MétaCan
Menu
Back to cohort
Record W4409814790 · doi:10.1016/j.procs.2025.03.057

Survey of Graph Neural Network Methods for Dynamic Link Prediction

2025· article· en· W4409814790 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

VenueProcedia Computer Science · 2025
Typearticle
Languageen
FieldEngineering
TopicTraffic Prediction and Management Techniques
Canadian institutionsUniversity of Windsor
Fundersnot available
KeywordsComputer scienceLink (geometry)GraphArtificial neural networkArtificial intelligenceData miningTheoretical computer scienceComputer network

Abstract

fetched live from OpenAlex

Graph Neural Network (GNN) methods for Dynamic Link Prediction (DLP) have been a very active research area in recent years. DLP extends traditional LP to time-varying graphs that demand models incorporating structural and temporal features. This survey studies the application of GNN methods for DLP in evolving networks. The paper offers a comprehensive overview of GNN-based methods, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), and GraphSAGE. We analyze these methods by comparing their scalability, ability to handle noise and incomplete data, and their effectiveness in modeling heterogeneous and dynamic graphs. Despite advancements, no single model effectively addresses all key challenges simultaneously, particularly in handling large-scale dynamic graphs, mitigating data sparsity, and capturing long-term temporal dependencies. This gap highlights the need for further research to develop specific methods for DLP. Finally, we explore some open and ongoing research directions for future work.

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)0.001
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 score0.882
Threshold uncertainty score0.336

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.014
GPT teacher head0.298
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