Mutual Information Measure for Glass Ceiling Effect in Preferential Attachment Models

Rui Luo, Buddhika Nettasinghe, Vikram Krishnamurthy

Abstract: This article introduces a novel mutual information-based measure to assess the glass ceiling effect in preferential attachment networks, which advances the analysis of inequalities in attributed networks. Using Shannon entropy and generalizing to Rényi entropy, our measure evaluates the conditional probability distributions of node attributes given the node degrees of adjacent nodes, which offers a more nuanced understanding of inequality compared to traditional methods that emphasize node degree distributions and degree assortativity alone. To evaluate the efficacy of the proposed measure, we evaluate it using an analytical structural inequality model as well as historical publication data. Results show that our mutual information measure aligns well with both the theoretical model and empirical data, underscoring its reliability as a robust approach for capturing inequalities in attributed networks. Moreover, we introduce a novel stochastic optimization algorithm that utilizes a parameterized conditional logit model for edge addition. Our algorithm is shown to outperform the baseline uniform distribution based approach in mitigating the glass ceiling effect. By strategically recommending links based on this algorithm, we can effectively hinder the glass ceiling effect within networks.