Methods › General › Regularization › Adaptive Dropout
Adaptive Dropout
Introduced by Jimmy Ba et al. in Adaptive dropout for training deep neural networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Adaptive Dropout is a regularization technique that extends dropout by allowing the dropout probability to be different for different units. The intuition is that there may be hidden units that can individually make confident predictions for the presence or absence of an important feature or combination of features. Dropout will ignore this confidence and drop the unit out 50% of the time.
Denote the activity of unit j in a deep neural network by aⱼ and assume that its inputs are {aᵢ: i < j}. In dropout, aⱼ is randomly set to zero with probability 0.5. Let mⱼ be a binary variable that is used to mask, the activity aⱼ, so that its value is:
aⱼ = mⱼg ( ∑_(i: i<j)w_(j, i)aᵢ )
where w_(j,i) is the weight from unit i to unit j and g(·) is the activation function and a₀ = 1 accounts for biases. Whereas in standard dropout, mⱼ is Bernoulli with probability 0.5, adaptive dropout uses adaptive dropout probabilities that depends on input activities:
P(mⱼ = 1|{aᵢ: i < j}) = f ( ∑_(i: i<j)π_(j, i)aᵢ )
where π_(j, i) is the weight from unit i to unit j in the standout network or the adaptive dropout network; f(·) is a sigmoidal function. Here 'standout' refers to a binary belief network is that is overlaid on a neural network as part of the overall regularization technique.
In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2506.12738) is about this method is not checked.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Gradient Sign Dropout · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Gradient Sign Dropout')
Origin paper of this answer, arXiv:2506.12738 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 15 · with a code link: 3 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 15 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 15 of 15, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout 14 Jul 2025 · 0 repositories · arXiv:2507.10430
-
A statistical physics framework for optimal learning 10 Jul 2025 · 0 repositories · arXiv:2507.07907
-
DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation 7 May 2025 · 0 repositories · arXiv:2505.04175
-
Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection 12 Mar 2025 · 0 repositories · arXiv:2503.08974
-
Dynamic DropConnect: Enhancing Neural Network Robustness through Adaptive Edge Dropping Strategies 27 Feb 2025 · 1 repository · arXiv:2502.19948
-
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings 23 Jan 2025 · 0 repositories · arXiv:2501.13758
-
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution 1 Jan 2025 · 0 repositories
-
Adaptive Dropout for Pruning Conformers 6 Dec 2024 · 0 repositories · arXiv:2412.04836
-
Communication-Efficient Split Learning via Adaptive Feature-Wise Compression 20 Jul 2023 · 0 repositories · arXiv:2307.10805
-
FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout 14 Jul 2023 · 0 repositories · arXiv:2307.07172
-
The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization 14 Jun 2021 · 1 repository · arXiv:2106.07769Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization 11 Oct 2020 · 1 repository · arXiv:2010.05244
-
Adaptive Low-Rank Factorization to regularize shallow and deep neural networks 5 May 2020 · 0 repositories · arXiv:2005.01995
-
Improved Dropout for Shallow and Deep Learning 6 Feb 2016 · 0 repositories · arXiv:1602.02220
-
Adaptive dropout for training deep neural networks 1 Dec 2013 · 0 repositories
Tasks archive 2025-07-28
20 shown of 30 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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