Node Duplication Improves Cold-start Link Prediction
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, we investigate improving GNNs' LP performance on low-degree nodes while preserving their performance on high-degree nodes and propose a simple yet surprisingly effective augmentation technique called NodeDup. Specifically, NodeDup duplicates low-degree nodes and creates links between nodes and their own duplicates before following the standard supervised LP training scheme. By leveraging a ``multi-view'' perspective for low-degree nodes, NodeDup shows significant LP performance improvements on low-degree nodes without compromising any performance on high-degree nodes. Additionally, as a plug-and-play augmentation module, NodeDup can be easily applied on existing GNNs with very light computational cost. Extensive experiments show that NodeDup achieves 38.49%, 13.34%, and 6.76% relative improvements on isolated, low-degree, and warm nodes, respectively, on average across all datasets compared to GNNs and the existing cold-start methods.
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=uNXGo3Tgdy
Changes Since Last Submission: This paper was desk-rejected due to the use of an incorrect font. We have now updated it to the correct font style and refined the main content.
Assigned Action Editor: ~Olgica_Milenkovic1
Submission Number: 4459
Loading