cs.LGOct 27, 2026

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

Authors: Aakash Sarkar, Ananya Mukherjee, Motoshige Sato

Organizations: University of California, San Francisco · Brigham and Women’s Hospital

Abstract

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=TijTjkTkiH = T_{ij} T_{jk} T_{ki} - a Wilson loop. And the only equivariant update of an edge is U=Ψ(H) TijU = Ψ(H)\, T_{ij} with ΨΨ 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 S4S_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.

Figures & tables

Explore similar work

CardsList
  1. When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index

    Aug 3, 2026Kleyton da Costa, Bernardo ModenesiGraph Attention NetworksAttention Mechanisms

  2. Emergent Loop Geometry in Gauge-Equivariant Graph Neural Networks

    Oct 13, 2026Ali Rayat, Gia-Wei ChernEquivariant GNNsGNN Expressivity

  3. Gauge-Equivariant Graph Neural Networks for Lattice Gauge Theories

    Apr 22, 2026Ali Rayat, Yaohang Li, Gia-Wei ChernMessage Passing Neural NetworksHigh-Energy Physics