Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?
This work addresses missing link prediction for graph-based tasks, but it appears incremental as it builds on existing graph transformer methods with new local features.
The paper tackled missing link prediction on the ogbl-citation2 dataset by introducing two local graph features called Circle Features, which enhanced a graph transformer model, achieving state-of-the-art performance.
In this paper, we introduce two local graph features for missing link prediction tasks on ogbl-citation2. We define the features as Circle Features, which are borrowed from the concept of circle of friends. We propose the detailed computing formulas for the above features. Firstly, we define the first circle feature as modified swing for common graph, which comes from bipartite graph. Secondly, we define the second circle feature as bridge, which indicates the importance of two nodes for different circle of friends. In addition, we firstly propose the above features as bias to enhance graph transformer neural network, such that graph self-attention mechanism can be improved. We implement a Circled Feature aware Graph transformer (CFG) model based on SIEG network, which utilizes a double tower structure to capture both global and local structure features. Experimental results show that CFG achieves the state-of-the-art performance on dataset ogbl-citation2.