E(2) Equivariant Self-Attention for Radio Astronomy
This work addresses the need for explainable AI in astronomy, specifically for radio galaxy classification, though it is incremental as it applies existing equivariance concepts to self-attention in a domain-specific context.
The paper tackled the problem of explainable radio galaxy classification in astronomy by introducing group-equivariant self-attention models, resulting in reduced training epochs and improved performance, with equivariant models attending to the same features as human astronomers.
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.