mlsanityData to 14 Oct 2026

Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems

arXiv 2209.01143 ↗First posted 2 Sep 2022cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error. To overcome, we propose to learn a meta future gradient generator that forecasts the gradient information of the future data distribution for training so that the recommendation model can be trained as if we were able to look ahead at the future of its deployment. Compared with Batch Update, a widely used paradigm, our theory suggests that the proposed algorithm achieves smaller temporal domain generalization error measured by a gradient variation term in a local regret. We demonstrate the empirical advantage by comparing with various representative baselines.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 70 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

48 of 70 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  6. 2019Invariant Risk Minimizationcited by 1,854
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  8. 2016Progressive Neural Networkscited by 1,361
  9. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  10. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  11. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  12. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
36 more
  1. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  2. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  3. 2016Learning to learn by gradient descent by gradient descentcited by 620
  4. 2019Gradient based sample selection for online continual learningcited by 571
  5. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  6. 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 417
  7. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 405
  8. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
  9. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  10. 2020Improve Unsupervised Domain Adaptation with Mixup Trainingcited by 185
  11. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 161
  12. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  13. 2019MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendationcited by 121
  14. 2019Meta-Learning with Warped Gradient Descentcited by 98
  15. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  16. 2020How to Retrain Recommender System? A Sequential Meta-Learning Methodcited by 42
  17. 2020GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systemscited by 42
  18. 2021Learnable Embedding Sizes for Recommender Systemscited by 42
  19. 2022Provable Domain Generalization via Invariant-Feature Subspace Recoverycited by 32
  20. 2022Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyondcited by 32
  21. 2017Efficient Regret Minimization in Non-Convex Gamescited by 28
  22. 2020GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendationcited by 24
  23. 2020ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendationcited by 22
  24. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  25. 2019LambdaOpt: Learn to Regularize Recommender Models in Finer Levelscited by 14
  26. 2021Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Setcited by 12
  27. 2020A Practical Incremental Method to Train Deep CTR Modelscited by 10
  28. 2020Regret minimization in stochastic non-convex learning via a proximal-gradient approachcited by 9
  29. 2021Online Continual Adaptation with Active Self-Trainingcited by 8
  30. 2021Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systemscited by 5
  31. 2020Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Datacited by 4
  32. 2022Algorithms and Theory for Supervised Gradual Domain Adaptationcited by 4
  33. 2018Evaluating and Characterizing Incremental Learning from Non-Stationary Datacited by 3
  34. 2021Alternate Model Growth and Pruning for Efficient Training of Recommendation Systemscited by 3
  35. 2020ShadowSync: Performing Synchronization in the Background for Highly Scalable Distributed Trainingcited by 2
  36. 2020Stratified and Time-aware Sampling based Adaptive Ensemble Learning for Streaming Recommendationscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2025Continual Low-Rank Adapters for LLM-based Generative Recommender Systemscited by 2
  2. 2023Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithmscited by 1
  3. 2024Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation Systemcited by 1