MétaCan
Menu
Back to cohort
Record W4386691567 · doi:10.52953/afyw5455

Designing graph neural networks training data with limited samples and small network sizes

2023· article· en· W4386691567 on OpenAlexafffund
Junior Momo Ziazet, Charles Boudreau, Oscar Delgado, Brigitte Jaumard

Bibliographic record

VenueITU Journal on Future and Evolving Technologies · 2023
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsConcordia University
FundersMitacs
KeywordsComputer scienceArtificial neural networkPipeline (software)GraphArtificial intelligenceData miningMachine learningTraining setBaseline (sea)Domain (mathematical analysis)Feature (linguistics)Small dataNode (physics)EngineeringTheoretical computer scienceMathematics

Abstract

fetched live from OpenAlex

Machine learning is a data-driven domain, which means a learning model's performance depends on the availability of large volumes of data to train it. However, by improving data quality, we can train effective machine learning models with little data. This paper demonstrates this possibility by proposing a methodology to generate high-quality data in the networking domain. We designed a dataset to train a given Graph Neural Network (GNN) that not only contains a small number of samples, but whose samples also feature network graphs of a reduced size (10-node networks). Our evaluations indicate that the dataset generated by the proposed pipeline can train a GNN model that scales well to larger networks of 50 to 300 nodes. The trained model compares favorably to the baseline, achieving a mean absolute percentage error of 5-6%, while being significantly smaller at 90 samples total (vs. thousands of samples for the baseline).

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.861
Threshold uncertainty score0.979

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.058
GPT teacher head0.251
Teacher spread0.192 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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

Citations2
Published2023
Admission routes2
Has abstractyes

Explore more

Same venueITU Journal on Future and Evolving TechnologiesSame topicAdvanced Graph Neural NetworksFrench-language works237,207