AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Unsupervised Learning of Equivariant Structure from Sequences

Takeru Miyato, Masanori Koyama, Kenji Fukumizu

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
Train an encoder-decoder to predict held-out future frames using a per-sequence linear latent transitionSequential MNIST and Sequential MNIST-bg · Sequential MNIST and Sequential MNIST-bgprediction qualityImproved
Use per-sequence neural transitions instead of a fitted linear latent transition (ablation)MSP · Sequential MNIST, extrapolationprediction qualityHurt
Predict M* with a neural network rather than optimize it internally for each sequence (ablation)MSP · Sequential MNIST, equivarianceequivariance errorHurt
Constrain the latent transition to fixed 2x2 blocks (ablation)MSP · Sequential MNIST, extrapolationprediction qualityHurt
Train on reconstruction within the conditional sequence rather than held-out future frames (ablation)MSP · Sequential MNIST, learned representationrepresentation qualityHurt
Use a learned nonlinear neural transition instead of a linear latent transition (ablation)MSP · Sequential MNIST, extrapolationprediction qualityHurt
Extend the transition model to second order to represent acceleration (ablation)Constant-velocity MSP · Accelerated Sequential MNISTprediction qualityImproved
Apply constant-velocity prediction to sequences with constant acceleration (ablation)MSP · Accelerated Sequential MNISTprediction qualityHurt
Apply MSP to rendered 3D rotations with potentially non-invertible transitionsMSP · Sequential ShapeNetprediction qualityHurt

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