2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

融合属性偏好和多阶交互信息的可解释评分预测研究

郑建兴 李沁文 王素格 李德玉

郑建兴, 李沁文, 王素格, 李德玉. 融合属性偏好和多阶交互信息的可解释评分预测研究. 自动化学报, 2024, 50(11): 2231−2244 doi: 10.16383/j.aas.c210457
引用本文: 郑建兴, 李沁文, 王素格, 李德玉. 融合属性偏好和多阶交互信息的可解释评分预测研究. 自动化学报, 2024, 50(11): 2231−2244 doi: 10.16383/j.aas.c210457
Zheng Jian-Xing, Li Qin-Wen, Wang Su-Ge, Li De-Yu. Research on explainable rating prediction by fusing attribute preference and multi-order interaction information. Acta Automatica Sinica, 2024, 50(11): 2231−2244 doi: 10.16383/j.aas.c210457
Citation: Zheng Jian-Xing, Li Qin-Wen, Wang Su-Ge, Li De-Yu. Research on explainable rating prediction by fusing attribute preference and multi-order interaction information. Acta Automatica Sinica, 2024, 50(11): 2231−2244 doi: 10.16383/j.aas.c210457

融合属性偏好和多阶交互信息的可解释评分预测研究

doi: 10.16383/j.aas.c210457 cstr: 32138.14.j.aas.c210457
基金项目: 国家自然科学基金(61632011, 62076158, 62072294, 61603229), 山西省自然科学基金(20210302123468)资助
详细信息
    作者简介:

    郑建兴:山西大学智能信息处理研究所副教授. 主要研究方向为自然语言处理, 推荐系统. E-mail: jxzheng@sxu.edu.cn

    李沁文:山西大学计算机与信息技术学院硕士研究生. 主要研究方向为自然语言处理, 推荐系统. E-mail: 201922404015@email.sxu.edu.cn

    王素格:山西大学智能信息处理研究所教授. 主要研究方向为自然语言处理, 情感分析. 本文通信作者. E-mail: wsg@sxu.edu.cn

    李德玉:山西大学智能信息处理研究所教授. 主要研究方向为数据挖掘. E-mail: lidy@sxu.edu.cn

Research on Explainable Rating Prediction by Fusing Attribute Preference and Multi-order Interaction Information

Funds: Supported by National Natural Science Foundation of China (61632011, 62076158, 62072294, 61603229) and Natural Science Foundation of Shanxi Province (20210302123468)
More Information
    Author Bio:

    ZHENG Jian-Xing Associate professor at the Institute of Intelligent Information Processing, Shanxi University. His research interest covers natural language processing and recommender systems

    LI Qin-Wen Master student at the School of Computer and Information Technology, Shanxi University. His research interest covers natural language processing and recommender systems

    WANG Su-Ge Professor at the Institute of Intelligent Information Processing, Shanxi University. Her research interest covers natural language processing and sentiment analysis. Corresponding author of this paper

    LI De-Yu Professor at the Institute of Intelligent Information Processing, Shanxi University. His main research interest is data mining

  • 摘要: 已有推荐系统主要基于用户−项目交互矩阵来学习用户和项目的向量表示, 而当交互矩阵稀疏时, 推荐系统的精度较低, 推荐的结果缺乏可解释性. 考虑到用户−项目交互行为中的评分标签信息, 提出了一种融合属性偏好和多阶交互信息的可解释评分预测方法, 并根据属性偏好对推荐结果进行解释. 首先, 基于注意力机制分析了用户和项目属性信息与评分标签的关系, 建模了节点的属性偏好特征表示; 然后, 聚合了用户−项目交互矩阵中节点自身、交互邻居和评分标签信息, 通过图神经网络学习了节点的多阶交互行为特征表示; 最后, 融合了节点的属性偏好特征和交互行为特征, 在异质类型信息空间下学习了用户和项目的语义特征表示, 利用多层感知机实现了评分预测, 并在MovieLens和Douban数据集上验证了方法的有效性. 实验结果表明, 所提方法在平均绝对误差(Mean absolute error, MAE)和均方根误差(Root mean square error, RMSE)指标上有效提高了推荐系统的精度, 缓解了数据稀疏场景下推荐模型性能较低的问题, 提升了推荐结果的可解释性.
    1)  11 https://grouplens.org/datasets/movielens/2 https://movie.douban.com/
    2)  22 https://movie.douban.com/
  • 图  1  融合属性偏好和多阶交互信息的评分预测

    Fig.  1  Rating prediction by fusing attribute preference and multi-order interaction information

    图  2  高阶交互邻居的信息传播

    Fig.  2  Information diffusion of higher-order interaction neighbors

    图  3  几种方法在ML-L-S数据集上不同稀疏性的MAE结果

    Fig.  3  MAE results of different methods on ML-L-S dataset with different sparsities

    图  4  几种方法在ML-L-S数据集上不同稀疏性的RMSE结果

    Fig.  4  RMSE results of different methods on ML-L-S dataset with different sparsities

    图  5  几种方法在ML-1M数据集上不同稀疏性的MAE结果

    Fig.  5  MAE results of different methods on ML-1M dataset with different sparsities

    图  6  几种方法在ML-1M数据集上不同稀疏性的RMSE结果

    Fig.  6  RMSE results of different methods on ML-1M dataset with different sparsities

    图  7  几种方法在Douban数据集上不同稀疏性的MAE结果

    Fig.  7  MAE results of different methods on Douban dataset with different sparsities

    图  8  几种方法在Douban数据集上不同稀疏性的RMSE结果

    Fig.  8  RMSE results of different methods on Douban dataset with different sparsities

    图  9  用户和电影的评分预测可解释案例

    Fig.  9  Explainable example of rating prediction for users and movies

    图  10  ML-1M数据集上的用户和电影节点嵌入表示(转换前)

    Fig.  10  The embedding representation of user and movie nodes on ML-1M dataset (before transformation)

    图  11  ML-1M数据集上的用户和电影节点嵌入表示(转换后)

    Fig.  11  The embedding representation of user and movie nodes on ML-1M dataset (after transformation)

    图  12  ML-L-S数据集上的用户和电影节点嵌入表示(转换前)

    Fig.  12  The embedding representation of user and movie nodes on ML-L-S dataset (before transformation)

    图  13  ML-L-S数据集上的用户和电影节点嵌入表示(转换后)

    Fig.  13  The embedding representation of user and movie nodes on ML-L-S dataset (after transformation)

    图  14  Douban数据集上的用户和电影节点嵌入表示(转换前)

    Fig.  14  The embedding representation of user and movie nodes on Douban dataset (before transformation)

    图  15  Douban数据集上的用户和电影节点嵌入表示(转换后)

    Fig.  15  The embedding representation of user and movie nodes on Douban dataset (after transformation)

    表  1  实验数据集统计信息

    Table  1  Statistical information of experimental datasets

    数据库用户数项目数交互数评分等级稀疏度(%)
    ML-L-S61097241008360.5 ~ 5.098.30
    ML-1M6040388310002091.0 ~ 5.095.74
    Douban302269711954931.0 ~ 5.099.07
    下载: 导出CSV

    表  2  不同方法在三组数据集上的MAE和RMSE结果

    Table  2  MAE and RMSE results of different methods on three datasets

    方法ML-L-S ML-1M Douban
    MAERMSEMAERMSEMAERMSE
    UserKNN0.875 21.278 4 0.771 00.969 3 0.649 40.825 6
    ItemKNN0.680 80.886 90.739 40.925 70.697 40.872 8
    BiasedMF0.676 90.882 40.684 50.872 40.577 50.728 4
    SVD++0.672 40.877 00.672 90.863 30.569 00.720 0
    NCF0.668 50.868 00.695 60.886 60.578 10.730 4
    AFM0.665 10.867 30.688 00.873 90.564 30.713 6
    Wide&Deep0.674 20.875 40.686 30.873 50.565 40.714 1
    ACCM0.662 80.865 70.673 40.856 60.578 90.730 1
    NGCF0.664 70.866 40.682 10.869 00.576 80.727 1
    LightGCN0.662 60.861 10.675 90.857 80.570 90.721 3
    AFN0.657 90.852 50.678 00.860 40.565 50.715 2
    IncorAtt-
    MOIntRec
    0.645 1*0.837 2*0.659 4**0.843 3**0.558 30.708 0
    注: 加粗字体表示各列最优结果; 下划线字体表示各列次优结果. “*”表示p值小于0.05; “**”表示p值小于0.01.
    下载: 导出CSV

    表  3  IncorAttMOIntRec方法在不同嵌入维度下的MAE和RMSE结果

    Table  3  MAE and RMSE results for IncorAttMOIntRec method with different embedding dimension sizes

    嵌入维度ML-L-S ML-1M Douban
    MAERMSEMAERMSEMAERMSE
    640.650 30.847 9 0.662 20.849 7 0.558 30.708 0
    1280.645 10.837 20.659 50.844 60.563 70.711 7
    2560.648 80.844 00.659 40.843 30.568 50.717 2
    5120.651 60.849 30.662 60.845 70.576 60.723 1
    注: 加粗字体表示各列最优结果.
    下载: 导出CSV

    表  4  IncorAttMOIntRec方法在不同注意力维度下的MAE和RMSE结果

    Table  4  MAE and RMSE results for IncorAttMOIntRec method with different attention dimension sizes

    注意力维度ML-L-S ML-1M Douban
    MAERMSEMAERMSEMAERMSE
    320.653 20.848 7 0.666 20.847 5 0.566 20.714 7
    640.645 10.837 20.657 10.846 30.558 30.708 0
    1280.648 60.842 40.659 40.843 30.566 90.718 6
    2560.650 20.846 10.659 20.845 90.573 10.722 6
    注: 加粗字体表示各列最优结果.
    下载: 导出CSV

    表  5  三组数据集上的IncorAttMOIntRec方法消融研究

    Table  5  Ablation study of IncorAttMOIntRec method on three datasets

    变体模型ML-L-S ML-1MDouban
    MAERMSEMAERMSEMAERMSE
    去掉Rating-tag0.653 80.854 70.667 90.847 70.568 30.713 4
    去掉Multi-order
    interaction
    0.688 40.890 10.680 20.866 70.574 60.722 8
    去掉Att-preference0.656 20.854 90.668 90.848 60.569 50.717 6
    去掉Interaction0.700 70.908 70.738 10.924 50.580 30.731 9
    去掉MLP-
    outputlayer
    0.667 50.873 60.710 50.896 20.568 40.713 7
    IncorAttMOIntRec0.645 10.837 20.659 40.843 30.558 30.708 0
    注: 加粗字体表示各列最优结果.
    下载: 导出CSV
  • [1] 汤文兵, 任正云, 韩芳. 基于注意力机制的协同卷积动态推荐网络. 自动化学报, 2021, 47(10): 2438−2448

    Tang Wen-Bing, Ren Zheng-Yun, Han Fang. Attention-based collaborative convolutional dynamic network for recommendation. Acta Automatica Sinica, 2021, 47(10): 2438−2448
    [2] Zhang Y F, Chen X. Explainable recommendation: A survey and new perspectives. Foundations and Trends in Information Retrieval, 2020, 14(1): 1−101
    [3] Lops P, De Gemmis M, Semeraro G. Content-based recommender systems: State of the art and trends. Recommender Systems Handbook. New York: Springer, 2011. 73−105
    [4] 潘涛涛, 文峰, 刘勤让. 基于矩阵填充和物品可预测性的协同过滤算法. 自动化学报, 2017, 43(9): 1597−1606

    Pan Tao-Tao, Wen Feng, Liu Qin-Rang. Collaborative filtering recommendation algorithm based on rating matrix filling and item predictability. Acta Automatica Sinica, 2017, 43(9): 1597−1606
    [5] Shi S Y, Zhang M, Liu Y Q, Ma S P. Attention-based adaptive model to unify warm and cold starts recommendation. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Torino, Italy: ACM, 2018. 127−136
    [6] Wu L, Yang Y H, Zhang K, Hong R C, Fu Y J, Wang M. Joint item recommendation and attribute inference: An adaptive graph convolutional network approach. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi'an, China: ACM, 2020. 679−688
    [7] Deshpande M, Karypis, G. Item-based top-N recommendation algorithms. ACM Transactions on Information Systems, 2004, 22(1): 143−177 doi: 10.1145/963770.963776
    [8] Konstan J A, Miller B N, Maltz D, Herlocker J L, Riedl J. GroupLens: Applying collaborative filtering to Usenet news. Communications of the ACM, 1997, 40(3): 77−87 doi: 10.1145/245108.245126
    [9] Adomavicius G, Tuzhilin A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734−749 doi: 10.1109/TKDE.2005.99
    [10] Herlocker J L, Konstan J A, Terveen L G, Riedl J T. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems, 2004, 22(1): 5−53 doi: 10.1145/963770.963772
    [11] Koren Y. Factorization meets the neighborhood: A multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Las Vegas, USA: ACM, 2008. 426−434
    [12] Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems. Computer, 2009, 42(8): 30−37
    [13] Salakhutdinov R, Mnih A. Probabilistic matrix factorization. In: Proceedings of the 20th International Conference on Neural Information Processing Systems. Vancouver, Canada: ACM, 2007. 1257−1264
    [14] Salakhutdinov R, Mnih A. Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In: Proceedings of the 25th International Conference on Machine Learning. Helsinki, Finland: ACM, 2008. 880−887
    [15] Lee J, Kim S, Lebanon G, Singer Y, Bengio S. LLORMA: Local low-rank matrix approximation. Journal of Machine Learning Research, 2016, 17: 1−24
    [16] Zhang Y F, Lai G K, Zhang M, Zhang Y, Liu Y Q, Ma S P. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In: Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval. Gold Coast, Australia: ACM, 2014. 83−92
    [17] Ren Z C, Liang S S, Li P J, Wang S Q, De Rijke M. Social collaborative viewpoint regression with explainable recommendations. In: Proceedings of the 10th ACM International Conference on Web Search and Data Mining. Cambridge, UK: ACM, 2017. 485−494
    [18] Chen X, Qin Z, Zhang Y F, Xu T. Learning to rank features for recommendation over multiple categories. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval. Pisa, Italy: ACM, 2016. 305−314
    [19] Tan Y Z, Zhang M, Liu Y Q, Ma S P. Rating-boosted latent topics: Understanding users and items with ratings and reviews. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2016. 2640−2646
    [20] Zhao K Q, Cong G, Yuan Q, Zhu K Q. SAR: A sentiment-aspect-region model for user preference analysis in geo-tagged reviews. In: Proceedings of the 31st International Conference on Data Engineering. Seoul, South Korea: IEEE, 2015. 675−686
    [21] Zhang S, Yao L N, Sun A X, Tay Y. Deep learning based recommender system: A survey and new perspectives. ACM Computing Surveys, 2020, 52(1): Article No. 5
    [22] Xiao J, Ye H, He X N, Zhang H W, Wu F, Chua T S. Attentional factorization machines: Learning the weight of feature interactions via attention networks. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne, Australia: ACM, 2017. 3119−3125
    [23] Cheng H T, Koc L, Harmsen J, Shaked T, Chandra T, Aradhye H, et al. Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. Boston, USA: ACM, 2016. 7−10
    [24] Wang X, He X N, Wang M, Feng F L, Chua T S. Neural graph collaborative filtering. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris, France: ACM, 2019. 165−174
    [25] Yang Z X, Dong S B. HAGERec: Hierarchical attention graph convolutional network incorporating knowledge graph for explainable recommendation. Knowledge-Based Systems, 2020, 204: Article No. 106194 doi: 10.1016/j.knosys.2020.106194
    [26] He X N, Liao L Z, Zhang H W, Nie L Q, Hu X, Chua T S. Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web. Perth, Australia: 2017. 173−182
    [27] Lian J X, Zhou X H, Zhang F Z, Chen Z X, Xie X, Sun G Z. xDeepFM: Combining explicit and implicit feature interactions for recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London, UK: ACM, 2018. 1754−1763
    [28] Chang S, Harper F M, Terveen L G. Crowd-based personalized natural language explanations for recommendations. In: Proceedings of the 10th ACM Conference on Recommender Systems. Boston, USA: ACM, 2016. 175−182
    [29] Seo S, Huang J, Yang H, Liu Y. Interpretable convolutional neural networks with dual local and global attention for review rating prediction. In: Proceedings of the 11th ACM Conference on Recommender Systems. Como, Italy: ACM, 2017. 297−305
    [30] Chen C, Zhang M, Liu Y Q, Ma S P. Neural attentional rating regression with review-level explanations. In: Proceedings of the World Wide Web Conference. Lyon, France: ACM, 2018. 1583−1592
    [31] 冯永, 陈以刚, 强保华. 融合社交因素和评论文本卷积网络模型的汽车推荐研究. 自动化学报, 2019, 45(3): 518−529

    Feng Yong, Chen Yi-Gang, Qiang Bao-Hua. Social and comment text CNN model based automobile recommendation. Acta Automatica Sinica, 2019, 45(3): 518−529
    [32] Li P J, Wang Z H, Ren Z C, Bing L D, Lam W. Neural rating regression with abstractive tips generation for recommendation. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. Shinjuku, Japan: ACM, 2017. 345−354
    [33] Chen X, Zhang Y F, Xu H T, Qin Z, Zha H Y. Adversarial distillation for efficient recommendation with external knowledge. ACM Transactions on Information Systems, 2019, 37(1): Article No. 12
    [34] 饶子昀, 张毅, 刘俊涛, 曹万华. 应用知识图谱的推荐方法与系统. 自动化学报, 2021, 47(9): 2061−2077

    Rao Zi-Yun, Zhang Yi, Liu Jun-Tao, Cao Wan-Hua. Recommendation methods and systems using knowledge graph. Acta Automatica Sinica, 2021, 47(9): 2061−2077
    [35] Wang H W, Zhao M, Xie X, Li W J, Guo M Y. Knowledge graph convolutional networks for recommender systems. In: Proceedings of the World Wide Web Conference. San Francisco, USA: ACM, 2019. 3307−3313
    [36] Wang X, He X N, Cao Y X, Liu M, Chua T S. KGAT: Knowledge graph attention network for recommendation. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Anchorage, USA: ACM, 2019. 950−958
    [37] Ying R, He R N, Chen K F, Eksombatchai P, Hamilton W L, Leskovec J. Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London, UK: ACM, 2018. 974−983
    [38] He X N, Deng K, Wang X, Li Y, Zhang Y D, Wang M. LightGCN: Simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi'an, China: ACM, 2020. 639−648
    [39] Jin B W, Gao C, He X N, Jin D P, Li Y. Multi-behavior recommendation with graph convolutional networks. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi'an, China: ACM, 2020. 659−668
    [40] Yao Q M, Chen X N, Kwok J T, Li Y, Hsieh C J. Efficient neural interaction function search for collaborative filtering. In: Proceedings of the World Wide Web Conference. Taipei, China: ACM, 2020. 1660−1670
    [41] Zheng J, Liu J, Shi C, Zhuang F Z, Li J Z, Wu B. Dual similarity regularization for recommendation. In: Proceedings of the 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining. Auckland, New Zealand: Springer, 2016. 542−554
    [42] Cheng W Y, Shen Y Y, Huang L P. Adaptive factorization network: Learning adaptive-order feature interactions. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2020. 3609−3616
  • 加载中
图(15) / 表(5)
计量
  • 文章访问数:  900
  • HTML全文浏览量:  385
  • PDF下载量:  62
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-05-25
  • 录用日期:  2021-08-12
  • 网络出版日期:  2022-01-08
  • 刊出日期:  2024-11-26

目录

    /

    返回文章
    返回