# MC2-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation

arXiv: https://arxiv.org/abs/2109.12314 · HTML: https://mlsanity.com/paper/2109.12314/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 25 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Collaborative Deep Learning for Recommender Systems](https://mlsanity.com/paper/1409.2944/) (2014)
- [Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks](https://mlsanity.com/paper/1706.04148/) (2017)
- [CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation](https://mlsanity.com/paper/2109.05261/) (2021)
- [Fast and Slow Learning of Recurrent Independent Mechanisms](https://mlsanity.com/paper/2105.08710/) (2021)
- [Device-Cloud Collaborative Learning for Recommendation](https://mlsanity.com/paper/2104.06624/) (2021)
- [EdgeRec: Recommender System on Edge in Mobile Taobao](https://mlsanity.com/paper/2005.08416/) (2020)
- [Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net](https://mlsanity.com/paper/1708.04106/) (2017)
- [Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling](https://mlsanity.com/paper/2104.14121/) (2021)
- [A Generic Network Compression Framework for Sequential Recommender Systems](https://mlsanity.com/paper/2004.13139/) (2020)
- [FedeRank: User Controlled Feedback with Federated Recommender Systems](https://mlsanity.com/paper/2012.11328/) (2020)
- [Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation](https://mlsanity.com/paper/2109.11790/) (2021)

## Built on by (most cited first, 5 of 5)

- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Intelligent Request Strategy Design in Recommender System](https://mlsanity.com/paper/2206.12296/) (2022)
- [Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems](https://mlsanity.com/paper/2404.13348/) (2024)
- [Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation](https://mlsanity.com/paper/2409.07416/) (2024)

## Abstract (arXiv)

With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks. Compared to the straightforward mobile-based modeling appended to the cloud-based modeling, we propose a Slow-Fast learning mechanism to make the Mobile-Cloud Collaborative recommendation (MC2-SF) mutual benefit. Specially, in our MC2-SF, the cloud-based model and the mobile-based model are respectively treated as the slow component and the fast component, according to their interaction frequency in real-world scenarios. During training and serving, they will communicate the prior/privileged knowledge to each other to help better capture the user interests about the candidates, resembling the role of System I and System II in the human cognition. We conduct the extensive experiments on three benchmark datasets and demonstrate the proposed MC2-SF outperforms several state-of-the-art methods.