Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Domain Generalization via Nuclear Norm Regularization

About

The ability to generalize to unseen domains is crucial for machine learning systems deployed in the real world, especially when we only have data from limited training domains. In this paper, we propose a simple and effective regularization method based on the nuclear norm of the learned features for domain generalization. Intuitively, the proposed regularizer mitigates the impacts of environmental features and encourages learning domain-invariant features. Theoretically, we provide insights into why nuclear norm regularization is more effective compared to ERM and alternative regularization methods. Empirically, we conduct extensive experiments on both synthetic and real datasets. We show nuclear norm regularization achieves strong performance compared to baselines in a wide range of domain generalization tasks. Moreover, our regularizer is broadly applicable with various methods such as ERM and SWAD with consistently improved performance, e.g., 1.7% and 0.9% test accuracy improvements respectively on the DomainBed benchmark.

Zhenmei Shi, Yifei Ming, Ying Fan, Frederic Sala, Yingyu Liang• 2023

Related benchmarks

TaskDatasetResultRank
Air Quality RegressionAir Quality R-212 → R-69, NO2
Normalized MAE0.073
16
Domain AdaptationEEG Signals S33 → S00
RMSE (Normalized)0.18
8
Pollutant concentration estimationAir Quality R-69 → R-212 (NO2) (test)
Normalized RMSE10.2
8
Air Quality RegressionAir Quality R-212 → R-69, O3
Normalized MAE15.9
8
Air Quality RegressionAir Quality Average across Scenarios
Normalized MAE11.1
8
O3 estimationReal-Time Deployment R-212 -> R-69 (O3) (final 20% of target domain data (streaming simulation))
Normalized RMSE0.132
8
Pollutant concentration estimationAir Quality R-212 → R-69 (O3) (test)
Normalized RMSE0.184
8
Pollutant concentration estimationAir Quality R-212 → R-69 (NO2) (test)
Normalized RMSE0.146
8
Air Quality RegressionAir Quality R-69 → R-212, O3
MAE (Normalized)9.9
8
Pollutant concentration estimationAir Quality R-69 → R-212 (O3) (test)
Normalized RMSE0.124
8
Showing 10 of 10 rows

Other info

Follow for update