Modality-task dependent heterogeneous mixture-of-experts model for multimodal time series representation learning
Lei Yao, Yong Zhang, Qin Li, Qi Li et autres
Multimodal time series representation learning has been extensively applied in healthcare, financial forecasting, and autonomous driving. However, heterogeneity among modalities has challenges for robust representation learning and multimodal task adaptation. To address the limitations of existing methods that lack sufficient consideration of …
cn (code pays fourni par la source)
0 citations
Complex & Intelligent Systems