Link Polarity Prediction from Sparse and Noisy Labels via Multiscale Social Balance
This work addresses the challenge of noisy and sparse data in signed network analysis, which is incremental as it builds on existing SGNN methods with a novel integration of social balance theory.
The paper tackled the problem of predicting link polarities in signed networks when available labels are sparse and noisy, and the result was a semi-supervised framework that outperformed baseline models by incorporating multiscale social balance theory.
Signed Graph Neural Networks (SGNNs) have recently gained attention as an effective tool for several learning tasks on signed networks, i.e., graphs where edges have an associated polarity. One of these tasks is to predict the polarity of the links for which this information is missing, starting from the network structure and the other available polarities. However, when the available polarities are few and potentially noisy, such a task becomes challenging. In this work, we devise a semi-supervised learning framework that builds around the novel concept of \emph{multiscale social balance} to improve the prediction of link polarities in settings characterized by limited data quantity and quality. Our model-agnostic approach can seamlessly integrate with any SGNN architecture, dynamically reweighting the importance of each data sample while making strategic use of the structural information from unlabeled edges combined with social balance theory. Empirical validation demonstrates that our approach outperforms established baseline models, effectively addressing the limitations imposed by noisy and sparse data. This result underlines the benefits of incorporating multiscale social balance into SGNNs, opening new avenues for robust and accurate predictions in signed network analysis.