MétaCan
Menu
Back to cohort

The Application of Graph Neural Network in Natural Language Processing and Computer Vision

2021· article· en· W4226436280 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI) · 2021
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceCategorizationArtificial intelligenceDeep learningBenchmark (surveying)GraphArtificial neural networkEuclidean geometryRecurrent neural networkTransformation (genetics)Machine learningNatural language processingTheoretical computer science

Abstract

fetched live from OpenAlex

Graphs can represent information transformation via geometrical relations, which have been well studied and applied in various research areas. A graph-based learning network named Graph Neural Network (GNN) arose with the vast development of deep learning in recent years. Unlike traditional deep learning networks such as CNN and RNN, GNN is superior in dealing with non-Euclidean graph data. This survey focuses on two widespread application fields of GNN, natural language processing (NLP) and computer vision (CV). Firstly, based on the tasks they perform, we categorize the most popular research sub-domains of NLP and CV, purpose a detailed review on the application of GNN in these areas. Secondly, we thoroughly analyzed the benchmark datasets applied in the GNN models while comparing them with different evaluation metrics. Finally, we briefly discuss the potential future direction of GNN according to its model building procedure and related application branches.

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.

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)0.000
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: Empirical · Consensus signal: none
Teacher disagreement score0.979
Threshold uncertainty score0.682

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.001
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 head0.036
GPT teacher head0.319
Teacher spread0.284 · 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