E(2) Equivariant Self-Attention for Radio Astronomy

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

mb010/equivariantselfattention — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work we introduce group-equivariant self-attention models to address the problem of explainable radio galaxy classification in astronomy. We evaluate various orders of both cyclic and dihedral equivariance, and show that including equivariance as a prior both reduces the number of epochs required to fit the data and results in improved performance. We highlight the benefits of equivariance when using self-attention as an explainable model and illustrate how equivariant models statistically attend the same features in their classifications as human astronomers.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2111.04742")
get_code_for_paper("2111.04742")
have("2111.04742")

Connect an agent — have() is free.