# CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration

arXiv: https://arxiv.org/abs/2510.03038 · HTML: https://mlsanity.com/paper/2510.03038/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 30 of 32)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [Proving the Lottery Ticket Hypothesis: Pruning is All You Need](https://mlsanity.com/paper/2002.00585/) (2020)
- [Learning the Pareto Front with Hypernetworks](https://mlsanity.com/paper/2010.04104/) (2020)
- [AdaBits: Neural Network Quantization with Adaptive Bit-Widths](https://mlsanity.com/paper/1912.09666/) (2019)
- [Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance](https://mlsanity.com/paper/2203.08368/) (2022)
- [HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs](https://mlsanity.com/paper/2007.09952/) (2020)
- [DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization](https://mlsanity.com/paper/2209.05227/) (2022)
- [Device-Cloud Collaborative Learning for Recommendation](https://mlsanity.com/paper/2104.06624/) (2021)
- [Fast-adapting and Privacy-preserving Federated Recommender System](https://mlsanity.com/paper/2104.00919/) (2021)
- [EdgeRec: Recommender System on Edge in Mobile Taobao](https://mlsanity.com/paper/2005.08416/) (2020)
- [Intelligent Model Update Strategy for Sequential Recommendation](https://mlsanity.com/paper/2302.07335/) (2023)
- [Real-time Short Video Recommendation on Mobile Devices](https://mlsanity.com/paper/2208.09577/) (2022)
- [On-Device Recommender Systems: A Comprehensive Survey](https://mlsanity.com/paper/2401.11441/) (2024)
- [Retraining-free Model Quantization via One-Shot Weight-Coupling Learning](https://mlsanity.com/paper/2401.01543/) (2024)
- [ThinkRec: Thinking-based recommendation via LLM](https://mlsanity.com/paper/2505.15091/) (2025)
- [Intelligent Request Strategy Design in Recommender System](https://mlsanity.com/paper/2206.12296/) (2022)
- [Parameter-Efficient Masking Networks](https://mlsanity.com/paper/2210.06699/) (2022)
- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities](https://mlsanity.com/paper/2404.13322/) (2024)
- [Towards Communication-Efficient Model Updating for On-Device Session-Based Recommendation](https://mlsanity.com/paper/2308.12777/) (2023)
- [DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation](https://mlsanity.com/paper/2406.08804/) (2024)

## Abstract (arXiv)

With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migrating models from cloud to devices, resource heterogeneity inevitably necessitates model compression. Recent quantization methods show promise for efficient deployment, yet they overlook device-specific user interests, resulting in compromised recommendation accuracy. While on-device finetuning captures personalized user preference, it imposes additional computational burden through local retraining. To address these challenges, we propose a framework for underlineCustomizing underlineHybrid-precision underlineOn-device model for sequential underlineRecommendation with underlineDevice-cloud collaboration (CHORD), leveraging channel-wise mixed-precision quantization to simultaneously achieve personalization and resource-adaptive deployment. CHORD distributes randomly initialized models across heterogeneous devices and identifies user-specific critical parameters through auxiliary hypernetwork modules on the cloud. Our parameter sensitivity analysis operates across multiple granularities (layer, filter, and element levels), enabling precise mapping from user profiles to quantization strategy. Through on-device mixed-precision quantization, CHORD delivers dynamic model adaptation and accelerated inference without backpropagation, eliminating costly retraining cycles. We minimize communication overhead by encoding quantization strategies using only 2 bits per channel instead of 32-bit weights. Experiments on three real-world datasets with two popular backbones (SASRec and Caser) demonstrate the accuracy, efficiency, and adaptivity of CHORD.