search

LabeliaLabs / distributed-learning-contributivity

Simulate collaborative ML scenarios, experiment multi-partner learning approaches and measure respective contributions of different datasets to model performance.
https://www.labelia.org
Apache License 2.0
56 stars 12 forks source link

Add gradient fusion method for multi-partner-learning #299

Closed arthurPignet closed 3 years ago

arthurPignet commented 3 years ago

This PR follows the PR271

codecov-io commented 3 years ago

Codecov Report

Merging #299 (cddc385) into master (b81ff8c) will decrease coverage by 0.05%. The diff coverage is 77.35%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #299      +/-   ##
==========================================
- Coverage   82.68%   82.63%   -0.06%     
==========================================
  Files          13       13              
  Lines        2588     2637      +49     
==========================================
+ Hits         2140     2179      +39     
- Misses        448      458      +10
Impacted Files Coverage Δ
mplc/mpl_utils.py 84.21% <45.00%> (-5.54%) :arrow_down:
mplc/multi_partner_learning.py 85.31% <96.87%> (+1.14%) :arrow_up:
mplc/partner.py 91.20% <100.00%> (+0.09%) :arrow_up:

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update b81ff8c...cddc385. Read the comment docs.