Papers › Fraternal Dropout
Fraternal Dropout
Konrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio
Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem. In this paper we propose a simple technique called fraternal dropout that takes advantage of dropout to achieve this goal. Specifically, we propose to train two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions. In this way our regularization encourages the representations of RNNs to be invariant to dropout mask, thus being robust. We show that our regularization term is upper bounded by the expectation-linear dropout objective which has been shown to address the gap due to the difference between the train and inference phases of dropout. We evaluate our model and achieve state-of-the-art results in sequence modeling tasks on two benchmark datasets - Penn Treebank and Wikitext-2. We also show that our approach leads to performance improvement by a significant margin in image captioning (Microsoft COCO) and semi-supervised (CIFAR-10) tasks.
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 |
|---|---|---|---|---|---|---|---|
| Language Modelling | Penn Treebank (Word Level) | AWD-LSTM 3-layer with Fraternal dropout | Params | 24M | #28 of 43 | Archive leaderboard | report |
| Language Modelling | Penn Treebank (Word Level) | AWD-LSTM 3-layer with Fraternal dropout | Test perplexity | 56.8 | #28 of 43 | Archive leaderboard | report |
| Language Modelling | Penn Treebank (Word Level) | AWD-LSTM 3-layer with Fraternal dropout | Validation perplexity | 58.9 | #28 of 43 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM 3-layer with Fraternal dropout | Number of params | 34M | #29 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM 3-layer with Fraternal dropout | Test perplexity | 64.1 | #29 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM 3-layer with Fraternal dropout | Validation perplexity | 66.8 | #29 of 38 | 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.
Methods
Introduced by this paper: Fraternal Dropout
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