mlsanityData to 7 Oct 2026

Neural Bandit with Arm Group Graph

arXiv 2206.03644 ↗First posted 8 Jun 2022cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Contextual bandits aim to identify among a set of arms the optimal one with the highest reward based on their contextual information. Motivated by the fact that the arms usually exhibit group behaviors and the mutual impacts exist among groups, we introduce a new model, Arm Group Graph (AGG), where the nodes represent the groups of arms and the weighted edges formulate the correlations among groups. To leverage the rich information in AGG, we propose a bandit algorithm, AGG-UCB, where the neural networks are designed to estimate rewards, and we propose to utilize graph neural networks (GNN) to learn the representations of arm groups with correlations. To solve the exploitation-exploration dilemma in bandits, we derive a new upper confidence bound (UCB) built on neural networks (exploitation) for exploration. Furthermore, we prove that AGG-UCB can achieve a near-optimal regret bound with over-parameterized neural networks, and provide the convergence analysis of GNN with fully-connected layers which may be of independent interest. In the end, we conduct extensive experiments against state-of-the-art baselines on multiple public data sets, showing the effectiveness of the proposed algorithm.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

28 of 50 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  5. 2019Simplifying Graph Convolutional Networkscited by 1,470
  6. 2017Neural Collaborative Filteringcited by 1,108
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  8. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  9. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  10. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  11. 2019Position-aware Graph Neural Networkscited by 203
  12. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
16 more
  1. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
  2. 2020Neural Thompson Samplingcited by 127
  3. 2015Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challengescited by 113
  4. 2014Online Clustering of Banditscited by 99
  5. 2021Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depthcited by 55
  6. 2017Multi-Task Learning for Contextual Banditscited by 47
  7. 2016On Context-Dependent Clustering of Banditscited by 43
  8. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  9. 2019Improved Algorithm on Online Clustering of Banditscited by 38
  10. 2021Local Clustering in Contextual Multi-Armed Banditscited by 29
  11. 2021Multi-facet Contextual Bandits: A Neural Network Perspectivecited by 20
  12. 2021DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Datacited by 17
  13. 2021From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systemscited by 9
  14. 2021Contextual Bandit Applications in Customer Support Botcited by 7
  15. 2022Neural Collaborative Filtering Bandits via Meta Learningcited by 7
  16. 2020Online Semi-Supervised Learning with Bandit Feedbackcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 1.

8 papers.

  1. 2023Graph Neural Banditscited by 20
  2. 2024PageRank Bandits for Link Predictioncited by 14
  3. 2022Improved Algorithms for Neural Active Learningcited by 11
  4. 2023Neural Contextual Bandits for Personalized Recommendationcited by 10
  5. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  6. 2024Meta Clustering of Neural Banditscited by 7
  7. 2025Generalized Low-Rank Matrix Contextual Bandits with Graph Informationcited by 4
  8. 2024Graph Neural Thompson Samplingcited by 1