IEEE

Time-DisCo: A Disentangled Contrastive Autoencoder Approach to Enhancing Multivariate Probabilistic Time Series Forecasting From Multisensor Data

Abstract: In the context of data-driven decision-making, constructing accurate and well-generalized probabilistic forecasting models to handle dynamic, complex, and high-dimensional multivariate time ...
IEEE

Time-DisCo: A Disentangled Contrastive Autoencoder Approach to Enhancing Multivariate Probabilistic Time Series Forecasting from Multi-Sensor Data

Abstract: In the context of data-driven decision-making, constructing accurate and well-generalized probabilistic forecasting models to handle dynamic, complex, and high-dimensional multivariate time ...
C&EN

MVCL-DTI: Predicting Drug–Target Interactions Using a Multiview Contrastive Learning Model on a Heterogeneous Graph

School of Computer Science and Technology, Soochow University, Jiangsu 215006, China Collaborative Innovation Center of Novel Software Technology and Industrialization, Jiangsu 210000, China ...
EurekAlert!

New AI method makes materials design more efficient and transparent

Disentangled variational autoencoder (D-VAE) separates materials properties from the latent space by conditioning to make inverse materials design more efficient and transparent. It combines labeled ...