MétaCan
Menu
← all works

Optimizing Federated Learning on Non-IID Data with Reinforcement Learning

2020· article· en· 958 citations· W3047304572 on OpenAlex· 10.1109/infocom41043.2020.9155494

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Full frame distilled prediction

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.

Candidate categories
Open science
Consensus categories
Open science
Domain
Candidate signal: noneConsensus signal: none
Study design
Candidate signal: Simulation or modelingConsensus signal: Simulation or modeling
Genre
Candidate signal: MethodsConsensus signal: none
Teacher disagreement score
0.570
Threshold uncertainty score
0.980
Validation status
machine_predicted_unvalidated · codex-gemma-dda1882f352a

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.008
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0250.100
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

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.

Opus teacher head0.057
GPT teacher head0.276
Teacher spread
0.219 · how far apart the two teachers sit on this one work
Validation status
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Abstract

The widespread deployment of machine learning applications in ubiquitous environments has sparked interests in exploiting the vast amount of data stored on mobile devices. To preserve data privacy, Federated Learning has been proposed to learn a shared model by performing distributed training locally on participating devices and aggregating the local models into a global one. However, due to the limited network connectivity of mobile devices, it is not practical for federated learning to perform model updates and aggregation on all participating devices in parallel. Besides, data samples across all devices are usually not independent and identically distributed (IID), posing additional challenges to the convergence and speed of federated learning. In this paper, we propose Favor, an experience-driven control framework that intelligently chooses the client devices to participate in each round of federated learning to counterbalance the bias introduced by non-IID data and to speed up convergence. Through both empirical and mathematical analysis, we observe an implicit connection between the distribution of training data on a device and the model weights trained based on those data, which enables us to profile the data distribution on that device based on its uploaded model weights. We then propose a mechanism based on deep Q-learning that learns to select a subset of devices in each communication round to maximize a reward that encourages the increase of validation accuracy and penalizes the use of more communication rounds. With extensive experiments performed in PyTorch, we show that the number of communication rounds required in federated learning can be reduced by up to 49% on the MNIST dataset, 23% on FashionMNIST, and 42% on CIFAR-10, as compared to the Federated Averaging algorithm.

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.

The record

Venue
Topic
Privacy-Preserving Technologies in Data
Field
Computer Science
Canadian institutions
University of AlbertaUniversity of Toronto
Funders
not available
Keywords
Computer scienceUploadReinforcement learningIndependent and identically distributed random variablesArtificial intelligenceMachine learningMobile deviceConvergence (economics)Software deploymentFederated learningDistributed computingData modelingDatabaseWorld Wide Web
Has abstract in OpenAlex
yes