AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Geometry Based Data Generation

Ofir Lindenbaum, Jay Stanley, Guy Wolf, Smita Krishnaswamy

NeurIPS 2018 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 20 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Apply SUGAR augmentation before k-NN classificationk-NN · 60 imbalanced datasetsACP: 0.67 -> 0.78Improved
Apply SUGAR augmentation before k-NN classificationk-NN · 60 imbalanced datasetsACR: 0.64 -> 0.77Improved
Apply SUGAR augmentation before kernel SVM classificationkernel SVM · 60 imbalanced datasetsACR: 0.78 -> 0.84Improved
Apply SUGAR augmentation before kernel SVM classificationkernel SVM · 60 imbalanced datasetsACP: 0.77 -> 0.77No clear effect
Apply SUGAR to unevenly sampled manifold dataSwiss roll · Swiss rolldegree variance: 0.19 -> 0.09Improved
Apply SUGAR to unevenly sampled manifold dataStanford Bunny · Stanford Bunnydegree variance: 0.24 -> 0.019Improved
Use SUGAR to augment density-biased data before clusteringk-means · 115 imbalanced datasetsRand IndexImproved
Generate manifold samples using SUGAR rather than a VAEMNIST rotated handwritten 6 · MNIST rotated handwritten 6coverage of sparse manifold anglesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy