ActiveHNE: Active Heterogeneous Network Embedding
This work addresses the problem of efficiently learning embeddings in heterogeneous networks for researchers and practitioners, representing an incremental advancement by integrating active learning into existing HNE methods.
The paper tackles the challenge of heterogeneous network embedding (HNE) by developing ActiveHNE, a framework that combines semi-supervised embedding with active learning to utilize rare supervised information, resulting in improved performance and reduced query costs on public datasets.
Heterogeneous network embedding (HNE) is a challenging task due to the diverse node types and/or diverse relationships between nodes. Existing HNE methods are typically unsupervised. To maximize the profit of utilizing the rare and valuable supervised information in HNEs, we develop a novel Active Heterogeneous Network Embedding (ActiveHNE) framework, which includes two components: Discriminative Heterogeneous Network Embedding (DHNE) and Active Query in Heterogeneous Networks (AQHN). In DHNE, we introduce a novel semi-supervised heterogeneous network embedding method based on graph convolutional neural network. In AQHN, we first introduce three active selection strategies based on uncertainty and representativeness, and then derive a batch selection method that assembles these strategies using a multi-armed bandit mechanism. ActiveHNE aims at improving the performance of HNE by feeding the most valuable supervision obtained by AQHN into DHNE. Experiments on public datasets demonstrate the effectiveness of ActiveHNE and its advantage on reducing the query cost.