Learning from complex data is becoming increasingly important, and graph kernels have recently evolved into a rapidly developing branch of learning on structured data. However, previously proposed kernels rely on having discrete node label information. In this paper, we explore the power of continuous node-level features for propagation-based graph kernels. Speci cally, propagation kernels expl...

The study of information spreading based on the complex network theory and topological structure has become an important issue in networks. Plenty infectious disease models are widely used for diffusion research Based these state-of-the-art models, a new epidemic dynamic model with evolution equations is proposed performed homogeneous heterogeneous networks, respectively, this paper. Meanwhile,...

Recurrent neural networks (RNNs) have been successfully applied to a variety of problems involving sequential data, but their optimization is sensitive parameter initialization, architecture, and optimizer hyperparameters. Considering RNNs as dynamical systems, natural way capture stability, i.e., the growth decay over long iterates, are Lyapunov Exponents (LEs), which form spectrum. The LEs be...

Multipath-based simultaneous localization and mapping (SLAM) is an emerging paradigm for accurate indoor constrained by limited navigation resources. The goal of multipath-based SLAM to support the estimation time-varying positions mobile agents detecting localizing radio-reflective surfaces in environment. In existing Bayesian methods, a propagation surface represented mirror image each physic...