Node Duplication Improves Cold-start Link Prediction

arXiv:2402.09711v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) are prominent in graph machine learning and have shown state-of-the-art performance in Link Prediction (LP) tasks. Nonetheless, recent studies show that GNNs struggle to produce good results on low-degree nodes despite their overall strong performance. In practical applications of LP, like recommendation systems, improving performance on low-degree nodes is critical, as it amounts to tackling the cold-start problem of improving the experiences of users with few observed interactions. In this paper, …

abstract applications art arxiv cs.lg gnns good graph graph neural networks link prediction low machine machine learning networks neural networks node nodes performance practical prediction recommendation recommendation systems show state struggle studies systems tasks type