Multi-behavior Session-based Recommendation via Graph Reinforcement Learning

Shuo Qin, Feng Lin, Lingxiao Xu, Bowen Deng, Siwen Li, Fangcheng Yang
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1119-1134, 2024.

Abstract

Multi-behavior session-based recommendation (MBSBR) is a critical task in e-commerce and online advertising. By modeling these multiple behaviors, models can better capture the user intent and make more effective recommendations. However, existing models face the challenge of incompletely differentiating between different behavior types, which hinders their ability to fully capture the different tendencies exhibited by each behavior. In addition, most existing multi-behavior methods focus only on predicting a single target behavior and fail to achieve a unified model for predicting the next user-item interaction across multiple behavior types. To address these limitations, we introduce reinforcement learning to the multi-behavior session-based recommendation task and propose a novel approach called the multi-behavior graph reinforcement learning network (MB-GRL). Specifically, we use a graph neural network to encode item transition information from the session graph. Then, we use an attention network to obtain a session representation and generate recommendations based on it. At the same time, we also apply Deep Q-Network (DQN) as a regularizer to improve the recommendation performance for certain behavior types. Experiments on various public benchmark datasets show that MB-GRL outperforms other models for multi-behavior session-based recommendation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-qin24a, title = {Multi-behavior Session-based Recommendation via Graph Reinforcement Learning}, author = {Qin, Shuo and Lin, Feng and Xu, Lingxiao and Deng, Bowen and Li, Siwen and Yang, Fangcheng}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1119--1134}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/qin24a/qin24a.pdf}, url = {https://proceedings.mlr.press/v222/qin24a.html}, abstract = {Multi-behavior session-based recommendation (MBSBR) is a critical task in e-commerce and online advertising. By modeling these multiple behaviors, models can better capture the user intent and make more effective recommendations. However, existing models face the challenge of incompletely differentiating between different behavior types, which hinders their ability to fully capture the different tendencies exhibited by each behavior. In addition, most existing multi-behavior methods focus only on predicting a single target behavior and fail to achieve a unified model for predicting the next user-item interaction across multiple behavior types. To address these limitations, we introduce reinforcement learning to the multi-behavior session-based recommendation task and propose a novel approach called the multi-behavior graph reinforcement learning network (MB-GRL). Specifically, we use a graph neural network to encode item transition information from the session graph. Then, we use an attention network to obtain a session representation and generate recommendations based on it. At the same time, we also apply Deep Q-Network (DQN) as a regularizer to improve the recommendation performance for certain behavior types. Experiments on various public benchmark datasets show that MB-GRL outperforms other models for multi-behavior session-based recommendation.} }
Endnote
%0 Conference Paper %T Multi-behavior Session-based Recommendation via Graph Reinforcement Learning %A Shuo Qin %A Feng Lin %A Lingxiao Xu %A Bowen Deng %A Siwen Li %A Fangcheng Yang %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-qin24a %I PMLR %P 1119--1134 %U https://proceedings.mlr.press/v222/qin24a.html %V 222 %X Multi-behavior session-based recommendation (MBSBR) is a critical task in e-commerce and online advertising. By modeling these multiple behaviors, models can better capture the user intent and make more effective recommendations. However, existing models face the challenge of incompletely differentiating between different behavior types, which hinders their ability to fully capture the different tendencies exhibited by each behavior. In addition, most existing multi-behavior methods focus only on predicting a single target behavior and fail to achieve a unified model for predicting the next user-item interaction across multiple behavior types. To address these limitations, we introduce reinforcement learning to the multi-behavior session-based recommendation task and propose a novel approach called the multi-behavior graph reinforcement learning network (MB-GRL). Specifically, we use a graph neural network to encode item transition information from the session graph. Then, we use an attention network to obtain a session representation and generate recommendations based on it. At the same time, we also apply Deep Q-Network (DQN) as a regularizer to improve the recommendation performance for certain behavior types. Experiments on various public benchmark datasets show that MB-GRL outperforms other models for multi-behavior session-based recommendation.
APA
Qin, S., Lin, F., Xu, L., Deng, B., Li, S. & Yang, F.. (2024). Multi-behavior Session-based Recommendation via Graph Reinforcement Learning. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1119-1134 Available from https://proceedings.mlr.press/v222/qin24a.html.

Related Material