Methods › General › Regularization › LVR
Low Variance Regularization
LVR
Introduced by Shahed Masoudian et al. in Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Method introduces a novel unlabeled debiasing technique which works on classification task to reduce the bias of the transformer based language models on downstream classification task. In their method authors use the classes as metric for regularization and punish the network if the embedding produced by the model are far from each other. by doing so the authors claim to be able to reduce the domain shift caused by any unwanted attribute information hence results in fair embedding.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Loss-Versus-Rebalancing under Deterministic and Generalized block-times 8 May 2025 · 0 repositories · arXiv:2505.05113
-
Impermanent loss and Loss-vs-Rebalancing II 6 Feb 2025 · 0 repositories · arXiv:2502.04097
-
Impermanent loss and loss-vs-rebalancing I: some statistical properties 1 Oct 2024 · 0 repositories · arXiv:2410.00854
-
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization 29 Sep 2024 · 0 repositories · arXiv:2409.19541
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Attribute | 1 |
| Language Modeling | 1 |
| Language Modelling | 1 |
| Sentence | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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