MétaCan
Menu
Back to cohort
Record W3170809304 · doi:10.48550/arxiv.2106.06401

Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous\n Distributed Learning

2021· preprint· en· W3170809304 on OpenAlexaff
Eugene Belilovsky, Louis Leconte, Lucas Caccia, Michael Eickenberg, Edouard Oyallon

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsMcGill UniversityConcordia UniversityMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsAsynchronous communicationComputer scienceGreedy algorithmAsynchronous learningArtificial intelligenceTheoretical computer scienceDistributed computingAlgorithmComputer networkMathematicsSynchronous learningCooperative learningMathematics educationTeaching method

Abstract

fetched live from OpenAlex

A commonly cited inefficiency of neural network training using\nback-propagation is the update locking problem: each layer must wait for the\nsignal to propagate through the full network before updating. Several\nalternatives that can alleviate this issue have been proposed. In this context,\nwe consider a simple alternative based on minimal feedback, which we call\nDecoupled Greedy Learning (DGL). It is based on a classic greedy relaxation of\nthe joint training objective, recently shown to be effective in the context of\nConvolutional Neural Networks (CNNs) on large-scale image classification. We\nconsider an optimization of this objective that permits us to decouple the\nlayer training, allowing for layers or modules in networks to be trained with a\npotentially linear parallelization. With the use of a replay buffer we show\nthat this approach can be extended to asynchronous settings, where modules can\noperate and continue to update with possibly large communication delays. To\naddress bandwidth and memory issues we propose an approach based on online\nvector quantization. This allows to drastically reduce the communication\nbandwidth between modules and required memory for replay buffers. We show\ntheoretically and empirically that this approach converges and compare it to\nthe sequential solvers. We demonstrate the effectiveness of DGL against\nalternative approaches on the CIFAR-10 dataset and on the large-scale ImageNet\ndataset.\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: none
Teacher disagreement score0.708
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
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.002
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 head0.039
GPT teacher head0.202
Teacher spread0.163 · 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

Citations1
Published2021
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdvanced Neural Network ApplicationsFrench-language works237,207