Multiscale Clustering Based Diffusion Representation Learning Method

Abstract

Information diffusion model aims to understand the process of information diffusion in the network. Currently, state-of-the-art methods utilize vector representation of users to encode these factors. Apart from personal factors, decisions of others of the local community can also affect a user's decision on propagation. Recently, a multiscale information diffusion model called HID applies hierarchical clustering to improve the performance of many existing diffusion models. Though extensive experiments have proven the effectiveness of the model, it fails to encode diffusion time into the representation space, and the adopted clustering algorithms are independent of the diffusion model. Thus, we propose a multiscale clustering based diffusion representation method that incorporates diffusion time into diffusion proximity matrix and adopts a hierarchical clustering method suitable for multiscale diffusion learning. Experiments show the effectiveness of the proposed method. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Cluster analysis.

A Survey of Information Dissemination Model, Datasets, and Insight

“…Ramezani et al [109] propose a probabilistic generative model that maps the interrelationships between chain edges and cascade processes with a coupling matrix decomposition to infer the underlying social network structure and information dissemination. Considering the temporal, Xu et al [110] incorporate the time feature into the proximity matrix and utilize hierarchical clustering methods to classify multi-scale information, which improves the model's performance. Liu et al [111] use Markov to analyze the information dissemination process, which considers an adaptive network's information state and network topology.…”

“…Matrix Factorization [109], Clustering [110], Energy Mode [27,112,116], Forest-Fire Model [28,115] Belonging to probabilistic statistical models. Good interpretability to the patterns and causal relationships behind the information dissemination data.…”