Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
This work is significant for researchers and practitioners working with HINs, particularly in scenarios with limited labeled data, by offering a more effective and efficient classification solution.
This paper addresses the challenge of classifying objects in Heterogeneous Information Networks (HINs, networks with different types of nodes and edges), especially when labeled data is scarce. The proposed model, ConCH, improves classification accuracy while maintaining computational efficiency.
A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types. We study the problem of classifying objects in HINs. Most existing methods perform poorly when given scarce labeled objects as training sets, and methods that improve classification accuracy under such scenarios are often computationally expensive. To address these problems, we propose ConCH, a graph neural network model. ConCH formulates the classification problem as a multi-task learning problem that combines semi-supervised learning with self-supervised learning to learn from both labeled and unlabeled data. ConCH employs meta-paths, which are sequences of object types that capture semantic relationships between objects. ConCH co-derives object embeddings and context embeddings via graph convolution. It also uses the attention mechanism to fuse such embeddings. We conduct extensive experiments to evaluate the performance of ConCH against other 15 classification methods. Our results show that ConCH is an effective and efficient method for HIN classification.