Node Attribute Generation on Graphs
This work addresses a domain-specific problem for researchers and practitioners in graph-based machine learning, offering a method to enhance data completeness for applications like profiling and data augmentation, but it is incremental as it builds on existing adversarial learning techniques.
The paper tackles the problem of missing or incomplete node attributes in graph-structured data, which can degrade performance in tasks like node classification and link prediction, by proposing a deep adversarial learning method called NANG that generates high-quality node attributes, as demonstrated through extensive experiments on four real-world datasets.
Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deteriorates the performance. The task of node attribute generation aims to generate attributes for those nodes whose attributes are completely unobserved. This task benefits many real-world problems like profiling, node classification and graph data augmentation. To tackle this task, we propose a deep adversarial learning based method to generate node attributes; called node attribute neural generator (NANG). NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities. We thus use this latent representation as a bridge to convert information from one modality to another. We further introduce practical applications to quantify the performance of node attribute generation. Extensive experiments are conducted on four real-world datasets and the empirical results show that node attributes generated by the proposed method are high-qualitative and beneficial to other applications. The datasets and codes are available online.