MétaCan
Menu
Back to cohort
Record W4298126048 · doi:10.1007/978-3-031-11748-0_5

A Unifying Framework for Federated Learning

2022· book-chapter· en· W4298126048 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

VenueAdaptation, learning, and optimization · 2022
Typebook-chapter
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsHuawei Technologies (Canada)University of Waterloo
Fundersnot available
KeywordsComputer scienceUnificationScheme (mathematics)Convergence (economics)Theoretical computer scienceAlgorithmMathematics

Abstract

fetched live from OpenAlex

There have been multiple federated learning (FL) algorithms proposed in the FL community during the recent years. However, a thorough comparison of these algorithms has not been done, and our understanding of the theory of FL is still limited. The lack of a unifying view in practice has also led to the reinvention of the same algorithms under different names. Motivated by this gap, we develop a unifying scheme for FL and demonstrate that many of the algorithms that exist in the FL literature are special cases of this scheme. The unification allows us to get a deeper understanding of different FL algorithms, to compare them easier, to improve the previous results for their convergence analysis and to find new FL algorithms. In particular, we demonstrate the important role that step size plays in the convergence of FL algorithms. Further, based on our unifying scheme, we propose an efficient and economic method for accelerating FL algorithms. This streamlined acceleration method does not incur any communication overheads. We evaluate our findings by performing extensive experiments on both nonconvex and convex problems.

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)0.000
metaresearch head score (Gemma)0.012
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.230
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.012
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0030.008
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 head0.034
GPT teacher head0.266
Teacher spread0.232 · 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