Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks
This work addresses the challenge of insufficient information exploration and interpretability in node importance estimation for heterogeneous networks, offering an incremental improvement over existing graph neural methods.
The paper tackles the node importance estimation problem on heterogeneous information networks by proposing SKES, a framework that exploits structural knowledge to enrich node representations and quantify importance through disparity against a reference, achieving superior performance on three benchmarks.
Node importance estimation problem has been studied conventionally with homogeneous network topology analysis. To deal with network heterogeneity, a few recent methods employ graph neural models to automatically learn diverse sources of information. However, the major concern revolves around that their full adaptive learning process may lead to insufficient information exploration, thereby formulating the problem as the isolated node value prediction with underperformance and less interpretability. In this work, we propose a novel learning framework: SKES. Different from previous automatic learning designs, SKES exploits heterogeneous structural knowledge to enrich the informativeness of node representations. Based on a sufficiently uninformative reference, SKES estimates the importance value for any input node, by quantifying its disparity against the reference. This establishes an interpretable node importance computation paradigm. Furthermore, SKES dives deep into the understanding that "nodes with similar characteristics are prone to have similar importance values" whilst guaranteeing that such informativeness disparity between any different nodes is orderly reflected by the embedding distance of their associated latent features. Extensive experiments on three widely-evaluated benchmarks demonstrate the performance superiority of SKES over several recent competing methods.