A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
This work addresses the meta-path selection challenge in HIN embedding, which is important for network analysis applications, but it is incremental as it builds on existing variational and contrastive methods.
The authors tackled the problem of learning embeddings for Heterogeneous Information Networks (HINs) that improve clustering and preserve network structure, achieving competitive performance on real-world datasets for clustering and node classification tasks.
Heterogeneous Information Network (HIN) embedding refers to the low-dimensional projections of the HIN nodes that preserve the HIN structure and semantics. HIN embedding has emerged as a promising research field for network analysis as it enables downstream tasks such as clustering and node classification. In this work, we propose \ours for joint learning of cluster embeddings as well as cluster-aware HIN embedding. We assume that the connected nodes are highly likely to fall in the same cluster, and adopt a variational approach to preserve the information in the pairwise relations in a cluster-aware manner. In addition, we deploy contrastive modules to simultaneously utilize the information in multiple meta-paths, thereby alleviating the meta-path selection problem - a challenge faced by many of the famous HIN embedding approaches. The HIN embedding, thus learned, not only improves the clustering performance but also preserves pairwise proximity as well as the high-order HIN structure. We show the effectiveness of our approach by comparing it with many competitive baselines on three real-world datasets on clustering and downstream node classification.