MétaCan
Menu
Back to cohort
Record W3157781775 · doi:10.48550/arxiv.2104.11700

Robust Federated Learning by Mixture of Experts

2021· preprint· en· W3157781775 on OpenAlexaff
Saeedeh Parsaeefard, Sayed Ehsan Etesami, Alberto Leon‐Garcia

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsBusinessComputer scienceArtificial intelligence

Abstract

fetched live from OpenAlex

We present a novel weighted average model based on the mixture of experts (MoE) concept to provide robustness in Federated learning (FL) against the poisoned/corrupted/outdated local models. These threats along with the non-IID nature of data sets can considerably diminish the accuracy of the FL model. Our proposed MoE-FL setup relies on the trust between users and the server where the users share a portion of their public data sets with the server. The server applies a robust aggregation method by solving the optimization problem or the Softmax method to highlight the outlier cases and to reduce their adverse effect on the FL process. Our experiments illustrate that MoE-FL outperforms the performance of the traditional aggregation approach for high rate of poisoned data from attackers.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.019
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
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 score0.008
Threshold uncertainty score0.041

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.019
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.004
Open science0.0040.004
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0020.001

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 head0.079
GPT teacher head0.196
Teacher spread0.117 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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 topicPrivacy-Preserving Technologies in DataFrench-language works237,207