AI Paper Atlas

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

Improving Multi-Task Generalization via Regularizing Spurious Correlation

Ziniu Hu, Zhe Zhao, Xinyang Yi, Tiansheng Yao, Lichan Hong, Yizhou Sun, Ed H. Chi

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 13 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 MT-CRL with G-IRM VarMMoE multi-task learning · Multi-MNIST, MovieLens, Taskonomy, CityScape, NYUv2average relative performance improvement: +5.5%Improved
Remove G-IRM invariance regularization (ablation)MT-CRL · Multi-MNIST, MovieLens, Taskonomy, CityScape, NYUv2average relative performance improvement: +5.5% -> +3.0%Hurt
Use G-IRM Var instead of G-IRM Norm (ablation)MT-CRL · Multi-MNIST, MovieLens, Taskonomy, CityScape, NYUv2average relative performance improvement: +5.2% -> +5.5%Improved
Add decorrelation regularization (ablation)MT-CRL · Multi-MNISTaccuracy: 0.882 -> 0.915Improved
Replace decorrelation regularization with β-VAE (ablation)MT-CRL · Multi-MNISTaccuracy: 0.915 -> 0.896Hurt
Add sparsity and balance graph regularization (ablation)MT-CRL · Multi-MNISTaccuracy: 0.891 -> 0.915Improved
Vary module count from K=1 to K=8 (ablation)MT-CRL · Multi-MNISTaccuracy: 0.824 -> 0.915Improved
Increase module count from K=8 to K=128 (ablation)MT-CRL · Multi-MNISTaccuracy: 0.915 -> 0.882Hurt
Train jointly with MTL rather than separately with STLshared-bottom model · Multi-SEMvalidation accuracy: MTL 0.846; STL 0.874Hurt
Train jointly with MTL rather than separately with STLshared-bottom model · Multi-MNISTvalidation accuracyHurt

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