AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

ATD: Augmenting CP Tensor Decomposition by Self Supervision

Chaoqi Yang, Cheng Qian, Navjot Singh, Cao Xiao, M Brandon Westover, Edgar Solomonik, Jimeng Sun

NeurIPS 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 6 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
Add the self-supervised alignment loss to tensor decomposition (ablation)ATD · Sleep-EDFaccuracy: 84.19 ± 0.221 -> 85.01 ± 0.224Improved
Add the self-supervised alignment loss to tensor decomposition (ablation)ATD · HARaccuracy: 92.41 ± 0.391 -> 93.35 ± 0.357Improved
Add the self-supervised alignment loss to tensor decomposition (ablation)ATD · PTB-XLaccuracy: 69.38 ± 0.612 -> 70.26 ± 0.523Improved
Add the self-supervised alignment loss to tensor decomposition (ablation)ATD · MGHaccuracy: 72.78 ± 0.522 -> 74.15 ± 0.431Improved
Use two iterative-rule rounds instead of one (ablation)ATD · HARaccuracy: 93.30 ± 0.413 -> 93.35 ± 0.172No clear effect
Use two iterative-rule rounds instead of one (ablation)ATD · Sleep-EDFaccuracy: 85.25 ± 0.209 -> 85.33 ± 0.173No clear effect
Use more diverse augmentation methods (ablation)ATD · MGH Sleepaccuracy: 72.53 ± 0.652 -> 74.15 ± 0.203Improved
Combine jittering, bandpass filtering, and 3D position rotation rather than use one augmentation (ablation)ATD · HARaccuracy: 92.06 ± 0.621 -> 93.35 ± 0.357Improved
Increase decomposition rank from R=8 to R=64 (ablation)ATD · HARaccuracy: 71.91 ± 0.253 -> 93.43 ± 0.411Improved
Increase decomposition rank from R=64 to R=128 (ablation)ATD · HARaccuracy: 93.43 ± 0.411 -> 92.97 ± 0.273Hurt
Increase decomposition rank from R=8 to R=128 (ablation)ATD · Sleep-EDFaccuracy: 82.49 ± 0.464 -> 85.32 ± 0.305Improved
Use increasingly unrealistic jittering noise (ablation)ATD · MGHaccuracy: 74.18 ± 0.326 -> 72.18 ± 0.676Hurt

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