A Universal Framework for Compressing Embeddings in CTR Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909503572672512 |
|---|---|
| author | Wang, Kefan Wang, Hao Song, Kenan Guo, Wei Cheng, Kai Li, Zhi Liu, Yong Lian, Defu Chen, Enhong |
| author_facet | Wang, Kefan Wang, Hao Song, Kenan Guo, Wei Cheng, Kai Li, Zhi Liu, Yong Lian, Defu Chen, Enhong |
| contents | Accurate click-through rate (CTR) prediction is vital for online advertising and recommendation systems. Recent deep learning advancements have improved the ability to capture feature interactions and understand user interests. However, optimizing the embedding layer often remains overlooked. Embedding tables, which represent categorical and sequential features, can become excessively large, surpassing GPU memory limits and necessitating storage in CPU memory. This results in high memory consumption and increased latency due to frequent GPU-CPU data transfers. To tackle these challenges, we introduce a Model-agnostic Embedding Compression (MEC) framework that compresses embedding tables by quantizing pre-trained embeddings, without sacrificing recommendation quality. Our approach consists of two stages: first, we apply popularity-weighted regularization to balance code distribution between high- and low-frequency features. Then, we integrate a contrastive learning mechanism to ensure a uniform distribution of quantized codes, enhancing the distinctiveness of embeddings. Experiments on three datasets reveal that our method reduces memory usage by over 50x while maintaining or improving recommendation performance compared to existing models. The implementation code is accessible in our project repository https://github.com/USTC-StarTeam/MEC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Universal Framework for Compressing Embeddings in CTR Prediction Wang, Kefan Wang, Hao Song, Kenan Guo, Wei Cheng, Kai Li, Zhi Liu, Yong Lian, Defu Chen, Enhong Information Retrieval Accurate click-through rate (CTR) prediction is vital for online advertising and recommendation systems. Recent deep learning advancements have improved the ability to capture feature interactions and understand user interests. However, optimizing the embedding layer often remains overlooked. Embedding tables, which represent categorical and sequential features, can become excessively large, surpassing GPU memory limits and necessitating storage in CPU memory. This results in high memory consumption and increased latency due to frequent GPU-CPU data transfers. To tackle these challenges, we introduce a Model-agnostic Embedding Compression (MEC) framework that compresses embedding tables by quantizing pre-trained embeddings, without sacrificing recommendation quality. Our approach consists of two stages: first, we apply popularity-weighted regularization to balance code distribution between high- and low-frequency features. Then, we integrate a contrastive learning mechanism to ensure a uniform distribution of quantized codes, enhancing the distinctiveness of embeddings. Experiments on three datasets reveal that our method reduces memory usage by over 50x while maintaining or improving recommendation performance compared to existing models. The implementation code is accessible in our project repository https://github.com/USTC-StarTeam/MEC. |
| title | A Universal Framework for Compressing Embeddings in CTR Prediction |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.15355 |