# A Generic Network Compression Framework for Sequential Recommender Systems

arXiv: https://arxiv.org/abs/2004.13139 · HTML: https://mlsanity.com/paper/2004.13139/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [Device-Cloud Collaborative Learning for Recommendation](https://mlsanity.com/paper/2104.06624/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Accelerating Recommendation System Training by Leveraging Popular Choices](https://mlsanity.com/paper/2103.00686/) (2021)
- [Heterogeneous Acceleration Pipeline for Recommendation System Training](https://mlsanity.com/paper/2204.05436/) (2022)
- [Device-Cloud Collaborative Recommendation via Meta Controller](https://mlsanity.com/paper/2207.03066/) (2022)
- [MC2-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation](https://mlsanity.com/paper/2109.12314/) (2021)
- [Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search](https://mlsanity.com/paper/2107.07173/) (2021)
- [CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems](https://mlsanity.com/paper/2506.19993/) (2025)
- [Accelerating Recommender Model Training by Dynamically Skipping Stale Embeddings](https://mlsanity.com/paper/2404.04270/) (2024)

## Abstract (arXiv)

Sequential recommender systems (SRS) have become the key technology in capturing user's dynamic interests and generating high-quality recommendations. Current state-of-the-art sequential recommender models are typically based on a sandwich-structured deep neural network, where one or more middle (hidden) layers are placed between the input embedding layer and output softmax layer. In general, these models require a large number of parameters (such as using a large embedding dimension or a deep network architecture) to obtain their optimal performance. Despite the effectiveness, at some point, further increasing model size may be harder for model deployment in resource-constraint devices, resulting in longer responding time and larger memory footprint. To resolve the issues, we propose a compressed sequential recommendation framework, termed as CpRec, where two generic model shrinking techniques are employed. Specifically, we first propose a block-wise adaptive decomposition to approximate the input and softmax matrices by exploiting the fact that items in SRS obey a long-tailed distribution. To reduce the parameters of the middle layers, we introduce three layer-wise parameter sharing schemes. We instantiate CpRec using deep convolutional neural network with dilated kernels given consideration to both recommendation accuracy and efficiency. By the extensive ablation studies, we demonstrate that the proposed CpRec can achieve up to 4~8 times compression rates in real-world SRS datasets. Meanwhile, CpRec is faster during traininginference, and in most cases outperforms its uncompressed counterpart.