AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning

Alex Chan, Mihaela van der Schaar

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 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 separation and connection losses to the reconstruction-only representation learning (ablation)SMC · MNIST (ten single-digit classifiers)OneVsRest AUROC: 0.969 -> 0.972Improved
Provide only 3 feature samples per model instead of noneSMC · MNISTAUROC: 0.50 -> 0.83Improved
Provide all training features instead of few samplesSMC · MNISTAUROC: 0.83 -> 0.97Improved
Add representation learning step before density estimation (ablation)SMC · MNISTtest point coverageImproved
Use instance-wise SMC instead of a global ensembleSMC · Sin-wave regression with disjoint training domainsprediction accuracyImproved
Make model training domains fully overlapSMC · Sin-wave regressionprediction accuracy vs global ensemblesNo clear effect
Move model training domains further apart (centred at 0 and 20)SMC · Sin-wave regressionprediction accuracy in uncovered regionHurt
Replace global model averaging with SMCSMC · Vancomycin AUC, four observationsrelative RMSE: 16.6% -> 12.8%Improved
Replace global model averaging with SMCSMC · Vancomycin AUC, a priorirelative RMSE: 41.8% -> 55.7%Hurt
Increase number of concentration observations from 0 to 4SMC · Vancomycin AUCrelative RMSE: 41.8% -> 12.8%Improved
Include models with very poor performance in the pool (high performance variability)SMC · Vancomycin AUC a priorirelative RMSE: 32.7 -> 83.3Hurt
Increase weight of connection and separation losses within about 2.5% of reconstruction loss (ablation)SMC networks · MNIST representationprediction performanceImproved

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