TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling
This work addresses the challenge of robust and interpretable modeling in multivariate time series analysis for domains where variable semantics encode critical domain knowledge.
The paper tackles the problem of multivariate time series modeling by incorporating semantic information from variable names and descriptions, which traditional models overlook as anonymous signals. The proposed TimeMKG framework uses large language models to interpret variable semantics and construct knowledge graphs, resulting in significant improvements in predictive performance and generalization across diverse datasets.
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.