GTLP: A graph transformer based link prediction framework with unified feature pre-processing

Abstract

In the realm of graph representation learning, Graph Neural Networks (GNNs) have demonstrated exceptional efficacy across diverse tasks. Typically, GNNs employ message-passing schemes to disseminate node features along graph structures, culminating in learned graph representations. However, their heavy reliance on smoothed node features over graph structures, coupled with limited expressiveness in the presence of node attributes, often constrains link prediction performance. To surmount this challenge, we propose GTLP, a Graph Transformer based link prediction framework. GTLP integrates unsupervised GNNs and structure encoding, enabling a holistic consideration of both topological structures and node features. This approach preserves critical node location and role information, enhancing the model’s expressiveness. By introducing the Graph Transformer model, GTLP adeptly incorporates neighbor information, refining embedding quality and bolstering the model’s learning and generalization capabilities. Notably, our method exhibits superior scalability, accommodating diverse techniques for information extraction, embedding learning, and sampling. Experimental results underscore GTLP’s state-of-the-art performance, outpacing various baselines across five real-world datasets.