论文

Attention as Lattice Gauge Theory:关系只通过 Wilson Loop 交互

Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops

精选理由

这篇论文把 AlphaFold 的三角更新和格点 QCD 用同一个 Wilson Loop 框架串起来了,数学上挺漂亮,做关系推理和图模型的值得看看推导。

一篇 arXiv 论文提出把注意力机制解释为格点规范场论。核心结论是:在每实体坐标系可独立旋转的规范自由下,关系的唯一规范不变评分是 Wilson Loop(三角形的 holonomy H = T_ij T_jk T_ki)。论文将 AlphaFold 的三角更新、Edge Transformer、知识图谱的交换算子嵌入和格点 QCD 统一在这一框架下。作者实现的 holonomy attention 无需训练即可在 20% 边被破坏的稀疏图上以 0.88 的准确率推断未观测的 S_4 关系,而所有交换性架构上限为 0.083;其 holonomy 评分检测损坏三角形的 AUC 达 0.99,交换性评分上限为 0.76。

原文 · arXiv cs.AI

Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops

Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation means closing the loop. We show that if each entity's coordinate frame may be rotated independently (per-entity frame freedom), three things follow. In the pure-gauge sector, relations that share no cycle cannot interact at all. The only gauge-invariant score of a triangle is a class function of its holonomy $H = T_{ij} T_{jk} T_{ki}$ - a Wilson loop. And the only equivariant update of an edge is $U = Ψ(H)\, T_{ij}$ with $Ψ$ conjugation-equivariant. Edge attention by Wilson loops is therefore not one design among many but the unique form the symmetry permits. Three communities hold pieces of this form: the commuting-operator embeddings of knowledge graphs are its abelian (commuting) sector; AlphaFold's triangle update and the Edge Transformer have its shape - an edge updated through the third vertex - without its constraints; and lattice QCD builds it equivariantly on lattices. We instantiate the equivariant sub-family on general relational graphs as holonomy attention. With no training and composition alone, it infers unobserved $S_4$ relations on sparse graphs at 0.88 with a fifth of the edges corrupted, at or slightly below specialist synchronization algorithms, where every commutative architecture is capped at 0.083; its holonomy score flags corrupted triangles at AUC 0.99 where commuting scores are capped at 0.76 by a second selection rule, and it separates clusters without labels.