Skip to content
/ FCN Public

[KDD 2026] FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction

Notifications You must be signed in to change notification settings

salmon1802/FCN

Repository files navigation

If you have any questions, feel free to ask! :)
To ensure the correctness of the experimental results, please run FCN in FuxiCTR==2.0.1.
This model was formerly known as DCNv3: Towards Next Generation Deep Cross Network for CTR Prediction

Requirements

python>=3.6
pytorch>=1.10
fuxictr==2.0.1
PyYAML
pandas
scikit-learn
numpy
h5py
tqdm

Datasets

Get the datasets from https://github.com/reczoo/Datasets

Hyperparameter settings and logs

Get the result of FCN from https://github.com/salmon1802/FCN/tree/master/checkpoints
Get the result of baseline from https://github.com/reczoo/BARS/tree/main/ranking/ctr

Experiment results

image image

Acknowledgement

This implementation is based on FuxiCTR and BARS. Thanks for their sharing and contribution.
BARS: https://github.com/openbenchmark
FuxiCTR: https://github.com/xue-pai/FuxiCTR

About

[KDD 2026] FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages