Skip to content

FFT Wavelets and more

Adds several sharing methods and their accompanying training implementations:

  • FFT with frequency change based parameter selection (FrequencyAccumulator)
  • Wavelet with frequency change based parameter selection (FrequencyWaveletAccumulator)
  • topK with model change based parameter selection (ModelChangeAccumulator)
  • TopKParams: selects the topK highest values for sharing

It also adds an example config file for each mentioned sharing method.

Additionally it adds:

  • 96 nodes regular random graph with degree four
  • now also json dumps the average train loss, test loss, and test loss
  • changes template to store the logging data on the nfs
  • adds PyWavelets to setup.cfg
  • In it will now crash if the logging directory already exists to prevent accidentally overwriting old experiments.
  • converting indices to int32 before encoding
  • removing not needed imports
Edited by Jeffrey Wigger

Merge request reports