English

A preferential attachment model with random initial degrees

Probability 2020-06-05 v3 Combinatorics

Abstract

In this paper, a random graph process G(t)t1{G(t)}_{t\geq 1} is studied and its degree sequence is analyzed. Let (Wt)t1(W_t)_{t\geq 1} be an i.i.d. sequence. The graph process is defined so that, at each integer time tt, a new vertex, with WtW_t edges attached to it, is added to the graph. The new edges added at time t are then preferentially connected to older vertices, i.e., conditionally on G(t1)G(t-1), the probability that a given edge is connected to vertex i is proportional to di(t1)+δd_i(t-1)+\delta, where di(t1)d_i(t-1) is the degree of vertex ii at time t1t-1, independently of the other edges. The main result is that the asymptotical degree sequence for this process is a power law with exponent τ=min{τW,τP}\tau=\min\{\tau_{W}, \tau_{P}\}, where τW\tau_{W} is the power-law exponent of the initial degrees (Wt)t1(W_t)_{t\geq 1} and τP\tau_{P} the exponent predicted by pure preferential attachment. This result extends previous work by Cooper and Frieze, which is surveyed.

Keywords

Cite

@article{arxiv.0705.4151,
  title  = {A preferential attachment model with random initial degrees},
  author = {Maria Deijfen and Henri van den Esker and Remco van der Hofstad and Gerard Hooghiemstra},
  journal= {arXiv preprint arXiv:0705.4151},
  year   = {2020}
}
R2 v1 2026-06-21T08:32:51.879Z