Surrogate-Assisted Robust Optimization of Large-Scale Networks Based on Graph Embedding

Robust optimization of complex networks has attracted much attention in recent years. Although existing methods have been successful in achieving promising results, the computational cost for robust optimization tasks is extremely high, which prevents them from being further applied to large-scale networks. Thus, computationally efficient robust optimization methods are in high demand. This article proposes a low-cost method for estimating the robustness of networks with the help of graph embedding techniques and surrogate models. An evolutionary algorithm is then developed to find large-scale robust networks by combining the surrogate-assisted low-cost robustness estimator with the time-consuming real robustness measure by means of a model management strategy. The experimental results on different kinds of synthetic and real networks demonstrate the highly competitive search ability of the proposed algorithm. In addition, the algorithm is able to save up to 80% of the computation time for enhancing the robustness of large-scale networks compared with the state-of-the-art methods.

I. Introduction

The complex network model [1] is one of the research hotspots in recent decades, where members in the system can be denoted as nodes and the interactive relations between members can be denoted as links. This way, different kinds of networks give us descriptive and intuitive representations of systems’ dynamics, which can find a wide range of applications in nature and society [2]. The method to dig out and analyze the information involved in networks is of significance in practice, and a possible way is to dissect characteristics and features of networks, such as local small-world (SW) structure [3], power-law degree distribution [4], functional clusters detection [5], and nodal mixing pattern [6], which have been greatly emphasized in recent studies.