mlsanityData to 7 Oct 2026

Meta Clustering of Neural Bandits

arXiv 2408.05586 ↗First posted 10 Aug 2024cs.LG cs.IRcited by 7

Not on the map. Why?

Abstract (arXiv)

The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an arm and the objective is to minimize the regret of T rounds. In this paper, we study a new problem, Clustering of Neural Bandits, by extending previous work to the arbitrary reward function, to strike a balance between user heterogeneity and user correlations in the recommender system. To solve this problem, we propose a novel algorithm called M-CNB, which utilizes a meta-learner to represent and rapidly adapt to dynamic clusters, along with an informative Upper Confidence Bound (UCB)-based exploration strategy. We provide an instance-dependent performance guarantee for the proposed algorithm that withstands the adversarial context, and we further prove the guarantee is at least as good as state-of-the-art (SOTA) approaches under the same assumptions. In extensive experiments conducted in both recommendation and online classification scenarios, M-CNB outperforms SOTA baselines. This shows the effectiveness of the proposed approach in improving online recommendation and online classification performance.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 64 references that are in the map. First posted on arXiv 10 Aug 2024.

Builds on

40 of 64 references.

References · 40

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2017Neural Collaborative Filteringcited by 1,108
  4. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  5. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  6. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  7. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  8. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  9. 2020Neural Thompson Samplingcited by 127
  10. 2014Online Clustering of Banditscited by 99
  11. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  12. 2019Hierarchically Structured Meta-learningcited by 67
28 more
  1. 2021Meta-Thompson Samplingcited by 62
  2. 2016Distributed Clustering of Linear Bandits in Peer to Peer Networkscited by 50
  3. 2020Latent Bandits Revisitedcited by 43
  4. 2021Bayesian decision-making under misspecified priors with applications to meta-learningcited by 43
  5. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  6. 2021Neural Contextual Bandits without Regretcited by 40
  7. 2019Improved Algorithm on Online Clustering of Banditscited by 38
  8. 2023Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendationcited by 38
  9. 2021Hierarchical Bayesian Banditscited by 33
  10. 2017BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systemscited by 30
  11. 2021Local Clustering in Contextual Multi-Armed Banditscited by 29
  12. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  13. 2021Neural Active Learning with Performance Guaranteescited by 22
  14. 2021Multi-facet Contextual Bandits: A Neural Network Perspectivecited by 20
  15. 2023Graph Neural Banditscited by 20
  16. 2022Learning Neural Contextual Bandits Through Perturbed Rewardscited by 17
  17. 2023Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delaycited by 17
  18. 2019Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matchingcited by 16
  19. 2020Generic Outlier Detection in Multi-Armed Banditcited by 14
  20. 2023Online Clustering of Bandits with Misspecified User Modelscited by 12
  21. 2022Improved Algorithms for Neural Active Learningcited by 11
  22. 2022ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actorcited by 10
  23. 2023Neural Contextual Bandits for Personalized Recommendationcited by 10
  24. 2024Neural Active Learning Beyond Banditscited by 10
  25. 2022Neural Bandit with Arm Group Graphcited by 8
  26. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  27. 2023Contextual Bandits with Online Neural Regressioncited by 7
  28. 2019AutoML for Contextual Banditscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 1.

7 papers.

  1. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 16
  2. 2024PageRank Bandits for Link Predictioncited by 14
  3. 2024PyG-SSL: A Graph Self-Supervised Learning Toolkitcited by 14
  4. 2026Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewardscited by 10
  5. 2025Online Clustering of Dueling Banditscited by 2
  6. 2025Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Modelscited by 2
  7. 2025Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticitycited by 1