Search Results for author: Stephen Ra

Found 5 papers, 1 papers with code

Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling

1 code implementation7 Nov 2022 Romain Lopez, Nataša Tagasovska, Stephen Ra, Kyunghyn Cho, Jonathan K. Pritchard, Aviv Regev

Instead, recent methods propose to leverage non-stationary data, as well as the sparse mechanism shift assumption in order to learn disentangled representations with a causal semantic.

Disentanglement Domain Generalization +1

Multi-segment preserving sampling for deep manifold sampler

no code implementations9 May 2022 Daniel Berenberg, Jae Hyeon Lee, Simon Kelow, Ji Won Park, Andrew Watkins, Vladimir Gligorijević, Richard Bonneau, Stephen Ra, Kyunghyun Cho

We introduce an alternative approach to this guided sampling procedure, multi-segment preserving sampling, that enables the direct inclusion of domain-specific knowledge by designating preserved and non-preserved segments along the input sequence, thereby restricting variation to only select regions.

Language Modelling

Black Box Recursive Translations for Molecular Optimization

no code implementations21 Dec 2019 Farhan Damani, Vishnu Sresht, Stephen Ra

We call this method Black Box Recursive Translation (BBRT), a new inference method for molecular property optimization.

 Ranked #1 on Molecular Graph Generation on ZINC (QED Top-3 metric)

Drug Discovery Molecular Graph Generation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.