AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations

Rong Hu, Ling Chen

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 0 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 mode-based CMI with iterative mode discovery and meta-coordination (CoDID) vs best DRL baselineCoDID · seven datasetsaccuracy: average +7.8% accuracy, +7.9% macro F1Improved
add mode prediction loss and discrimination loss (ablation)CoDID-km · CMNIST test 3accuracy: 74.2 -> 79.0 (mode prediction); 73.0 -> 79.0 (discrimination)Improved
share discriminator parameters among modes under the same attribute value (ablation)CoDID-km · CMNIST test 3accuracy: 77.1 -> 79.0 (vs individual); 76.3 -> 79.0 (vs one shared)Improved
naive iterative clustering (k-means or DPGMM) during DRL instead of fixed clustering (ablation)CoDID-km · CMNIST test 3accuracy: 79.0 -> 76.5 (itkm); 79.0 -> 77.6 (itdpm)Hurt
add weighted CMI minimization (meta-learned weights) (ablation)CoDID-itdpm · CMNIST test 3accuracy: 77.6 -> 79.1Improved
add subcluster net with weight alignment loss for cluster splits (ablation)CoDID-w/o-SC · CMNIST test 3accuracy: 79.1 -> 85.2Improved
add partial network reconfiguration when number of clusters changes (ablation)CoDID-UA · CMNIST test 3accuracy: 82.0 -> 85.2Improved
use subcluster net instead of DPGMM subclustering (ablation)CoDID · CMNIST subclusteringsubcluster accuracy: 0.678 -> 0.892Improved
mode-based CMI with true mode labels vs attribute-based CMIA-CMI · Toy data test 3a1 accuracy: 0.669 -> 0.926Improved
invariance/independence baselines vs plain supervised learningBASE · CMNIST test 3accuracy: 79.2 -> 58.5 (A-CMI)Hurt
CoDID-itkm and CoDID-km on image data despite ground-truth mode count (ablation)CoDID · image datasetsaccuracy: CMNIST 79.0 -> 85.2 (vs CoDID-km)Improved

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