References and citation

Citation

If you use TreeIG in your work, please cite the TreeIG paper:

@misc{hentschel2026treeig,
  author = {Hentschel, Ludger},
  title  = {{TreeIG}: Exact Integrated Gradients for Tree-Based Models},
  year   = {2026},
  url    = {https://www.ludgerhentschel.com/PDFs/Hentschel%20'26g.pdf},
}

References

TreeIG:

• Hentschel, Ludger. 2026. “TreeIG: Exact Integrated Gradients for Tree-Based Models.” https://www.ludgerhentschel.com/Research.html and https://www.ludgerhentschel.com/Programs.html

Integrated Gradients:

• Sundararajan, Mukund, Ankur Taly, and Qiqi Yan. 2017. “Axiomatic Attribution for Deep Networks.” Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3319–3328.

SHAP and TreeSHAP:

• Lundberg, Scott M., and Su-In Lee. 2017. “A Unified Approach to Interpreting Model Predictions.” Advances in Neural Information Processing Systems (NeurIPS).

• Lundberg, Scott M., Gabriel Erion, and Su-In Lee. 2020. “From Local Explanations to Global Understanding with Explainable AI for Trees.” Nature Machine Intelligence.

Popular implementations of Integrated Gradients for smooth models:

• Captum for PyTorch: https://captum.ai/

• TensorFlow Integrated Gradients: https://www.tensorflow.org/tutorials/interpretability/integrated_gradients

License

TreeIG is released under the terms in LICENSE.

Integrated Gradients BibTeX

@inproceedings{sundararajan2017axiomatic,
  title = {Axiomatic Attribution for Deep Networks},
  author = {Sundararajan, Mukund and Taly, Ankur and Yan, Qiqi},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {70},
  pages = {3319--3328},
  year = {2017},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v70/sundararajan17a.html},
}