AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Conditional Graph Information Bottleneck for Molecular Relational Learning

Namkyeong Lee, Dongmin Hyun, Gyoung S. Na, Sungwon Kim, Junseok Lee, Chanyoung Park

ICML 2023 · Graph learning › Graph self-supervised learning · approach: Molecular graph pretraining · 13 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
Use conditional compression conditioned on the paired graph instead of single-graph compression (ablation)CGIB · Chromophore Absorption and EmissionRMSEImproved
Use conditional compression rather than joint mutual-information compression of both graphs (ablation)CGIB · Chromophore Absorption and Emissionmodel performanceImproved
Add the paired-graph information-preservation term (ablation)CGIB · Chromophore Absorption and Emissionmodel performanceImproved
Use single-graph subgraph compression instead of no IB (ablation)relational learning model · Chromophore Absorption and Emissionmodel performanceImproved
Set beta to 1 for aggressive compression (ablation)CGIB · Emissionmodel performanceHurt
Set beta to 0 and remove information compression (ablation)CGIB · Emissionmodel performanceHurt
Add minimization of mutual information between the target and the paired graph (ablation)CGIB · Molecular interaction predictionmodel performanceHurt
Use asymmetric loss with the task-critical molecule as G1 rather than symmetric loss (ablation)CGIB · Chromophore AbsorptionRMSE: 21.11 -> 17.84Improved
Use asymmetric loss rather than symmetric loss (ablation)CGIB · Chromophore EmissionRMSE: 25.49 -> 24.44Improved
Use asymmetric loss rather than symmetric loss (ablation)CGIB · Chromophore LifetimeRMSE: 0.798 -> 0.796Improved
Use contrastive learning instead of the variational IB-based paired-graph term (ablation)CGIB · FreeSolvRMSE: 0.831 -> 0.852Hurt
Use contrastive learning instead of the variational IB-based paired-graph term (ablation)CGIB · ZhangDDI transductiveAUROC: 94.74 -> 93.78Hurt

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