T-GINEE: A Tensor-Based Multilayer Graph Representation Learning
This work addresses the problem of learning from multilayer networks for network analysis researchers, but the improvements over existing methods are not quantified with concrete numbers, suggesting incremental novelty.
T-GINEE introduces a tensor-based regularization framework for multilayer graph representation learning that explicitly models inter-layer dependencies via CP decomposition and generalized estimating equations, achieving theoretical guarantees and empirical effectiveness on synthetic and real-world datasets.
Traditional network analysis focuses on single-layer networks, real-world systems often form multilayer networks with multiple relationship types. However, existing methods typically fail to capture complex inter-layer dependencies by treating layers independently or aggregating them. To address this, we propose T-GINEE (Tensor-Based Generalized Multilayer-graph Estimating Equation), a statistical regularization framework combining tensor-based generalized estimating equations with task-specific loss to model cross-network correlations explicitly. Key innovations include: (1) CP tensor decomposition capturing structural dependencies via shared latent factors; (2) a generalized estimating equation framework modeling inter-layer correlations through working covariance matrices; and (3) a flexible link function accommodating characteristics like sparsity. Our theoretical analysis establishes consistency and asymptotic normality under mild conditions. Extensive experiments on synthetic and real-world datasets validate T-GINEE's effectiveness for multilayer network analysis.