Hubness Reduction Improves Sentence-BERT Semantic Spaces

1 code implementation • 30 Nov 2023 • Beatrix M. G. Nielsen, Lars Kai Hansen

We find that when hubness is high, we can reduce error rate and hubness using hubness reduction methods.

Information Retrieval Retrieval +1

DiffEnc: Variational Diffusion with a Learned Encoder

1 code implementation • 30 Oct 2023 • Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi, Ole Winther

Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms over the hierarchy.