mlsanityData to 7 Oct 2026

Neural Collaborative Filtering Bandits via Meta Learning

arXiv 2201.13395 ↗First posted 31 Jan 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Contextual multi-armed bandits provide powerful tools to solve the exploitation-exploration dilemma in decision making, with direct applications in the personalized recommendation. In fact, collaborative effects among users carry the significant potential to improve the recommendation. In this paper, we introduce and study the problem by exploring `Neural Collaborative Filtering Bandits', where the rewards can be non-linear functions and groups are formed dynamically given different specific contents. To solve this problem, inspired by meta-learning, we propose Meta-Ban (meta-bandits), where a meta-learner is designed to represent and rapidly adapt to dynamic groups, along with a UCB-based exploration strategy. Furthermore, we analyze that Meta-Ban can achieve the regret bound of O(√T log T), improving a multiplicative factor √log T over state-of-the-art related works. In the end, we conduct extensive experiments showing that Meta-Ban significantly outperforms six strong baselines.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

19 of 39 references.

References · 19

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  3. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  4. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  5. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  6. 2020Neural Thompson Samplingcited by 127
  7. 2014Online Clustering of Banditscited by 99
  8. 2019Hierarchically Structured Meta-learningcited by 67
  9. 2016Distributed Clustering of Linear Bandits in Peer to Peer Networkscited by 50
  10. 2017Multi-Task Learning for Contextual Banditscited by 47
  11. 2016On Context-Dependent Clustering of Banditscited by 43
  12. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
7 more
  1. 2019Improved Algorithm on Online Clustering of Banditscited by 38
  2. 2017BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systemscited by 30
  3. 2021Local Clustering in Contextual Multi-Armed Banditscited by 29
  4. 2014A Neural Networks Committee for the Contextual Bandit Problemcited by 23
  5. 2020On the Global Optimality of Model-Agnostic Meta-Learningcited by 21
  6. 2021Multi-facet Contextual Bandits: A Neural Network Perspectivecited by 20
  7. 2020Generic Outlier Detection in Multi-Armed Banditcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1.

7 papers.

  1. 2023Graph Neural Banditscited by 20
  2. 2022Comprehensive Fair Meta-learned Recommender Systemcited by 18
  3. 2022Improved Algorithms for Neural Active Learningcited by 11
  4. 2023Optimal Algorithms for Latent Bandits with Cluster Structurecited by 11
  5. 2023Neural Contextual Bandits for Personalized Recommendationcited by 10
  6. 2024Neural Active Learning Beyond Banditscited by 10
  7. 2022Neural Bandit with Arm Group Graphcited by 8