MétaCan
Menu
Back to cohort

Dual Path Graph Convolutional Networks

2022· article· en· W4224919236 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

VenueICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsComputer scienceGraphResidualTheoretical computer scienceDeep learningConvolutional neural networkExploitArtificial intelligenceDual graphFeature learningPath (computing)AlgorithmComputer networkPlanar graph

Abstract

fetched live from OpenAlex

Graph Convolutional Networks (GCNs) are a powerful approach for learning graph representations and show promising results in various applications. Despite their success, they are usually limited to shallow architectures due to the vanishing gradients, over-smoothing, and over-squashing problems. As Convolutional Neural Networks benefit tremendously from stacking very deep layers, recently techniques such as various types of residual connections and dense connections are proposed to tackle these problems and make GCNs go deeper. In this work, we further study the problem of designing deep architectures for GCNs. Firstly, we introduce the Higher Order Graph Recurrent Networks (HOGRNs), which can unify most existing architectures of GCNs. Then we show that ResGCN and DenseGCN are special cases of HOGRNs. To enjoy the benefits from both residual connections and dense connections and compensate for the drawbacks from each other, we propose Dual Path Graph Convolutional Networks (DPGCNs), which exploit a new topology of connection paths internally. In DPGCNs, we maintain both a residual path and a densely connected path while learning the graph representations. Extensive experiments on OGB datasets demonstrate superior performances of the proposed DPGCNs over competitive baseline methods on the large-scale graph learning tasks of node property prediction and graph property prediction.

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), Insufficient payload (model declined to judge)
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 score0.964
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0010.000

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 head0.035
GPT teacher head0.281
Teacher spread0.246 · 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