Personalized Degrees: Effects on Link Formation in Dynamic Networks from an Egocentric Perspective

Abstract

Understanding mechanisms driving link formation in dynamic social networks is a long-standing problem that has implications to understanding social structure as well as link prediction and recommendation. Social networks exhibit a high degree of transitivity, which explains the successes of common neighbor-based methods for link prediction. In this paper, we examine mechanisms behind link formation from the perspective of an ego node. We introduce the notion of personalized degree for each neighbor node of the ego, which is the number of other neighbors a particular neighbor is connected to. From empirical analyses on four on-line social network datasets, we find that neighbors with higher personalized degree are more likely to lead to new link formations when they serve as common neighbors with other nodes, both in undirected and directed settings. This is complementary to the finding of Adamic and Adar [1] that neighbor nodes with higher (global) degree are less likely to lead to new link formations. Furthermore, on directed networks, we find that personalized out-degree has a stronger effect on link formation than personalized in-degree, whereas global in-degree has a stronger effect than global out-degree. We validate our empirical findings through several link recommendation experiments and observe that incorporating both personalized and global degree into link recommendation greatly improves accuracy.

Continuous-Time Graph Representation with Sequential Survival Process

“…However, in recent years, substantial attention has also been devoted to the modeling of continuous-time networks. Prominent works have utilized Poisson (Fan et al 2021;Trivedi et al 2019;Celikkanat, Nakis, and Mørup 2022) and Hawkes processes (Hawkes 1971b,a;Blundell, Beck, and Heller 2012;Arastuie, Paul, and Xu 2020;Delattre, Fournier, and Hoffmann 2016;Zuo et al 2018;Lu et al 2019;Huang et al 2022;Yang, Rao, and Neville 2017) in order to define principled learning procedures under continuous-time network likelihoods of eventbased data. Contrary to the previous studies, which work on a network block level, the HTNE (Zuo et al 2018) extends the Hawkes process modeling to account for node-level embeddings.…”