Hengshu Zhu

TL;DR: Wang et al. as discussed by the authors proposed a multi-task hierarchical graph representation learning (MugRep) framework for real estate appraisal, which first constructs a rich feature set to profile the real estate from multiple perspectives, and then constructs an evolving real estate transaction graph and a corresponding event graph convolution module to incorporate asynchronously spatiotemporal dependencies among real estate transactions.

TL;DR: This paper proposes a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to inherently accommodate the characteristics of implicit feedback in recommender system and aims at maximizing the posterior probability of novel set Wise preference comparisons.

TL;DR: A sequence-based semisupervised approach to modeling personalized context for mobile users using the Bayesian Hidden Markov Model and a novel approach for parameter estimation by integrating the Dirichlet Process Mixture model and the Mixture Unigram model are proposed.

TL;DR: This paper develops a scalable method for measuring the relevancy between categories through topic models and provides a link analysis approach for ranking user authority by considering the information in both the target category and the relevant categories.