Methods › Sequential › Recurrent Neural Networks › Mogrifier LSTM
Mogrifier LSTM
Introduced by Gábor Melis et al. in Mogrifier LSTM
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Mogrifier LSTM is an extension to the LSTM where the LSTM’s input x is gated conditioned on the output of the previous step hₚᵣₑᵥ. Next, the gated input is used in a similar manner to gate the output of the previous time step. After a couple of rounds of this mutual gating, the last updated x and hₚᵣₑᵥ are fed to an LSTM.
In detail, the Mogrifier is an LSTM where two inputs x and hₚᵣₑᵥ modulate one another in an alternating fashion before the usual LSTM computation takes place. That is: Mogrify(x, cₚᵣₑᵥ, hₚᵣₑᵥ) = LSTM(x^↑, cₚᵣₑᵥ, h^↑ₚᵣₑᵥ) where the modulated inputs x^↑ and h^↑ₚᵣₑᵥ are defined as the highest indexed xⁱ and hⁱₚᵣₑᵥ, respectively, from the interleaved sequences:
xⁱ = 2σ(Qⁱhⁱ⁻¹ₚᵣₑᵥ) ⊙xⁱ⁻² for odd i ∈[1 …r]
hⁱₚᵣₑᵥ = 2σ(Rⁱxⁱ⁻¹) ⊙hⁱ⁻²ₚᵣₑᵥ for even i ∈[1 …r]
with x⁻¹ = x and h⁰ₚᵣₑᵥ = hₚᵣₑᵥ. The number of "rounds", r ∈ℕ, is a hyperparameter; r = 0 recovers the LSTM. Multiplication with the constant 2 ensures that randomly initialized Qⁱ, Rⁱ matrices result in transformations close to identity. To reduce the number of additional model parameters, we typically factorize the Qⁱ, Rⁱ matrices as products of low-rank matrices: Qⁱ = Qⁱ_(left)Qⁱ_(right) with Qⁱ ∈ℝ^(m×n), Qⁱ_(left) ∈ℝ^(m×k), Qⁱ_(right) ∈ℝ^(k×n), where k < min(m, n) is the rank.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: LSTM-MAS; IPM-LSTM; AMA-LSTM; LSTM-VRN; FDHT-LSTM; SACL-LSTM; GARCH-LSTM; CNN-LSTM-RL.
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.
Papers archive 2025-07-28
archive papers tagged: 2 · with a code link: 2 · where Syntology ran a sample: 0 (0 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: none of the 2 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 2 of 2, 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.
-
Gates Are Not What You Need in RNNs 1 Aug 2021 · 1 repository · arXiv:2108.00527
-
Mogrifier LSTM 4 Sep 2019 · 3 repositories · arXiv:1909.01792
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 |
|---|---|
| Language Modelling | 2 |
| Language Modeling | 1 |
| Music Modeling | 1 |
| Sentiment Analysis | 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