Using Linear Graph Theory and the Principle of Orthogonality to Model Multibody, ... Using Linear Graph Theory and the Principle of Orthogonality to Model Multibody, Multi-Domain Systems: Author: C ...

However, such tensor models are often unable to incorporate the underlying domain knowledge when compressing high-dimensional models. To this end, we introduce a novel graph-regularized tensor ...

A domain generalized approach on surgical scene graphs to predict instrument-tissue interaction during robot-assisted surgery. We incorporate incremental learning to the feature extraction network and ...

State space models (SSMs) like Mamba are effective and efficient in modeling long-range dependencies in sequential data, but adapting them to non-sequential graph data is challenging. Many sequence ...

In this paper, we study graph contrastive learning in the context of biomedical domain, where molecular graphs are present. We propose a novel framework called MoCL, which utilizes domain knowledge at ...

The domain decomposed behavior of the adjoint Neumann-Ulam Monte Carlo method for solving linear systems is analyzed using the spectral properties of the linear oper- ator. Relationships for the ...