MétaCan
Menu
Back to cohort
Record W4287236889 · doi:10.48550/arxiv.2104.03546

Graph Partitioning and Sparse Matrix Ordering using Reinforcement\n Learning and Graph Neural Networks

2021· preprint· en· W4287236889 on OpenAlexaboutno aff
Alice Gatti, Zhixiong Hu, Tess Smidt, Esmond Ng, Pieter Ghysels

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldEngineering
TopicVLSI and FPGA Design Techniques
Canadian institutionsnot available
Fundersnot available
KeywordsGraph partitionComputer scienceDense graphReinforcement learningSparse matrixAdjacency matrixGraphAlgorithmTheoretical computer scienceCombinatoricsArtificial intelligenceMathematicsLine graphPathwidth

Abstract

fetched live from OpenAlex

We present a novel method for graph partitioning, based on reinforcement\nlearning and graph convolutional neural networks. Our approach is to\nrecursively partition coarser representations of a given graph. The neural\nnetwork is implemented using SAGE graph convolution layers, and trained using\nan advantage actor critic (A2C) agent. We present two variants, one for finding\nan edge separator that minimizes the normalized cut or quotient cut, and one\nthat finds a small vertex separator. The vertex separators are then used to\nconstruct a nested dissection ordering to permute a sparse matrix so that its\ntriangular factorization will incur less fill-in. The partitioning quality is\ncompared with partitions obtained using METIS and SCOTCH, and the nested\ndissection ordering is evaluated in the sparse solver SuperLU. Our results show\nthat the proposed method achieves similar partitioning quality as METIS and\nSCOTCH. Furthermore, the method generalizes across different classes of graphs,\nand works well on a variety of graphs from the SuiteSparse sparse matrix\ncollection.\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.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.470
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.041
GPT teacher head0.186
Teacher spread0.145 · 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.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations7
Published2021
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicVLSI and FPGA Design TechniquesFrench-language works237,207