Neural Bandit with Arm Group Graph

Qi, Yunzhe; Ban, Yikun; He, Jingrui

doi:10.1145/3534678.3539312

Cited by 4 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After kernel-based methods [13,30] were used to tackle the kernel-based reward mapping function under the non-linear settings, neural algorithms [5,41,43] have been proposed to utilize neural networks to estimate the reward function and confidence bound. Meanwhile, AGG-UCB [26] adopts GNN to model the arm group correlations. GCN-UCB [29] manages to apply the GNN model to embed arm contexts for the downstream linear regression, and GNN-PE [21] utilizes the UCB based on information gains to achieve exploration for classification tasks on graphs.…”

Section: Related Workmentioning

confidence: 99%

“…𝑢 ) inspired by [7]. As it has proved that the confidence interval (uncertainty) of reward estimation can be expressed as a function of network gradients [26,43], we apply 𝑓 𝑖,𝑡 and two user nodes 𝑢, 𝑢 ′ , we let the edge weight be…”

Section: User Graph Estimation With User Networkmentioning

confidence: 99%

“…Remark 5.3 (Dimension terms 𝑑, d). Existing neural single-bandit (i.e., with no user collaborations) algorithms [26,41,43] keep the bound of O ( d√ 𝑇 log(𝑇 )) based on gradient mappings and ridge regression. d is the effective dimension of the NTK matrix, which can grow along with the number of parameters 𝑝 and rounds 𝑇 .…”

Section: Theoretical Analysismentioning

confidence: 99%

See 2 more Smart Citations

Graph Neural Bandits

Ban

2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Contextual bandits algorithms aim to choose the optimal arm with the highest reward out of a set of candidates based on the contextual information. Various bandit algorithms have been applied to realworld applications due to their ability of tackling the exploitationexploration dilemma. Motivated by online recommendation scenarios, in this paper, we propose a framework named Graph Neural Bandits (GNB) to leverage the collaborative nature among users empowered by graph neural networks (GNNs). Instead of estimating rigid user clusters as in existing works, we model the "fine-grained" collaborative effects through estimated user graphs in terms of exploitation and exploration respectively. Then, to refine the recommendation strategy, we utilize separate GNN-based models on estimated user graphs for exploitation and adaptive exploration. Theoretical analysis and experimental results on multiple real data sets in comparison with state-of-the-art baselines are provided to demonstrate the effectiveness of our proposed framework.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: User Graph Estimation With User Networkmentioning

confidence: 99%

Section: Theoretical Analysismentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Bandits

Ban

2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…In contrast, our goal is to derive an NN-based algorithm in the non-parametric setting that performs well both empirically and theoretically. Neural contextual bandits [57,55,14,12,13,41] provide the principled method to balance between the exploitation and exploration [10,11]. [50] transforms active learning into neural contextual bandit problem and obtains a performance guarantee, of which limitations are discussed above.…”

Section: Related Workmentioning

confidence: 99%

Improved Algorithms for Neural Active Learning

Ban¹,

Zhang²,

Tong³

et al. 2022

Preprint

View full text Add to dashboard Cite

We improve the theoretical and empirical performance of neural-network(NN)based active learning algorithms for the non-parametric streaming setting. In particular, we introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for k-class classification problems with the performance guarantee, utilizes the full feedback, and updates parameters in a more practical and efficient manner. These careful designs lead to a better regret upper bound, improving by a multiplicative factor O(log T ) and removing the curse of input dimensionality. Furthermore, we show that the algorithm can achieve the same performance as the Bayes-optimal classifier in the long run under the hard-margin setting in classification problems. In the end, we use extensive experiments to evaluate the proposed algorithm and SOTA baselines, to show the improved empirical performance.

show abstract

Neural Contextual Bandits for Personalized Recommendation

Ban,

Qi,

2024

Companion Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

Neural Bandit with Arm Group Graph

Cited by 4 publications

References 8 publications

Graph Neural Bandits

Graph Neural Bandits

Improved Algorithms for Neural Active Learning

Neural Contextual Bandits for Personalized Recommendation

Contact Info

Product

Resources

About