1.1k citations · 2.3k across the 10 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 1 cited
PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations
Han Gao, Xu Han, Jiaoyang Huang +2
Recently the Transformer structure has shown good performances in graph learning tasks. However, these Transformer models directly work on graph nodes and may have difficulties lea…
cs.LG2022★ 11 cited
Predicting Physics in Mesh-reduced Space with Temporal Attention
Xu Han, Han Gao, Tobias Pfaff +2
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short te…