MétaCan
Menu
Back to cohort
Record W4414322228 · doi:10.1109/access.2025.3611390

A Developer’s Guide to Compressing Pre-Trained Transformer Neural Networks Across Different Domains

2025· article· en· W4414322228 on OpenAlexaff
Fernando A. Barrios, Ali Emadi

Bibliographic record

VenueIEEE Access · 2025
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Applications
Canadian institutionsMcMaster University
Fundersnot available
KeywordsTransformerArtificial neural networkInferenceBenchmark (surveying)EmbeddingKey (lock)Deep learning

Abstract

fetched live from OpenAlex

Transformer neural networks have become the benchmark across a variety of domains in part thanks to their competence in comprehending the importance and dependencies between large input segments. Pre-trained transformer models typically contain millions of parameters that have been trained with comprehensive datasets improving their generalization, allowing them to be fine-tuned quicker and with less data. Therefore, starting with a pre-trained model provides a substantial advantage over developing a network from the ground up. However, the race to exceed the accuracy of previous model generations leads pre-trained model to increase in size and the required computational resources for inference, as well as training. This is where compression techniques are vital to maximize the impact and performance of the models, while minimizing the cost to deploy. This work covers six of the most successful compression techniques including pruning, knowledge distillation, quantization, adaptive inference (early exit), low-rank factorization and mixture of experts. The study presents a comprehensive overview of their methods, strengths, and weaknesses meant to serve as a guide for machine learning practitioners. The key areas explored are model speedup, model size, accuracy retention, and training requirements.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.112
Threshold uncertainty score0.374

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.012
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0020.002
Open science0.0030.002
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.1120.072

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.022
GPT teacher head0.360
Teacher spread0.338 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicNeural Networks and ApplicationsFrench-language works237,207