CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling
This addresses a limitation in random-walk-based HIN embedding for network analysis tasks, though it appears incremental as it builds on existing sampling methods.
The paper tackles the problem of imbalanced node sampling in heterogeneous information network (HIN) embedding by proposing CoarSAS2hvec, which uses self-avoid short sequence sampling with HIN coarsening to collect richer information, resulting in outperformance over nine other methods on four real-world datasets.
Heterogeneous information network (HIN) embedding aims to find the representations of nodes that preserve the proximity between entities of different nature. A family of approaches that are wildly adopted applies random walk to generate a sequence of heterogeneous context, from which the embedding is learned. However, due to the multipartite graph structure of HIN, hub nodes tend to be over-represented in the sampled sequence, giving rise to imbalanced samples of the network. Here we propose a new embedding method CoarSAS2hvec. The self-avoid short sequence sampling with the HIN coarsening procedure (CoarSAS) is utilized to better collect the rich information in HIN. An optimized loss function is used to improve the performance of the HIN structure embedding. CoarSAS2hvec outperforms nine other methods in two different tasks on four real-world data sets. The ablation study confirms that the samples collected by CoarSAS contain richer information of the network compared with those by other methods, which is characterized by a higher information entropy. Hence, the traditional loss function applied to samples by CoarSAS can also yield improved results. Our work addresses a limitation of the random-walk-based HIN embedding that has not been emphasized before, which can shed light on a range of problems in HIN analyses.