How Graph Structure and Label Dependencies Contribute to Node Classification in a Large Network of Documents
This work provides insights for semi-supervised classification in document networks, though it appears incremental in evaluating known information sources.
The researchers investigated how article content, network connections, and label correlations affect node classification in Wikipedia articles, finding that label dependencies matter more when training data is sparse.
We introduce a new dataset named WikiVitals which contains a large graph of 48k mutually referred Wikipedia articles classified into 32 categories and connected by 2.3M edges. Our aim is to rigorously evaluate the contributions of three distinct sources of information to the label prediction in a semi-supervised node classification setting, namely the content of the articles, their connections with each other and the correlations among their labels. We perform this evaluation using a Graph Markov Neural Network which provides a theoretically principled model for this task and we conduct a detailed evaluation of the contributions of each sources of information using a clear separation of model selection and model assessment. One interesting observation is that including the effect of label dependencies is more relevant for sparse train sets than it is for dense train sets.