https://github.com/csinva/local-vae

Making locally disentangled vaes.
https://github.com/csinva/local-vae

disentanglement neural-network pytorch vae

Last synced: 2 months ago
JSON representation

Making locally disentangled vaes.

• Host: GitHub
• URL: https://github.com/csinva/local-vae
• Owner: csinva
• License: mit
• Created: 2020-09-11T07:49:14.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-02-12T21:33:07.000Z (over 4 years ago)
• Last Synced: 2025-02-08T13:31:17.890Z (4 months ago)
• Topics: disentanglement, neural-network, pytorch, vae
• Language: Jupyter Notebook
• Homepage: https://csinva.io/local-vae/
• Size: 102 MB
• Stars: 3
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md
  • License: LICENSE

Awesome Lists containing this project

README

        
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](https://arxiv.org/abs/2003.01926), [github](https://github.com/csinva/transformation-importance)) - using simple reparameterizations, allows for calculating disentangled importances to transformations of the input (e.g. assigning importances to different frequencies)

- ACD (ICLR 2019 [pdf](https://openreview.net/pdf?id=SkEqro0ctQ), [github](https://github.com/csinva/hierarchical-dnn-interpretations)) - extends CD to CNNs / arbitrary DNNs, and aggregates explanations into a hierarchy

- CDEP (ICML 2020 [pdf](https://arxiv.org/abs/1909.13584), [github](https://github.com/laura-rieger/deep-explanation-penalization)) - penalizes CD / ACD scores during training to make models generalize better

- DAC (arXiv 2019 [pdf](https://arxiv.org/abs/1905.07631), [github](https://github.com/csinva/disentangled-attribution-curves)) - finds disentangled interpretations for random forests

- PDR framework (PNAS 2019 [pdf](https://arxiv.org/abs/1901.04592)) - an overarching framewwork for guiding and framing interpretable machine learning

# reference

- feel free to use/share this code openly

- uses code from [disentangling-vae](https://github.com/YannDubs/disentangling-vae) + [TRIM](https://github.com/csinva/transformation-importance)

- if you find this code useful for your research, please cite the following:

```r

```