graph-transformer

X-LogSMask introduces a logarithmic structural mask for graph transformers, injecting graph topology directly into attention logits to achieve state-of-the-art performance on 13 out of 20 benchmarks while preserving interpretability and multi-hop information propagation.

This paper introduces RelGT-AC, a relational graph transformer architecture tailored for autocomplete tasks in relational databases. The model extends the RelGT architecture with column masking to prevent trivial solutions, a unified task head for multiple prediction types, and a TF-IDF text encoder to leverage lexical signals, achieving significant improvements over baselines on RelBench v2 benchmarks.