Methods › General › Sparsity › SET

Sparse Evolutionary Training

SET

13,419 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 method where weight mask is updated randomly periodically

PaperSource

Papers archive 2025-07-28

30 shown of 13,419, 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.

Tasks archive 2025-07-28

20 shown of 1,762 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
Language Modelling632
Language Modeling508
Large Language Model396
Retrieval347
Diversity324
Decision Making308
Question Answering298
Semantic Segmentation296
Benchmarking288
Prediction264
Segmentation233
Image Generation224
reinforcement-learning223
Reinforcement Learning (RL)220
Reinforcement Learning211
Transfer Learning203
Object200
Image Classification199
Classification194
Data Augmentation191

Usage over time archive 2025-07-28

Papers per year tagged with SET: 2017 to 2025, peak 8,295 8,295 0 2017: 1 paper 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 0 papers 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 1640 papers 2023 2024: 8295 papers 2024 2025: 3483 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (13,419 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

Sparsity

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