Methods › General › Regularization › Fraternal Dropout
Fraternal Dropout
Introduced by Konrad Zolna et al. in Fraternal Dropout
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Fraternal Dropout is a regularization method for recurrent neural networks that trains two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions. This encourages the representations of RNNs to be invariant to dropout mask, thus being robust.
Papers archive 2025-07-28
2 shown of 2, 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.
-
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization 28 Oct 2021 · 0 repositories · arXiv:2110.14945
-
Fraternal Dropout 31 Oct 2017 · 1 repository · arXiv:1711.00066
Tasks archive 2025-07-28
5 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 |
|---|---|
| Decoder | 1 |
| Image Captioning | 1 |
| Language Modeling | 1 |
| Language Modelling | 1 |
| Text Generation | 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