标签
本文介绍了Graph Machine，一种通过动态指针将Transformer中的密集注意力层替换为稀疏层的方法，从而在预训练期间提高效率并保持或增强性能。
This paper introduces Graph Machine, an architecture with explicit edge-based mechanisms (edge-augmented attention and edge-centric referral) to improve iterative relational reasoning. Experiments on Sudoku show it outperforms Transformer baselines, with ablations and mechanistic analysis attributing gains to the edge mechanisms.