MétaCan
Menu
Back to cohort
Record W2971325383 · doi:10.48550/arxiv.1906.07159

vGraph: A Generative Model for Joint Community Detection and Node\n Representation Learning

2019· preprint· W2971325383 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

VenuearXiv (Cornell University) · 2019
Typepreprint
Language
FieldPhysics and Astronomy
TopicComplex Network Analysis Techniques
Canadian institutionsCanadian Institute for Advanced ResearchHEC MontréalMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsComputer scienceGenerative modelNode (physics)Representation (politics)InferenceGraphFeature learningParameterized complexityGenerative grammarCommunity structureTheoretical computer scienceMachine learningJoint probability distributionArtificial intelligenceAlgorithmMathematics

Abstract

fetched live from OpenAlex

This paper focuses on two fundamental tasks of graph analysis: community\ndetection and node representation learning, which capture the global and local\nstructures of graphs, respectively. In the current literature, these two tasks\nare usually independently studied while they are actually highly correlated. We\npropose a probabilistic generative model called vGraph to learn community\nmembership and node representation collaboratively. Specifically, we assume\nthat each node can be represented as a mixture of communities, and each\ncommunity is defined as a multinomial distribution over nodes. Both the mixing\ncoefficients and the community distribution are parameterized by the\nlow-dimensional representations of the nodes and communities. We designed an\neffective variational inference algorithm which regularizes the community\nmembership of neighboring nodes to be similar in the latent space. Experimental\nresults on multiple real-world graphs show that vGraph is very effective in\nboth community detection and node representation learning, outperforming many\ncompetitive baselines in both tasks. We show that the framework of vGraph is\nquite flexible and can be easily extended to detect hierarchical communities.\n

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 categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.565
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0000.002
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 head0.136
GPT teacher head0.231
Teacher spread0.095 · 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