Unified Low-rank Compression Framework for Large-scale Recommendation Systems
Authors: Hao Yu, Minghao Fu, Jiandong Ding, Yusheng Zhou, Jianxin Wu
Introduction: This repository provides an implementation for the KDD2024 ADS track paper: "Unified Low-rank Compression Framework for Large-scale Recommendation Systems" based on DeepCTR-Torch. We propose a unified and efficient low-rank decomposition framework to compress the embedding tables and MLP layers of CTR prediction models.
Note: Due to copyright restrictions, we can only provide evaluation code, including eval_criteo.py and eval_avazu.py, and the core compression code demo (afm_emb.py and afm_mlp.py). We cannot provide the detailed engineering code.
Compress MLP Layers:
First given a pre-trained CTR prediction model, calculate the MLP output of each layer of the model and calculate
Compress Embedding Tables:
First given a pre-trained model, count the output of each sparse embedding feature of the model and calculate
Please view our paper for more informations.
@article{yu2024Unified,
title={Unified Low-rank Compression Framework for Large-scale Recommendation Systems},
journal={arXiv preprint arXiv:2405.18146},
author={Hao Yu,Minghao Fu,Jiandong Ding,Yusheng Zhou,Jianxin Wu},
year={2024}
}
If you have any questions about our work, feel free to contact us through email (Hao Yu: yuh@lamda.nju.edu.cn) or Github issues.