Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916834887860224 |
|---|---|
| author | Zheng, Shanle Bao, Keqin Zhang, Jizhi Zhang, Yang Feng, Fuli He, Xiangnan |
| author_facet | Zheng, Shanle Bao, Keqin Zhang, Jizhi Zhang, Yang Feng, Fuli He, Xiangnan |
| contents | LLM-based recommender systems have made significant progress; however, the deployment cost associated with the large parameter volume of LLMs still hinders their real-world applications. This work explores parameter pruning to improve parameter efficiency while maintaining recommendation quality, thereby enabling easier deployment. Unlike existing approaches that focus primarily on inter-layer redundancy, we uncover intra-layer redundancy within components such as self-attention and MLP modules. Building on this analysis, we propose a more fine-grained pruning approach that integrates both intra-layer and layer-wise pruning. Specifically, we introduce a three-stage pruning strategy that progressively prunes parameters at different levels and parts of the model, moving from intra-layer to layer-wise pruning, or from width to depth. Each stage also includes a performance restoration step using distillation techniques, helping to strike a balance between performance and parameter efficiency. Empirical results demonstrate the effectiveness of our approach: across three datasets, our models achieve an average of 88% of the original model's performance while pruning more than 95% of the non-embedding parameters. This underscores the potential of our method to significantly reduce resource requirements without greatly compromising recommendation quality. Our code will be available at: https://github.com/zheng-sl/PruneRec |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07064 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning Zheng, Shanle Bao, Keqin Zhang, Jizhi Zhang, Yang Feng, Fuli He, Xiangnan Information Retrieval LLM-based recommender systems have made significant progress; however, the deployment cost associated with the large parameter volume of LLMs still hinders their real-world applications. This work explores parameter pruning to improve parameter efficiency while maintaining recommendation quality, thereby enabling easier deployment. Unlike existing approaches that focus primarily on inter-layer redundancy, we uncover intra-layer redundancy within components such as self-attention and MLP modules. Building on this analysis, we propose a more fine-grained pruning approach that integrates both intra-layer and layer-wise pruning. Specifically, we introduce a three-stage pruning strategy that progressively prunes parameters at different levels and parts of the model, moving from intra-layer to layer-wise pruning, or from width to depth. Each stage also includes a performance restoration step using distillation techniques, helping to strike a balance between performance and parameter efficiency. Empirical results demonstrate the effectiveness of our approach: across three datasets, our models achieve an average of 88% of the original model's performance while pruning more than 95% of the non-embedding parameters. This underscores the potential of our method to significantly reduce resource requirements without greatly compromising recommendation quality. Our code will be available at: https://github.com/zheng-sl/PruneRec |
| title | Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2507.07064 |