Methods › General › Model Compression › DST

Dynamic Sparse Training

DST

205 papers tagged archive 2025-07-28

Introduced by Decebal Constantin Mocanu et al. in Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

PaperSource

In Syntology about another paper, arXiv:2204.00972: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2204.00972, while the archive credits arXiv:1707.04780, so it does not say whether this method has code.

Origin paper of this answer, arXiv:2204.00972 (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.

Papers archive 2025-07-28

archive papers tagged: 205 · with a code link: 87 · where Syntology ran a sample: 16 (14 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (16 of 205 tagged: 14 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 205, 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.

Tasks archive 2025-07-28

20 shown of 143 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Dialogue State Tracking129
Task-Oriented Dialogue Systems32
Multi-domain Dialogue State Tracking24
dialog state tracking20
Language Modelling18
Language Modeling16
Transfer Learning15
Decoder12
In-Context Learning9
Question Answering9
Slot Filling9
slot-filling9
Data Augmentation8
Reading Comprehension7
Domain Adaptation6
Few-Shot Learning6
Response Generation6
Diversity5
Management5
Natural Language Understanding5

Usage over time archive 2025-07-28

Papers per year tagged with DST: 2017 to 2025, peak 38 38 0 2017: 3 papers 2017 2018: 8 papers 2018 2019: 15 papers 2019 2020: 32 papers 2020 2021: 38 papers 2021 2022: 34 papers 2022 2023: 37 papers 2023 2024: 30 papers 2024 2025: 8 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (205 dated). Bars are counts, not a trend claim.

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

Model Compression

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