AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Unsupervised Manifold Alignment with Joint Multidimensional Scaling

Dexiong Chen, Bowen Fan, Carlos Oliver, Karsten Borgwardt

ICLR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 3 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
Increase embedding dimension from d=2 to d=16 (ablation)Joint MDS · Bifurcation, Swiss roll, Circular frustum, SNAREseq, scGEMFOSCTTM: 11.15 -> 7.56; 0.96 -> 0.58; 0.90 -> 0.87; 17.18 -> 15.59; 20.42 -> 18.54Improved
Increase embedding dimension from d=2 to d=16 (ablation)Joint MDS · Bifurcationclassification accuracy: 96.0 -> 96.7Improved
Increase embedding dimension from d=2 to d=16 (ablation)Joint MDS · Swiss rollclassification accuracy: 99.3 -> 99.3No clear effect
Increase embedding dimension from d=2 to d=16 (ablation)Joint MDS · Circular frustum, SNAREseq, scGEM, MNIST-USPSclassification accuracy: 94.0 -> 94.7; 85.5 -> 94.7; 64.4 -> 72.9; 15.0 -> 60.2Improved
Use Joint MDS with d=16 rather than the strongest listed baselineJoint MDS · Bifurcation, Swiss roll, scGEM, MNIST-USPSclassification accuracy: 96.7 vs 95.7; 99.3 vs 99.3; 72.9 vs 62.7; 60.2 vs 43.1Improved
Use Joint MDS with d=16 rather than the strongest listed baselineJoint MDS · Circular frustum, SNAREseqclassification accuracy: 94.7 vs 95.7; 94.7 vs 98.2Hurt
Use Joint MDS instead of the strongest listed baselineJoint MDS · PPI 5%, MIMIC-III top 3node correctness / accuracy: 84.31 -> 86.44$\pm$0.33; 27.98 -> 30.24$\pm$1.66Improved
Use Joint MDS instead of the strongest listed baselineJoint MDS · PPI 15%, PPI 25%, MIMIC-III top 5node correctness / accuracy: 72.31$\pm$0.62 vs 74.35; 55.3$\pm$0.78 vs 67.42; 46.28$\pm$1.51 vs 47.86Hurt

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