PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
BeginnerPanagiotis Koromilas, Andreas D. Demou et al.Feb 1arXiv
PolySAE is a new kind of sparse autoencoder that keeps a simple, linear way to find features but uses a smarter decoder that can multiply features together.
#Sparse Autoencoder#Polynomial Decoder#Feature Interactions