极深因子分解机（eXtreme deep factorization machine,xDeepFM）是一种基于上下文感知的推荐模型，它提出了一种压缩交叉网络对特征进行阶数可控的特征交叉，并将该网络与深度神经网络进行结合以优化推荐效果。为了进一步提升xDeepFM在推荐场景下的表现，提出一种基于场因子分解的xDeepFM改进模型。该模型通过场信息增强了特征的表达能力，并建立了多个交叉压缩网络以学习高阶组合特征。最后分析了用户场、项目场设定的合理性，并在3个不同规模的MovieLens系列数据集上通过受试者工作特征曲线下面积、对数似然损失指标进行性能评估，验证了该改进模型的有效性。
The eXtreme deep factorization machine (xDeepFM) is a context-aware recommendation model integrating a compressed interaction network for controllable feature cross-ordering. The network is combined with deep neural network to optimize the recommendation performance. To further improve xDeepFM’s performance in recommended scenarios, eXtreme deep field factorization machine (xDeepFFM) is proposed in this paper. The improved model enhances feature expression capabilities through field information and uses multiple compressed interaction networks to learn higher-order combinatorial features based on field information. Furthermore, this paper analyzes the rationality of the setting of user field and item field. The effectiveness of the improved model is evaluated using area under curve and Log-likelihood loss metrics on three public datasets of different sizes.
[1] Goldberg D, Nichols D, Oki B M, et al. Using collaborative filtering to weave an information tapestry [J]. Communications of the ACM, 1992, 35(12): 61-70.
[2] Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems [J]. Computer, 2009, 42(8): 30-37.
[3] Sedhain S, Menon A K, Sanner S, et al. Autorec: autoencoders meet collaborative filtering [C]//The 24th International Conference on World Wide Web, 2015: 111-112.
[4] Shan Y, Hoens T R, Jiao J, et al. Deep crossing: web-scale modeling without manually crafted combinatorial features [C]//The 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2016: 255-262.
[5] He X N, Liao L Z, Zhang H W, et al. Neural collaborative filtering [C]//The 26th International Conference on World Wide Web, 2017: 173-182.
[6] Qu Y R, Cai H, Ren K, et al. Product-based neural networks for user response prediction [C]//IEEE 16th International Conference on Data Mining (ICDM), 2016: 1149-1154.
[7] Cheng H T, Koc L, Harmsen J, et al. Wide & deep learning for recommender systems [C]//The 1st Workshop on Deep Learning for Recommender Systems, 2016: 7-10.
[8] Guo H F, Tang R M, Ye Y M, et al. DeepFM: a factorization-machine based neural network for CTR prediction [DB/OL]. 2017[2021-12-15]. http: //arxiv.org/abs/1703.04247.
[9] Guo Q Y, Zhuang F Z, Qin C, et al. A survey on knowledge graph-based recommender systems [J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3549-3568.
[10] Sun R, Cao X Z, Zhao Y, et al. Multi-modal knowledge graphs for recommender systems [C]//The 29th ACM International Conference on Information & Knowledge Management, 2020: 1405-1414.
[11] Zhao W X, Mu S L, Hou Y P, et al. RecBole: towards a unified, comprehensive and efficient framework for recommendation algorithms [DB/OL]. 2020[2021-12-15]. https://arxiv.org/abs/2011.01731.
[12] Zhou K, Wang H, Zhao W X, et al. S3-rec: self-supervised learning for sequential recommendation with mutual information maximization [C]//The 29th ACM International Conference on Information & Knowledge Management, 2020: 1893-1902.
[13] Zhou G, Mou N, Fan Y, et al. Deep interest evolution network for click-through rate prediction [DB/OL]. 2020[2021-12-15]. https://arxiv.org/abs/1809.03672.
[14] 陈卓, 李倩, 杜军威. 面向化工领域社区问答的答案质量预测研究[J]. 东北师大学报(自然科学版), 2021, 53(3): 81-88. Chen Z, Li Q, Du J W. Prediction of answer quality for community Q & A in chemical industry [J]. Journal of Northeast Normal University (Natural Science Edition), 2021, 53(3): 81-88. (in Chinese)
[15] Zhang J, Wu Z C, Li F, et al. Deep attentional factorization machines learning approach for driving safety risk prediction [J]. Journal of Physics: Conference Series, 2021, 1732: 012007.
[16] Lian J X, Zhou X H, Zhang F Z, et al. xDeepFM: combining explicit and implicit feature interactions for recommender systems [C]//The 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1754-1763.
[17] Juan Y, Zhuang Y, Chin W S, et al. Field-aware factorization machines for CTR prediction [C]//The 10th ACM Conference on Recommender Systems, 2016: 43-50.
[18] 黄若然, 崔莉, 韩传奇. 推荐系统中稀疏情景预测的特征—类别交互因子分解机[J]. 计算机研究与发展, 2022, 59(7): 1553-1568. Huang R R, Cui L, Han C Q. Feature-over-field interaction factorization machine for sparse contextualized prediction in recommender systems [J]. Journal of Computer Research and Development, 2022, 59(7): 1553-1568. (in Chinese)
[19] Zhang W N, Du T M, Wang J. Deep learning over multi-field categorical data [C]//European Conference on Information Retrieval, 2016: 45-57.
[20] He X N, Chua T S. Neural factorization machines for sparse predictive analytics [C]//The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017: 355-364.
[21] Harper F M, Konstan J A. The MovieLens datasets: history and context [J]. ACM Transactions on Interactive Intelligent Systems, 2015, 5(4): 1-19.
[22] Ziegler C N, Mcnee S M, Konstan J A, et al. Improving recommendation lists through topic diversification [C]//The 14th International Conference on World Wide Web, 2005: 22-32.
