Pith. sign in

For instance, in the DO scenario, we start with the configuration of Master #1, which specifies the use of VGG19 as the architecture and CyclicLR as the scheduler

In our experimental scenarios, we always start with a master configuration, modify specific parameters accordingly · arXiv 5050.00604

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

On the Robustness of Distributed Machine Learning against Transfer Attacks

cs.LG · 2024-12-18 · conditional · novelty 5.0

Distributed ML with partitioned data and independently tuned learners improves robustness against transfer-based attacks over an ensemble baseline, but the abstract's emphasis on full heterogeneity is contradicted by the paper's regression results.

citing papers explorer

Showing 1 of 1 citing paper.

  • On the Robustness of Distributed Machine Learning against Transfer Attacks cs.LG · 2024-12-18 · conditional · none · ref 8

    Distributed ML with partitioned data and independently tuned learners improves robustness against transfer-based attacks over an ensemble baseline, but the abstract's emphasis on full heterogeneity is contradicted by the paper's regression results.