基于解耦图卷积网络的协同过滤推荐模型

李驰,游小钰,张谧

PDF(4925 KB)
PDF(4925 KB)
中文信息学报 ›› 2023, Vol. 37 ›› Issue (11) : 131-141.
信息检索

基于解耦图卷积网络的协同过滤推荐模型

  • 李驰,游小钰,张谧
作者信息 +

Decoupled Graph Convolution Network for Collaborative Filtering

  • LI Chi, YOU Xiaoyu, ZHANG Mi
Author information +
History +

摘要

图卷积网络(GCN)可以缓解传统推荐算法数据稀疏的问题,有效提高推荐准确度,被广泛应用于各种推荐任务中。但是现有基于GCN的推荐模型还存在计算开销大的问题。因此,该文提出了一种基于解耦图卷积网络的协同过滤推荐模型(DeGCF)。首先,在模型参数初始化阶段,DeGCF利用负采样增强的图卷积操作,显式地为用户和物品的初始嵌入向量注入局部和全局图结构特征;其次,在模型训练阶段DeGCF仅使用用户和物品的嵌入向量的内积作为模型的输出,实现图卷积操作与模型训练过程的解耦;最后,DeGCF使用逆倾向分数加权的损失函数训练模型参数。在三个基准数据集上的实验结果显示,该方法性能显著超过现有方法,在Amazon-book数据集上相较于LightGCN模型Recall指标提高了31%,训练效率提升了13倍,避免了五百余万次的全图矩阵计算。

Abstract

Graph convolutional network (GCN) based recommender models represent the state-of-the-art of collaborative recommendation, though defected in high computation costs. This paper proposes a collaborative filtering recommendation model based on decoupled graph convolutional network (DeGCF). For the parameter initialization, DeGCF utilizes negative samples-enhanced graph convolution to explicitly inject local and global graph structure features into the initial embedding of users and items. As for the model training, DeGCF only uses the inner product of the embedding vectors of users and items as the model outputs, thereby decoupling the graph convolution from the model training process. In addition, DeGCF trains model parameters using an inverse propensity score reweighted loss function. Experiments on three benchmark datasets demonstrate that the proposed model not only outperforms the state-of-the-art GCN models, but also achieves more than 13x speedup than LightGCN on large-scale datasets like Amazon-book.

关键词

解耦图卷积网络 / 协同过滤 / 推荐系统

Key words

decoupled graph convolution network / collaborative filtering / recommender system

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
李驰,游小钰,张谧. 基于解耦图卷积网络的协同过滤推荐模型. 中文信息学报. 2023, 37(11): 131-141
LI Chi, YOU Xiaoyu, ZHANG Mi. Decoupled Graph Convolution Network for Collaborative Filtering. Journal of Chinese Information Processing. 2023, 37(11): 131-141

参考文献

[1] 冷亚军,陆青,梁昌勇.协同过滤推荐技术综述[J].模式识别与人工智能,2014,27(8): 720-734.
[2] KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30-37.
[3] HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web, 2017: 173-182.
[4] SEDHAIN S, MENON A K, SANNER S, et al. Autorec: Autoencoders meet collaborative filtering[C]//Proceedings of the 24th International Conference on World Wide Web, 2015: 111-112.
[5] 徐冰冰,岑科廷,黄俊杰,等.图卷积神经网络综述[J]. 计算机学报,2020,43(5): 755-780.
[6] 葛尧,陈松灿.面向推荐系统的图卷积网络[J].软件学报, 2020, 31(4): 12.
[7] 王磊,熊于宁,李云鹏,等.基于增强图卷积神经网络的协同推荐模型[J].计算机研究与发展,2020: 1-9.
[8] WU S, SUN F, ZHANG W, et al. Graph neural networks in recommender systems: A survey[C]//Proceedings of the ACM computing surveys, 2022.
[9] HE X, DENG K, WANG X, et al. Lightgcn: Simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 639-648.
[10] HAMILTON W, YING Z, LESKOVEC J. Inductive representation learning on large graphs[C]//Proceedings of Advances in Neural Information Processing Systems, 2017: 1024-1034.
[11] CHEN J, MA T, XIAO C. Fastgcn: Fast learning with graphconvolutional networks via importance sampling[C]//Proceedings of the 6th International Conference on Learning Representations, 2018.
[12] CHIANG W L, LIU X, SI S, et al. Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 257-266.
[13] ZENG H, ZHOU H, SRIVASTAVA A, et al. Graphsaint: Graph sampling based inductive learning method[J/OL]. arXiv preprint arXiv: 1907.04931, 2019.
[14] WU F, SOUZA A, ZHANG T, et al. Simplifying graph convolutional networks[C]//Proceedings of the International Conference on Machine Learning. PMLR, 2019: 6861-6871.
[15] FRASCA F, ROSSI E, EYNARD D, et al. Sign: Scalable inception graph neural networks[J/OL]. arXiv preprint arXiv: 2004.11198, 2020.
[16] SUN C, GU H, HU J. Scalable and adaptive graph neural networks with self-label-enhanced training[J/OL]. arXiv preprint arXiv: 2104.09376, 2021.
[17] ZHU H, KONIUSZ P. Simple spectral graph convolution[C]//Proceedings of the 9th International Conference on Learning Representations, 2020.
[18] CHEN M, WEI Z, DING B, et al. Scalable graph neural networks via bidirectional propagation[J]. Advances in Neural Information Processing Systems, 2020, 33: 14556-14566.
[19] ZHANG W, SHEN Y, LIN Z, et al. Gmlp: Building scalable and flexible graph neural networks with feature-message passing[J/OL]. arXiv preprint arXiv: 2104.09880, 2021.
[20] ZHANG W, YIN Z, SHENG Z, et al. Graph attention multi-layer perceptron[J/OL]. arXiv preprint arXiv: 2108.10097, 2021.
[21] ZHANG W, SHEN Y, LIN Z, et al. PaSca: A graph neural architecture search system under the scalable paradigm[C]//Proceedings of the ACM Web Conference, 2022: 1817-1828.
[22] BERG R, KIPF T N, WELLING M. Graph convolutional matrix completion[J/OL]. arXiv preprint arXiv: 1706.02263, 2017.
[23] WANG X, HE X, WANG M, et al. Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 165-174.
[24] CHEN L, WU L, HONG R, et al. Revisiting graph based collaborative filtering: A linear residual graph convolutional network approach[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(01): 27-34.
[25] WANG X, JIN H, ZHANG A, et al. Disentangled graph collaborative filtering[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 1001-1010.
[26] WU J, WANG X, FENG F, et al. Self-supervised graph learning for recommendation[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 726-735.
[27] FAN W, MA Y, LI Q, et al. Graph neural networks for social recommendation[C]//Proceedings of the 28th International Conference on World Wide Web, 2019: 417-426.
[28] JIN B, GAO C, HE X, et al. Multi-behavior recommendation with graph convolutional networks[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 659-668.
[29] GUO Q, ZHUANG F, QIN C, et al. A survey on knowledge graph-based recommender systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2020: 1-10.
[30] YING R, HE R, CHEN K, et al. Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 974-983.
[31] YANG Z, DING M, ZHOU C, et al. Understanding negative sampling in graph representation learning[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020: 1666-1676.
[32] DUAN W, XUAN J, QIAO M, et al. Learning from the dark: boosting graph convolutional neural networks with diverse negative samples [C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022.
[33] JOHNSON W B, LINDENSTRAUSS J. Extensions of Lipschitz mappings into a Hilbert space[J]. Contemporary Mathematics, 1984, 26: 28-35.
[34] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and locally connected networks on graphs[J/OL]. arXiv preprint arXiv: 1312.6203, 2013.
[35] CHEN J, DONG H, WANG X, et al. Bias and debias in recommender system: A survey and future directions[J/OL]. arXiv preprint arXiv: 2010.03240, 2020.
[36] TANG X, YAO H, SUN Y, et al. Investigating and mitigating degree-related biases in graph convoltuional networks[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020: 1435-1444.
[37] SCHNABEL T, SWAMINATHAN A, SINGH A, et al. Recommendations as treatments: Debiasing learning and evaluation[C]//Proceedings of the International Conference on Machine Learning. PMLR, 2016: 1670-1679.
[38] KINGMA D P, BA J. Adam: A method for stochastic optimization[J/OL]. arXiv preprint arXiv: 1412.6980, 2014.
[39] FENG Y, HU B, LV F, et al. Atbrg: Adaptive target-behavior relational graph network for effective recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval,2020: 2231-2240.

基金

国家重点研发计划(SQ2021YFB3100017);国家自然科学基金(61972099);上海自然科学基金(19ZR1404800)
PDF(4925 KB)

548

Accesses

0

Citation

Detail
段落导航
相关文章

  • 版权所有 © 《中文信息学报》编辑部 网站统计

    地址：北京市海淀区中关村南四街4号　邮编：100190　电话：010-62562916　E-mail：cips@iscas.ac.cn

    本系统由北京玛格泰克科技发展有限公司设计开发

/

〈 〉