Search Results for author:
Found 3 papers, 3 papers with code
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
Ranked #1 on
Drug Discovery
on LIT-PCBA(KAT2A)
The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles
However, the dynamic (i. e., input-dependent) nature of these pathways makes it difficult to prune dense self-attention during training.
Ranked #12 on
Graph Regression
on PCQM4Mv2-LSC
Global Self-Attention as a Replacement for Graph Convolution
The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data.
Ranked #1 on
Graph Regression
on PCQM4Mv2-LSC
