Semi-supervised Node Classification via Adaptive Graph Smoothing Networks

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations



Original languageEnglish
Article number108492
Journal / PublicationPattern Recognition
Online published11 Dec 2021
Publication statusPublished - Apr 2022
Externally publishedYes


Inspections on current graph neural networks suggest us to reconsider the computational aspect of the final aggregation. We consider that such aggregations perform a prediction smoothing and impute their potential drawbacks to be the inter-class interference implied by the underlying graphs. We aim at weakening the inter-class connections so that aggregations focus more on intra-class relations and producing smooth predictions according to weakening results. We apply a metric learning module to learn new edge weights and combine entropy losses to ensure the correspondence between the predictions and the learnt distances so that the weights of inter-class edges are reduced and predictions are smoothed according to the modified graph. Experiments on four citation networks and a Wiki network show that in comparison with other state-of-the-art graph neural networks, the proposed algorithm can improve the classification accuracy.

Research Area(s)

  • Adaptive graph smoothing networks, Graph convolutional networks, Semi-supervised learning, Graph node classification