Scalable Deep Generative Relational Models with High-Order Node Dependence

Abstract

We propose a probabilistic framework for modelling and exploring the latent structure of relational data. Given feature information for the nodes in a network, the scalable deep generative relational model (SDREM) builds a deep network architecture that can approximate potential nonlinear mappings between nodes' feature information and the nodes' latent representations. Our contribution is two-fold:(1) We incorporate high-order neighbourhood structure information to generate the latent representations at each node, which vary smoothly over the network. (2) Due to the Dirichlet random variable structure of the latent representations, we introduce a novel data augmentation trick which permits efficient Gibbs sampling. The SDREM can be used for large sparse networks as its computational cost scales with the number of positive links. We demonstrate its competitive performance through improved link prediction performance on a range of real-world datasets.

Parallel Prediction Method of Knowledge Proficiency Based on Bloom’s Cognitive Theory

“…With the continuous advancement of internet and artificial intelligence technologies, AI algorithms have significantly impacted various aspects of our lives, such as smart city development [1][2][3], energy management [4,5], and financial services [6,7]. Similarly, the field of education has been continually evolving due to the influence of artificial intelligence [8][9][10][11][12][13] and internet technologies [14,15]. This is particularly evident in the context of 'Internet + Education', a new educational model that has emerged in recent years.…”