Official Implementation of Kolmogorov-Arnold Network (KAN) for Recommendations
Table of Contents
MovieLens-1m and MovieLens-20m.
| datasets | #users | #items | #actions | average length | density |
|---|---|---|---|---|---|
| ML-1m | 6040 | 3416 | 1m | 163.5 | 4.79% |
| ML-20m | 138,493 | 26,744 | 20m | 144.4 | 0.54% |
codes are tested on Python3.8.16 and 1 NVIDIA Tesla V100 SXM2 16 GB
numpy==1.23.5
pandas==1.5.3
scipy==1.9.1
torch==2.0.0
tqdm==4.65.0
wget==3.2
Our code are partly based on the following GitHub repository. Thanks for their awesome works.
- BERT4Rec-VAE-Pytorch: the implement of BERT4Rec model (PyTorch version).
- fast-kan: the implement of KAN (fast version).
If you find this repository helpful, please cite our paper (coming soon).