报告题目：可视图表示学习在时间序列预测中的应用研究（Learning Visibility Graph Representation for Time Series Forecasting）
报告人：毛胜忠 博士
报告时间：2024年11月29日（周五） 上午9:00-11:00
报告地点：临江楼A916
主持人：姜 峰 教授 南京信息工程大学
报告人简介
毛胜忠，曼彻斯特大学计算机科学专业博士，研究方向为人工智能、机器学习、图神经网络和时序数据挖掘，主要集中在通过图表示学习和注意力机制处理小样本和长序列时序数据建模问题，并将其应用于机器学习的预测和分类任务。其博士研究课题获得曼彻斯特大学校长、女爵Nancy Rothwell教授发起的校长奖学金 (President's Doctoral Scholar Award) 全额资助，同时入选校长博士学者研究领导力发展项目，并获得校长博士学者发展基金的支持。过去五年，其相关研究成果已在十余篇国际顶级期刊和会议上发表。
报告摘要
Visibility algorithm acts as a mapping that bridges graph representation learning with time series analysis, which has been broadly investigated for forecasting tasks. However, the intrinsic nature of visibility encoding yields graphs structured exclusively by binary adjacency matrix, leading to inevitable information loss of temporal sequence during the mapping. To this end, we introduce Angular Visibility Graph Networks (AVGNets), designed with two core features: (i) The framework reconstructs weighted graphs to encode time series by leveraging topological insights derived from visual angles of visibility networks, which capture sequential and structural information within weighted angular matrix. (ii) 𝑃𝑟𝑜𝑏𝐴𝑡𝑡𝑒𝑛𝑡𝑖𝑜𝑛 module is proposed for evaluating probabilistic attention of weighted networks, with remarkable capabilities to extract intrinsic and extrinsic temporal dependencies across multi-layer graphs. Extensive experiments and ablation studies on real-world datasets covering diverse ranges demonstrate that AVGNets achieve state-of-the-art performance, offering an innovative perspective on graph representation for sequence modeling.
欢迎广大师生踊跃参加！
计算机学院
未来技术学院
2024年11月25日