Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Yuxing, Zhu, Mingjie, Luo, Jiachi, Li, Song
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910459335016448
author Tian, Yuxing
Zhu, Mingjie
Luo, Jiachi
Li, Song
author_facet Tian, Yuxing
Zhu, Mingjie
Luo, Jiachi
Li, Song
contents This study focuses on long-term forecasting (LTF) on continuous-time dynamic graph networks (CTDGNs), which is important for real-world modeling. Existing CTDGNs are effective for modeling temporal graph data due to their ability to capture complex temporal dependencies but perform poorly on LTF due to the substantial requirement for historical data, which is not practical in most cases. To relieve this problem, a most intuitive way is data augmentation. In this study, we propose \textbf{\underline{U}ncertainty \underline{M}asked \underline{M}ix\underline{U}p (UmmU)}: a plug-and-play module that conducts uncertainty estimation to introduce uncertainty into the embedding of intermediate layer of CTDGNs, and perform masked mixup to further enhance the uncertainty of the embedding to make it generalize to more situations. UmmU can be easily inserted into arbitrary CTDGNs without increasing the number of parameters. We conduct comprehensive experiments on three real-world dynamic graph datasets, the results demonstrate that UmmU can effectively improve the long-term forecasting performance for CTDGNs.
format Preprint
id arxiv_https___arxiv_org_abs_2304_05749
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
Tian, Yuxing
Zhu, Mingjie
Luo, Jiachi
Li, Song
Machine Learning
Artificial Intelligence
This study focuses on long-term forecasting (LTF) on continuous-time dynamic graph networks (CTDGNs), which is important for real-world modeling. Existing CTDGNs are effective for modeling temporal graph data due to their ability to capture complex temporal dependencies but perform poorly on LTF due to the substantial requirement for historical data, which is not practical in most cases. To relieve this problem, a most intuitive way is data augmentation. In this study, we propose \textbf{\underline{U}ncertainty \underline{M}asked \underline{M}ix\underline{U}p (UmmU)}: a plug-and-play module that conducts uncertainty estimation to introduce uncertainty into the embedding of intermediate layer of CTDGNs, and perform masked mixup to further enhance the uncertainty of the embedding to make it generalize to more situations. UmmU can be easily inserted into arbitrary CTDGNs without increasing the number of parameters. We conduct comprehensive experiments on three real-world dynamic graph datasets, the results demonstrate that UmmU can effectively improve the long-term forecasting performance for CTDGNs.
title Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2304.05749