Meta-path Free Semi-supervised Learning for Heterogeneous Networks
This work addresses the problem of semi-supervised learning on heterogeneous networks for researchers and practitioners, offering an incremental improvement by eliminating the need for meta-paths.
The paper tackles the challenge of injecting heterogeneity into graph neural networks for heterogeneous graphs by proposing a meta-path free approach that relaxes heterogeneity stress through expanded model capacity, achieving superior performance over state-of-the-art methods on six real-world graphs.
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification. However, analyzing heterogeneous graph of different types of nodes and links still brings great challenges for injecting the heterogeneity into a graph neural network. A general remedy is to manually or automatically design meta-paths to transform a heterogeneous graph into a homogeneous graph, but this is suboptimal since the features from the first-order neighbors are not fully leveraged for training and inference. In this paper, we propose simple and effective graph neural networks for heterogeneous graph, excluding the use of meta-paths. Specifically, our models focus on relaxing the heterogeneity stress for model parameters by expanding model capacity of general GNNs in an effective way. Extensive experimental results on six real-world graphs not only show the superior performance of our proposed models over the state-of-the-arts, but also demonstrate the potentially good balance between reducing the heterogeneity stress and increasing the parameter size. Our code is freely available for reproducing our results.