔥 Abundant resources related to GNNs for time series analysis (GNN4TS) by Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, Shirui Pan

🙋 Please let us know if you find out a mistake or have any suggestions!

🌟 If you find this resource helpful, please consider to star this repository and cite our survey paper:

@article{jin2024gnn4ts,
  title={A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection},
  author={Jin, Ming and Koh, Huan Yee and Wen, Qingsong and Zambon, Daniele and Alippi, Cesare and Webb, Geoffrey I and King, Irwin and Pan, Shirui},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year={2024}
}

Time series analysis is a fundamental task in many real-world applications, such as finance, healthcare, and transportation. Recently, graph neural networks (GNNs) have been widely used in time series analysis. This repository aims to collect the resources related to GNNs for time series analysis (GNN4TS).

时间序列分析是许多现实应用场景中的一项基本任务,例如对金融、医疗、和交通运输数据的分析与建模。近年来,图神经网络(GNN)已广泛应用于时间序列分析。本项目旨在收集整理与时间序列分析相关图神经网络(GNN4TS)的资源。

<p align="center"> <img src="./assets/taxonomy.png" width="1200"> </p>

We provide two taxonomies for GNN4TS. The first taxonomy (left) is task-oriented and the second taxonomy (right) is model-oriented. The task-oriented taxonomy is based on the tasks that GNNs are used for in time series analysis. The model-oriented taxonomy is based on the types of GNNs used in time series analysis.

针对GNN4TS的大框架,我们提出了两种分类法:其一(左)是面向任务的,其次(右)是面向模型的。第一种分类法基于GNN在时间序列分析中施展的具体任务进行划分,第二种分类法则基于时间序列分析中GNN的类型与设计进行归纳。

✨ News

  • [2024-08-09] 🔥 Our survey was accepted by IEEE TPAMI (IF 20.8). 🎉
  • [2023-08-09] 📮 Our updated version (ver. 10 Aug) of the survey is released [paper link]
  • [2023-07-07] 📮 Our GNN4TS survey (ver. 11 Jul) is made available on arXiv [paper link]
  • [2023-06-19] 📮 We have released this repository that collects the resources related to GNNs for time series analysis (GNN4TS). We will keep updating this repository, and welcome to STAR🌟 and WATCH to keep track of it.

🔭 Table of Contents

📚 Collection of Papers

GNNs for Time Series Forecasting (GNN4TSF)

  • Diffusion convolutional recurrent neural network: Data-driven traffic forecasting (ICLR, 2018) [paper]
  • Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting (IJCAI, 2018) [paper]
  • Urban traffic prediction from spatio-temporal data using deep meta learning (KDD, 2019) [paper]
  • Autoregressive Models for Sequences of Graphs (IEEE IJCNN, 2019) [paper]
  • ST-UNet: A Spatio-Temporal U-Network forGraph-structured Time Series Modeling (arXiv, 2019) [paper]
  • Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting (AAAI, 2019) [paper]
  • Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting (MileTS, 2019) [paper]
  • Attention Based Spatial-Temporal Graph Convolutional Networksfor Traffic Flow Forecasting (AAAI, 2019) [paper]
  • Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting (AAAI, 2019) [paper]
  • Graph wavenet for deep spatial-temporal graph modeling (IJCAI, 2019) [paper]
  • STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting (IJCAI, 2019) [paper]
  • Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting (AAAI, 2020) [paper]
  • Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks (KDD, 2020) [paper]
  • Traffic Flow Prediction via Spatial Temporal Graph Neural Network (WWW, 2020) [paper]
  • Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems (WWW, 2020) [paper]
  • GMAN: A Graph Multi-Attention Network for Traffic Prediction (AAAI, 2020) [paper]
  • Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting (AAAI, 2020) [paper]
  • Spatio-Temporal Graph Structure Learning for Traffic Forecasting (AAAI, 2020) [paper]
  • Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting (NeurIPS, 2020) [paper]
  • Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (NeurIPS, 2020) [paper]
  • GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for Sleep Stage Classification (IJCAI, 2020) [paper]
  • LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks (IJCAI, 2020) [paper]
  • ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed (CIKM, 2020) [paper]
  • Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting (ICDM, 2020) [paper]
  • Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data (ECAI, 2020) [paper]
  • Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction (ECCV, 2020) [paper]
  • Discrete Graph Structure Learning for Forecasting Multiple Time Series (ICLR, 2021) [paper]
  • MTHetGNN: A heterogeneous graph embedding framework for multivariate time series forecasting (Pattern Recognition, 2021) [paper]
  • Graph Edit Networks (ICLR, 2021) [paper]
  • Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting (ICML, 2021) [paper]
  • Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting (KDD, 2021) [paper]
  • Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting (AAAI, 2021) [paper]
  • Hierarchical Graph Convolution Network for Traffic Forecasting (AAAI, 2021) [paper]
  • Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network (AAAI, 2021) [paper]
  • TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning (IJCAI, 2021) [paper]
  • DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting (ICML, 2022) [paper]
  • Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks (NeurIPS, 2022) [paper]
  • Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities (CIKM, 2022) [paper]
  • Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs (IEEE TKDE, 2022) [paper]
  • Graph Neural Controlled Differential Equations for Traffic Forecasting (AAAI, 2022) [paper]
  • CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting (AAAI, 2022) [paper]
  • Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search (ACM TKDD, 2022) [paper]
  • TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting (ICLR, 2022) [paper]
  • Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting (KDD, 2022) [paper]
  • Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting (KDD, 2022) [paper]
  • Mining Spatio-Temporal Relations via Self-Paced Graph Contrastive Learning (KDD, 2022) [paper]
  • Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting (IJCAI, 2022) [paper]
  • Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention (IJCAI, 2022) [paper]
  • FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffc Flow Forecasting (IJCAI, 2022) [paper]
  • METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting (VLDB, 2022) [paper]
  • Scalable Spatiotemporal Graph Neural Networks (AAAI, 2023) [paper]
  • Graph State-Space Models (arXiv,

编辑推荐精选

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

TRELLIS

TRELLIS

用于可扩展和多功能 3D 生成的结构化 3D 潜在表示

TRELLIS 是一个专注于 3D 生成的项目,它利用结构化 3D 潜在表示技术,实现了可扩展且多功能的 3D 生成。项目提供了多种 3D 生成的方法和工具,包括文本到 3D、图像到 3D 等,并且支持多种输出格式,如 3D 高斯、辐射场和网格等。通过 TRELLIS,用户可以根据文本描述或图像输入快速生成高质量的 3D 资产,适用于游戏开发、动画制作、虚拟现实等多个领域。

ai-agents-for-beginners

ai-agents-for-beginners

10 节课教你开启构建 AI 代理所需的一切知识

AI Agents for Beginners 是一个专为初学者打造的课程项目,提供 10 节课程,涵盖构建 AI 代理的必备知识,支持多种语言,包含规划设计、工具使用、多代理等丰富内容,助您快速入门 AI 代理领域。

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

下拉加载更多