AI Paper Atlas

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

RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks

Jinsung Yoon, James Jordon, Mihaela Schaar

ICML 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 11 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
Use RadialGAN translations from other datasets to augment the target training dataTarget-specific predictive models on MAGGIC · MAGGIC, M=3, 5, and 7AUC gain over Target-only: M=3: .0154$\pm$.0091; M=5: .0292$\pm$.0009; M=7: .0297$\pm$.0071Improved
Use RadialGAN translations from other datasets to augment the target training dataTarget-specific predictive models on MAGGIC · MAGGIC, M=3, 5, and 7APR gain over Target-only: M=3: .0243$\pm$.0096; M=5: .0310$\pm$.0096; M=7: .0287$\pm$.0073Improved
Increase the number of datasets used from M=3 to M=7 (ablation)RadialGAN · MAGGICAUC gain over Target-only: .0154$\pm$.0091 -> .0297$\pm$.0071Improved
Increase the number of datasets used from M=3 to M=7 (ablation)RadialGAN · MAGGICAPR gain over Target-only: .0243$\pm$.0096 -> .0287$\pm$.0073Mixed
Augment with samples generated by a GAN trained only on the target datasetTarget-only predictive model · MAGGIC studiesPrediction gainHurt
Use RadialGAN instead of target-only GAN to generate additional training samplesTarget-specific predictive model · MAGGIC studiesPrediction gainImproved
Use RadialGAN when feature mismatch is absent (ablation)Target-specific predictive model · MAGGIC, Setting AAUC gain over Target-only: .0169Improved
Use RadialGAN when distribution mismatch is absent (ablation)Target-specific predictive model · MAGGIC, Setting BAUC gain over Target-only: .0313Improved
Use a pairwise translation method that does not address distribution mismatchTarget-specific predictive model · MAGGIC, Setting BAUC gain over Target-only: .0249Improved
Use StarGAN, which does not naturally address feature mismatch, in the no-distribution-mismatch settingTarget-specific predictive model · MAGGIC, Setting BAUC gain over Target-only: .0020Hurt

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