Poster
Pure Transformers are Powerful Graph Learners
Jinwoo Kim · Dat Nguyen · Seonwoo Min · Sungjun Cho · Moontae Lee · Honglak Lee · Seunghoon Hong
Hall J (level 1) #438
Keywords: [ permutation equivariance ] [ self-attention ] [ graph ] [ transformer ] [ graph positional embedding ] [ Graph neural network ] [ equivariant neural network ] [ Graph Transformer ]
We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent tokens, augment them with token embeddings, and feed them to a Transformer. With an appropriate choice of token embeddings, we prove that this approach is theoretically at least as expressive as an invariant graph network (2-IGN) composed of equivariant linear layers, which is already more expressive than all message-passing Graph Neural Networks (GNN). When trained on a large-scale graph dataset (PCQM4Mv2), our method coined Tokenized Graph Transformer (TokenGT) achieves significantly better results compared to GNN baselines and competitive results compared to Transformer variants with sophisticated graph-specific inductive bias. Our implementation is available at https://github.com/jw9730/tokengt.