Parameter-free Structural Diversity Search

TL;DR

This paper introduces a parameter-free model for structural diversity search in graphs, eliminating the need for input parameters and improving robustness in identifying social contexts.

Contribution

The paper proposes a novel parameter-free structural diversity model using discriminative cores and h-index, along with an efficient top-k search algorithm.

Findings

Existing models are sensitive to parameter t.

The proposed method outperforms t-core based models.

Experiments confirm the effectiveness and efficiency of the new approach.

Abstract

The problem of structural diversity search is to find the top-k vertices with the largest structural diversity in a graph. However, when identifying distinct social contexts, existing structural diversity models (e.g., t-sized component, t-core, and t-brace) are sensitive to an input parameter of t. To address this drawback, we propose a parameter-free structural diversity model. Specifically, we propose a novel notation of discriminative core, which automatically models various kinds of social contexts without parameter t. Leveraging on discriminative cores and h-index, the structural diversity score for a vertex is calculated. We study the problem of parameter-free structural diversity search in this paper. An efficient top-k search algorithm with a well-designed upper bound for pruning is proposed. Extensive experiment results demonstrate the parameter sensitivity of existing t-core based model and verify the superiority of our methods.