Papers › Global-Local Regularization Via Distributional Robustness
Global-Local Regularization Via Distributional Robustness
Hoang Phan, Trung Le, Trung Phung, Tuan Anh Bui, Nhat Ho, Dinh Phung
Despite superior performance in many situations, deep neural networks are often vulnerable to adversarial examples and distribution shifts, limiting model generalization ability in real-world applications. To alleviate these problems, recent approaches leverage distributional robustness optimization (DRO) to find the most challenging distribution, and then minimize loss function over this most challenging distribution. Regardless of achieving some improvements, these DRO approaches have some obvious limitations. First, they purely focus on local regularization to strengthen model robustness, missing a global regularization effect which is useful in many real-world applications (e.g., domain adaptation, domain generalization, and adversarial machine learning). Second, the loss functions in the existing DRO approaches operate in only the most challenging distribution, hence decouple with the original distribution, leading to a restrictive modeling capability. In this paper, we propose a novel regularization technique, following the veins of Wasserstein-based DRO framework. Specifically, we define a particular joint distribution and Wasserstein-based uncertainty, allowing us to couple the original and most challenging distributions for enhancing modeling capability and applying both local and global regularizations. Empirical studies on different learning problems demonstrate that our proposed approach significantly outperforms the existing regularization approaches in various domains: semi-supervised learning, domain adaptation, domain generalization, and adversarial machine learning.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Adversarial Robustness | CIFAR-10 | GLOT-DR | Accuracy | 84.13 | #4 of 5 | Archive leaderboard | report |
| Adversarial Robustness | CIFAR-10 | GLOT-DR | Attack: AutoAttack | 49.94 | #4 of 5 | Archive leaderboard | report |
| Domain Adaptation | ImageCLEF-DA | GLOT-DR | Accuracy | 90.4 | #3 of 17 | Archive leaderboard | report |
| Domain Adaptation | Office-31 | GLOT-DR | Average Accuracy | 87.8 | #24 of 40 | Archive leaderboard | report |
| Domain Generalization | CIFAR-100C | GLOT-DR | Accuracy | 58.4 | #1 of 1 | Archive leaderboard | report |
| Domain Generalization | CIFAR-10C | GLOT-DR | Accuracy | 84.5 | #1 of 1 | Archive leaderboard | report |
| Domain Generalization | PACS | GLOT-DR | Average Accuracy | 73.5 | #109 of 133 | Archive leaderboard | report |
| Semi-Supervised Image Classification | CIFAR-10, 4000 Labels | GLOT-DR | Percentage error | 10.6 | #42 of 49 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections