/local-vae

Making locally disentangled vaes.

Primary LanguageJupyter NotebookMIT LicenseMIT

Trying to make locally disentangled VAEs.

This repo is actively maintained. For any questions please file an issue.

related work

  • TRIM (ICLR 2020 workshop pdf, github) - using simple reparameterizations, allows for calculating disentangled importances to transformations of the input (e.g. assigning importances to different frequencies)
  • ACD (ICLR 2019 pdf, github) - extends CD to CNNs / arbitrary DNNs, and aggregates explanations into a hierarchy
  • CDEP (ICML 2020 pdf, github) - penalizes CD / ACD scores during training to make models generalize better
  • DAC (arXiv 2019 pdf, github) - finds disentangled interpretations for random forests
  • PDR framework (PNAS 2019 pdf) - an overarching framewwork for guiding and framing interpretable machine learning

reference

  • feel free to use/share this code openly
  • uses code from disentangling-vae + TRIM
  • if you find this code useful for your research, please cite the following: