Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yifei, Liu, Junming, Chen, Yirong, Yan, Xuefeng, Wang, Ding
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.09630
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911106011758592
author Sun, Yifei
Liu, Junming
Chen, Yirong
Yan, Xuefeng
Wang, Ding
author_facet Sun, Yifei
Liu, Junming
Chen, Yirong
Yan, Xuefeng
Wang, Ding
contents Multivariate time series data typically comprises two distinct modalities: variable semantics and sampled numerical observations. Traditional time series models treat variables as anonymous statistical signals, overlooking the rich semantic information embedded in variable names and data descriptions. However, these textual descriptors often encode critical domain knowledge that is essential for robust and interpretable modeling. Here we present TimeMKG, a multimodal causal reasoning framework that elevates time series modeling from low-level signal processing to knowledge informed inference. TimeMKG employs large language models to interpret variable semantics and constructs structured Multivariate Knowledge Graphs that capture inter-variable relationships. A dual-modality encoder separately models the semantic prompts, generated from knowledge graph triplets, and the statistical patterns from historical time series. Cross-modality attention aligns and fuses these representations at the variable level, injecting causal priors into downstream tasks such as forecasting and classification, providing explicit and interpretable priors to guide model reasoning. The experiment in diverse datasets demonstrates that incorporating variable-level knowledge significantly improves both predictive performance and generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling
Sun, Yifei
Liu, Junming
Chen, Yirong
Yan, Xuefeng
Wang, Ding
Machine Learning
Artificial Intelligence
Multivariate time series data typically comprises two distinct modalities: variable semantics and sampled numerical observations. Traditional time series models treat variables as anonymous statistical signals, overlooking the rich semantic information embedded in variable names and data descriptions. However, these textual descriptors often encode critical domain knowledge that is essential for robust and interpretable modeling. Here we present TimeMKG, a multimodal causal reasoning framework that elevates time series modeling from low-level signal processing to knowledge informed inference. TimeMKG employs large language models to interpret variable semantics and constructs structured Multivariate Knowledge Graphs that capture inter-variable relationships. A dual-modality encoder separately models the semantic prompts, generated from knowledge graph triplets, and the statistical patterns from historical time series. Cross-modality attention aligns and fuses these representations at the variable level, injecting causal priors into downstream tasks such as forecasting and classification, providing explicit and interpretable priors to guide model reasoning. The experiment in diverse datasets demonstrates that incorporating variable-level knowledge significantly improves both predictive performance and generalization.
title TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.09630