GRPE: Relative Positional Encoding for Graph Transformer. (arXiv:2201.12787v3 [cs.LG] UPDATED)

We propose a novel positional encoding for learning graph on Transformer
architecture. Existing approaches either linearize a graph to encode absolute
position in the sequence of nodes, or encode relative position with another
node using bias terms. The former loses preciseness of relative position from
linearization, while the latter loses a tight integration of node-edge and
node-topology interaction. To overcome the weakness of the previous approaches,
our method encodes a graph without linearization and considers both
node-topology and node-edge interaction. …

arxiv encoding graph positional encoding transformer