Striders is a surrogate-based explainable AI (XAI) library for efficient feature attribution. It uses landmark-based kernel approximations to reduce the computational cost of generating additive feature contributions, providing a scalable alternative to SHAP for tabular models.
Installation
pip install striders
Performance Benchmarking
| Dataset (Task) | Samples / Features | Metric | TreeSHAP | Striders | Speed-up |
|---|---|---|---|---|---|
| CA Housing (Reg.) | 20,640 / 8 | Execution Time | 22.1948s | 0.3927s | 56.5x 🚀 |
| Fidelity ($R^2$) | - | 0.9081 | |||
| Correlation | - | 0.9490 | |||
| Credit Default (Clf.) | 30,000 / 23 | Execution Time | 47.0008s | 2.4718s | 19.0x 🚀 |
| Fidelity ($R^2$) | - | 0.9776 | |||
| Correlation | - | 0.9429 |
Reproducibility: You can run directly in:
Acknowledgments & Citations
This is an unofficial implementation based on the principles described in:
@article{ko2025stride,
title={STRIDE: Subset-Free Functional Decomposition for XAI in Tabular Settings},
author={Ko, Chaeyun},
journal={arXiv preprint arXiv:2509.09070},
year={2025}
}
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file striders-0.1.1.tar.gz.
File metadata
- Download URL: striders-0.1.1.tar.gz
- Upload date:
- Size: 45.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
maturin/1.14.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
10e90330dc9644d78c79c28d7597237b56bf532a27177d6a6309195f2fff17d2
|
|
| MD5 |
608340d6bdd89614db04ea3a516a628c
|
|
| BLAKE2b-256 |
db24b689753e5deaef598f4e18c555d7dab84f91f05ddc62082075e4a6a2c33a
|
File details
Details for the file striders-0.1.1-cp38-abi3-win_amd64.whl.
File metadata
- Download URL: striders-0.1.1-cp38-abi3-win_amd64.whl
- Upload date:
- Size: 789.9 kB
- Tags: CPython 3.8+, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via:
maturin/1.14.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e4b1e0c6a2dac138456dfde16bbc319d4f50e48c78d303c7c629fedb1ae7addb
|
|
| MD5 |
616c603d71dbdee2f9f31d560124b8a5
|
|
| BLAKE2b-256 |
7e9ee5eb5decace1bad0233d01479660958a115eee1fa140052bbe235f3532e4
|
File details
Details for the file striders-0.1.1-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: striders-0.1.1-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 1.1 MB
- Tags: CPython 3.8+, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via:
maturin/1.14.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
00e97b14f9dc5a2b56af9d3e7e130fb7b3d40bc1569ffba6d41f79af9854ed3d
|
|
| MD5 |
26bbb8f58e530d4fffc041112803d8f5
|
|
| BLAKE2b-256 |
424399546ba3dbb71c4bd12c94b7648a195838aa45ee5d54023b3068ae8c35b7
|
File details
Details for the file striders-0.1.1-cp38-abi3-macosx_11_0_arm64.whl.
File metadata
- Download URL: striders-0.1.1-cp38-abi3-macosx_11_0_arm64.whl
- Upload date:
- Size: 698.3 kB
- Tags: CPython 3.8+, macOS 11.0+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via:
maturin/1.14.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
185164754025d573d0e48a635a5ed23f5f92110cae5e1b066a87e7c1009b95fe
|
|
| MD5 |
bff977316413f38f618e93b9085454f3
|
|
| BLAKE2b-256 |
b209e3240102faba18fe0667e2b3d0912d3690b0fc6c4f42c6e0588b1ba60c01
|
