ColdExpand: Semi-Supervised Graph Learning in Cold Start
Most real-world graphs are dynamic and eventually face the cold start problem. A fundamental question is how the new cold nodes acquire initial information in order to be adapted in to the existing graph. Here we propose a method that utilizes the deep autoencoding principle to extract structural information from the existing graph. In particular, we apply graph convolutional networks to solve the ”Expanded Semi-Supervised Graph Learning” problem in cold start situations. The proposed ColdExpand model classifies the cold nodes based on link prediction with multiple goals to tackle. We experimentally prove that by adding additional goal to existing link prediction method, our method outperforms the baseline in both expanded semi-supervised link prediction(at most 24%) and node classification tasks(at most 15%).To the best of our knowledge this is the first study to address expansion of the semi-supervised learning to unseen nodes.
PDF Abstract
