hiw3c 日报精选
arXiv cs.AI/CL/LG 网页快照

注意力作为格点规范理论:各种关系仅通过威尔逊环进行相互作用

原文标题 · Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops

作者:Aakash Sarkar, Ananya Mukherjee, Motoshige Sato | 关系是通过它们共有的实体来构建的——例如,Alice是Bob的母亲,而Bob则是Carol的父亲;因此,Alice同时也是Carol的祖母。这种关系的顺序非常重要,因为父亲的母亲并不等同于母亲的父亲。验证这种关系意味着要形成一个闭环。我们发现,如果每个实体的坐标系都可以独立旋转(即每个实体都有

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Computer Science > Machine Learning

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

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

Submission history

Access Paper:

Additional Features

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .