Single-Model Any-Subgroup Equivariance via Symmetric Positional Encodings
Name
goel-amgoel-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
602.48 KB
Format
Adobe PDF
Checksum (MD5)
e8b391a9accc6ea106d0c3e9d770c955
Author(s)
Goel, Abhinav
Advisor(s)
Jegelka, Stefanie
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
The inclusion of symmetries as an inductive bias, known as “equivariance”, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant architectures are usually highly constrained, designed for pre-chosen symmetries, and cannot be applied to datasets with different symmetries. This work constructs a single model that is simultaneously equivariant to several groups, by simply regulating a certain input feature. Starting with a permutation-equivariant base model respecting the full Sₙ symmetry group, we can obtain subgroup G ⊆ Sₙ equivariance by using a symmetry-breaking input that is G-symmetric. Under mild conditions, the resultant network is only G-equivariant. But finding an input with automorphism group exactly G is computationally hard, which can be overcome by relaxing exact symmetry breaking to approximate symmetry breaking. This is done by leveraging the notion of 2-closure to derive fast algorithms. This method is validated on symmetry selection, multitask, and transfer learning settings, demonstrating that a single network equivariant to multiple permutation subgroups outperforms both separate equivariant models or a single non-equivariant model.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
