Skip to main content

Hierarchical interpretatations and contextual decomposition in pytorch

Project description

Hierarchical neural-net interpretations (ACD) 🧠

Produces hierarchical interpretations for a single prediction made by a pytorch neural network. Official code for Hierarchical interpretations for neural network predictions (ICLR 2019 pdf).

DocumentationDemo notebooks

Note: this repo is actively maintained. For any questions please file an issue.

examples/documentation

  • installation: pip install acd (or clone and run python setup.py install)
  • examples: the reproduce_figs folder has notebooks with many demos
  • src: the acd folder contains the source for the method implementation
  • allows for different types of interpretations by changing hyperparameters (explained in examples)
  • test with pytorch >1.0 with/without gpu
  • all required data/models/code for reproducing are included in the dsets folder
Inspecting NLP sentiment models Detecting adversarial examples Analyzing imagenet models

notes on using ACD on your own data

  • the current CD implementation doesn't always work for all types of networks. If you are getting an error inside of cd.py, you may need to write a custom function that iterates through the layers of your network (for examples see cd.py). Should work out-of-the-box for many common layers though, including antyhing in alexnet, vgg, or resnet.
  • to use baselines such build-up and occlusion, replace the pred_ims function by a function, which gets predictions from your model given a batch of examples.

related work

  • PDR framework (PNAS 2019 pdf) - an overarching framewwork for guiding and framing interpretable machine learning
  • CDEP (ICML 2020 pdf, github) - penalizes CD / ACD scores during training to make models generalize better
  • 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)
  • DAC (arXiv 2019 pdf, github) - finds disentangled interpretations for random forests
  • Baseline interpretability methods - the file scores/score_funcs.py also contains simple pytorch implementations of integrated gradients and the simple interpration technique gradient * input

reference

  • feel free to use/share this code openly
  • if you find this code useful for your research, please cite the following:
@inproceedings{
   singh2019hierarchical,
   title={Hierarchical interpretations for neural network predictions},
   author={Chandan Singh and W. James Murdoch and Bin Yu},
   booktitle={International Conference on Learning Representations},
   year={2019},
   url={https://openreview.net/forum?id=SkEqro0ctQ},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

acd-0.0.2.tar.gz (19.9 kB view hashes)

Uploaded Source

Built Distribution

acd-0.0.2-py3-none-any.whl (23.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page