Papers › Equivariance Through Parameter-Sharing

Equivariance Through Parameter-Sharing

27 Feb 2017ICML 2017 8arXiv:1702.08389archive 2025-07-28

Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos

We propose to study equivariance in deep neural networks through parameter symmetries. In particular, given a group 𝒢 that acts discretely on the input and output of a standard neural network layer ϕ_W: ᴹ →ᴺ, we show that ϕ_W is equivariant with respect to 𝒢-action iff 𝒢 explains the symmetries of the network parameters W. Inspired by this observation, we then propose two parameter-sharing schemes to induce the desirable symmetry on W. Our procedures for tying the parameters achieve 𝒢-equivariance and, under some conditions on the action of 𝒢, they guarantee sensitivity to all other permutation groups outside 𝒢.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

raymondyeh07/chirality_nets mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Sensitivity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections