# How to Retrain Recommender System? A Sequential Meta-Learning Method

arXiv: https://arxiv.org/abs/2005.13258 · HTML: https://mlsanity.com/paper/2005.13258/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 30 of 42)

- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [Ensuring User-side Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2308.15651/) (2023)
- [Cross-Market Product Recommendation](https://mlsanity.com/paper/2109.05929/) (2021)
- [DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting](https://mlsanity.com/paper/2306.09862/) (2023)
- [User Response Prediction in Online Advertising](https://mlsanity.com/paper/2101.02342/) (2021)
- [Causal Incremental Graph Convolution for Recommender System Retraining](https://mlsanity.com/paper/2108.06889/) (2021)
- [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https://mlsanity.com/paper/2202.06129/) (2022)
- [KEEP: An Industrial Pre-Training Framework for Online Recommendation via Knowledge Extraction and Plugging](https://mlsanity.com/paper/2208.10174/) (2022)
- [Deep Configuration Performance Learning: A Systematic Survey and Taxonomy](https://mlsanity.com/paper/2403.03322/) (2024)
- [Online Caching with Optimistic Learning](https://mlsanity.com/paper/2202.10590/) (2022)
- [Meta-Learning for Online Update of Recommender Systems](https://mlsanity.com/paper/2203.10354/) (2022)
- [CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation](https://mlsanity.com/paper/2108.10511/) (2021)
- [Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction](https://mlsanity.com/paper/2112.11136/) (2021)
- [Online Caching with no Regret: Optimistic Learning via Recommendations](https://mlsanity.com/paper/2204.09345/) (2022)
- [Lightweight Compositional Embeddings for Incremental Streaming Recommendation](https://mlsanity.com/paper/2202.02427/) (2022)
- [Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems](https://mlsanity.com/paper/2209.01143/) (2022)
- [On the Permanence of Backdoors in Evolving Models](https://mlsanity.com/paper/2206.04677/) (2022)
- [Improving conversion rate prediction via self-supervised pre-training in online advertising](https://mlsanity.com/paper/2401.16432/) (2024)
- [Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences](https://mlsanity.com/paper/2403.19871/) (2024)
- [Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approach](https://mlsanity.com/paper/2405.01063/) (2024)
- [Low Rank Field-Weighted Factorization Machines for Low Latency Item Recommendation](https://mlsanity.com/paper/2408.00801/) (2024)
- [Adversarial Attacks on Data Attribution](https://mlsanity.com/paper/2409.05657/) (2024)
- [HAKES: Scalable Vector Database for Embedding Search Service](https://mlsanity.com/paper/2505.12524/) (2025)
- [Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts](https://mlsanity.com/paper/2508.05993/) (2025)
- [Ultra Fast Warm Start Solution for Graph Recommendations](https://mlsanity.com/paper/2509.01549/) (2025)
- [Learning to Learn a Cold-start Sequential Recommender](https://mlsanity.com/paper/2110.09083/) (2021)
- [CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning](https://mlsanity.com/paper/2309.04802/) (2023)
- [Better Late Than Never: Formulating and Benchmarking Recommendation Editing](https://mlsanity.com/paper/2406.04553/) (2024)

## Abstract (arXiv)

Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since it can account for both long-term and short-term user preference. However, a full model retraining could be very time-consuming and memory-costly, especially when the scale of historical data is large. In this work, we study the model retraining mechanism for recommender systems, a topic of high practical values but has been relatively little explored in the research community. Our first belief is that retraining the model on historical data is unnecessary, since the model has been trained on it before. Nevertheless, normal training on new data only may easily cause overfitting and forgetting issues, since the new data is of a smaller scale and contains fewer information on long-term user preference. To address this dilemma, we propose a new training method, aiming to abandon the historical data during retraining through learning to transfer the past training experience. Specifically, we design a neural network-based transfer component, which transforms the old model to a new model that is tailored for future recommendations. To learn the transfer component well, we optimize the "future performance" -- i.e., the recommendation accuracy evaluated in the next time period. Our Sequential Meta-Learning(SML) method offers a general training paradigm that is applicable to any differentiable model. We demonstrate SML on matrix factorization and conduct experiments on two real-world datasets. Empirical results show that SML not only achieves significant speed-up, but also outperforms the full model retraining in recommendation accuracy, validating the effectiveness of our proposals. We release our codes at: https://github.com/zyang1580/SML.