Quasi-equivariant metanetworks relax strict equivariance to preserve functional identity in weight-space learning while improving expressivity for feedforward, convolutional, and transformer networks.
Andreas M¨uller, Carlo Curino, and Raghu Ramakrishnan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quasi-Equivariant Metanetworks
Quasi-equivariant metanetworks relax strict equivariance to preserve functional identity in weight-space learning while improving expressivity for feedforward, convolutional, and transformer networks.