融合时间和知识信息的生成对抗网络序列推荐算法

doi:10.19678/j.issn.1000-3428.0068300

摘要/Abstract

摘要：

序列推荐作为一种常用的推荐系统技术, 通过对用户的历史交互序列进行建模来预测下一个可能交互的项目。现有的序列推荐方法主要利用用户交互序列和上下文信息进行推荐, 忽略了序列中交互项目之间的时间间隔信息, 交互项目之间的组合依赖以及上下文信息中存在噪声的问题, 导致推荐结果受限。针对以上问题, 提出一种基于生成对抗网络的序列推荐模型TKWGAN, 该模型包含一个生成器和一个判别器。生成器结合了用户历史交互序列和各项目之间的时间间隔信息对用户偏好进行建模并生成预测, 判别器则引入了知识图谱信息对项目进行语义扩充, 从而能更准确地对生成器的预测进行合理性判断。针对用户交互序列和知识图谱信息中可能存在噪声的问题, 提出一种基于小波变换的多核卷积神经网络来构造判别器, 以更全面、准确地捕获用户的潜在兴趣, 提高推荐的准确性。在MovieLens-1M、Amazon Books和Yelp2018这3个公开数据集上的实验结果表明, 与8个序列化推荐算法相比, 提出的TKWGAN模型在命中率(HR@N)和归一化折损累计增益(NDCG@N)指标上均有显著提升。

Abstract:

Sequential recommendation is a pivotal technique within the realm of recommendation systems and is employed to predict subsequent interaction items by modeling the users' historical sequences of engagements. Nonetheless, contemporary sequential recommendation methods predominantly emphasize user interaction sequences and contextual data in their recommendations. This approach inadvertently disregards the salient temporal interval information between interaction items, the intricate interdependencies among these items, and potential perturbations in contextual information. Consequently, the efficacy of the resulting recommendations is constrained. To address these inherent limitations, this study proposes an innovative sequential recommendation model called TKWGAN, which is founded on a Generative Adversarial Network(GAN). This model consists of a generator and a discriminator. The generator seamlessly integrates the users' historical interaction sequences with temporal interval data pertaining to items within the sequence. This synthesis of information enables the accurate modeling of user preferences and the subsequent generation of predictions. The discriminator introduces salient insights offered by the knowledge graph to enrich the semantic context of the items. This augmentation of the contextual information facilitates a judicious assessment of the predictions formulated by the generator. To address the potential noise inherent in both user interaction sequences and knowledge graph data, a multikernel Convolutional Neural Network(CNN) augmented with wavelet transformation is introduced for the discriminator. This discerning approach enables a comprehensive exploration of users' latent interests, consequently elevating the precision of the recommendations. An empirical evaluation conducted on widely recognized datasets, specifically MovieLens-1M, Amazon Books, and Yelp2018, underscores the superiority of the TKWGAN model. In contrast to eight state-of-the-art sequential recommendation algorithms, the TKWGAN model demonstrates a marked enhancement in the Hit Rate(HR@N) and Normalized Discounted Cumulative Gain(NDCG@N) indicators.

Key words: recommendation algorithm, sequential recommendation, Generative Adversarial Network(GAN), knowledge graph, wavelet convolution network

李忠伟, 周洁, 刘昕, 吴金燠, 李可一. 融合时间和知识信息的生成对抗网络序列推荐算法[J]. 计算机工程, 2024, 50(11): 70-79.

LI Zhongwei, ZHOU Jie, LIU Xin, WU Jinyu, LI Keyi. Sequence Recommendation Algorithm Based on Generative Adversarial Network Integrating Time and Knowledge Information[J]. Computer Engineering, 2024, 50(11): 70-79.

https://www.ecice06.com/CN/Y2024/V50/I11/70

图/表 9

图1 融合时间和知识信息的生成对抗网络序列推荐模型

Fig.1 Sequential recommendation model based on generative adversarial network integrating time and knowledge information

图2 融合时间间隔的生成器

Fig.2 Generator integrating time interval

图3 离散小波变换

Fig.3 Discrete wavelet transform

图4 TKWGAN消融实验结果(NDCG@10)

Fig.4 Ablation experiment results of TKWGAN model(NDCG@10)

图5 不同预训练次数对应的损失

Fig.5 Loss with different pre-training epochs

图6 不同预训练次数对应的模型性能(NDCG@10)

Fig.6 Performance with different pre-training epochs(NDCG@10)

图7 最大序列长度n对性能的影响(NDCG@10)

Fig.7 Effect of maximum sequence length n on performance(NDCG@10)

参考文献 27

1	BIAN S Q, ZHAO W X, WANG J P, et al. A relevant and diverse retrieval-enhanced data augmentation framework for sequential recommendation[C]//Proceedings of the 31st ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press, 2022: 2923-2932.
2	ZHOU K, WANG H, WEN J R, et al. Enhancing multi-view smoothness for sequential recommendation models. ACM Transactions on Information Systems, 2023, 41(4): 1- 27.
3	HE R N, MCAULEY J. Fusing similarity models with Markov chains for sparse sequential recommendation[C]//Proceedings of the IEEE International Conference on Data Mining(ICDM). Washington D. C., USA: IEEE Press, 2016: 191-200.
4	RENDLE S, FREUDENTHALER C, SCHMIDT-THIEME L. Factorizing personalized Markov chains for next-basket recommendation[C]//Proceedings of the 19th International Conference on World Wide Web. New York. USA: ACM Press, 2010: 811-820.
5	KANG W C, MCAULEY J. Self-attentive sequential recommendation[C]//Proceedings of the IEEE International Conference on Data Mining(ICDM). Washington D. C., USA: IEEE Press, 2018: 197-206.
6	汪雨竹, 彭涛, 朱蓓蓓, 等. 基于元学习的小样本知识图谱补全. 吉林大学学报(理学版), 2023, 61(3): 623- 630.
	WANG Y Z, PENG T, ZHU B B, et al. Few-shot knowledge graph completion based on meta learning. Journal of Jilin University(Science Edition), 2023, 61(3): 623- 630.
7	QIU R H, HUANG Z, YIN H Z. Memory augmented multi-instance contrastive predictive coding for sequential recommendation[C]//Proceedings of the IEEE International Conference on Data Mining(ICDM). Washington D. C., USA: IEEE Press, 2021: 519-528.
8	NI S, ZHOU W, WEN J H, et al. Enhancing sequential recommendation with contrastive Generative Adversarial Network. Information Processing & Management, 2023, 60(3): 103331.
9	GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks. Communications of the ACM, 2020, 63(11): 139- 144. doi: 10.1145/3422622
10	LIU M Y, TUZEL O. Coupled generative adversarial networks. Advances in Neural Information Processing Systems, 2016, 29.
11	BHARADHWAJ H, PARK H, LIM B Y. RecGAN: recurrent generative adversarial networks for recommendation systems[C]//Proceedings of the 12th ACM Conference on Recommender Systems. New York, USA: ACM Press, 2018: 372-376.
12	WANG J, YU L T, ZHANG W N, et al. IRGAN: a minimax game for unifying generative and discriminative information retrieval models[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2017: 515-524.
13	CHAE D K, KANG J S, KIM S W, et al. CFGAN: a generic collaborative filtering framework based on generative adversarial networks[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press, 2018: 137-146.
14	REN R Y, LIU Z Y, LI Y L, et al. Sequential recommendation with self-attentive multi-adversarial network[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2020: 89-98.
15	WANG Z, ZHANG J W, FENG J L, et al. Knowledge graph embedding by translating on hyperplanes. Proceedings of the AAAI Conference on Artificial Intelligence, 2014, 28(1): 1112- 1119.
16	WANG X, HE X N, CAO Y X, et al. KGAT: knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, USA: ACM Press, 2019: 950-958.
17	BAI J M, HUANG X, LI M, et al. KSR: knowledge-based sequential news recommendation system. IOP Conference Series: Materials Science and Engineering, 2020, 799(1): 012042.
18	梁小慧, 郭晟楠, 万怀宇. 基于自适应小波分解的时间序列分类方法. 计算机工程, 2022, 48(4): 81-88, 98. doi: 10.19678/j.issn.1000-3428.0061110
	LIANG X H, GUO S N, WAN H Y. Time series classification method based on adaptive wavelet decomposition. Computer Engineering, 2022, 48(4): 81-88, 98. doi: 10.19678/j.issn.1000-3428.0061110
19	许凤, 杨兴耀, 于炯, 等. 小波卷积增强的对比学习推荐算法. 计算机工程, 2023, 49(5): 105-111, 121. doi: 10.19678/j.issn.1000-3428.0064747
	XU F, YANG X Y, YU J, et al. Wavelet convolution enhanced contrastive learning recommendation algorithm. Computer Engineering, 2023, 49(5): 105-111, 121. doi: 10.19678/j.issn.1000-3428.0064747
20	SHAW P, USZKOREIT J, VASWANI A. Self-attention with relative position representations[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, USA: Association for Computational Linguistics, 2018: 464-468.
21	YU L T, ZHANG W N, WANG J, et al. SeqGAN: sequence generative adversarial nets with policy gradient[EB/OL]. [2023-04-15]. https://arxiv.org/pdf/1609.05473.pdf.
22	HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[EB/OL]. [2023-04-15]. https://arxiv.org/pdf/1511.06939.pdf.
23	HIDASI B, QUADRANA M, KARATZOGLOU A, et al. Parallel recurrent neural network architectures for feature-rich session-based recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems. New York, USA: ACM Press, 2016: 241-248.
24	TANG J X, WANG K. Personalized top-N sequential recommendation via convolutional sequence embedding[C]//Proceedings of the 11th ACM International Conference on Web Search and Data Mining. New York, USA: ACM Press, 2018: 565-573.
25	LI J C, WANG Y J, MCAULEY J. Time interval aware self-attention for sequential recommendation[C]//Proceedings of the 13th International Conference on Web Search and Data Mining. New York, USA: ACM Press, 2020: 322-330.
26	MAO K, ZHU J, WANG J, et al. SimpleX: a simple and strong baseline for collaborative filtering[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York, USA: ACM Press, 2021: 1243-1252.
27	ZHOU K, YU H, ZHAO W X, et al. Filter-enhanced MLP is all you need for sequential recommendation[C]//Proceedings of the ACM Web Conference. New York, USA: ACM Press, 2022: 2388-2399.

[1]	李泽霖, 吕兆峰, 陈富强, 李克. 基于多跳信息融合的实体对齐模型[J]. 计算机工程, 2024, 50(9): 142-152.
[2]	汤志康, 武毓琦, 李春英, 汤庸. 基于知识图谱卷积网络的学习资源推荐[J]. 计算机工程, 2024, 50(9): 153-160.
[3]	李华昱, 张智康, 闫阳, 岳阳. 基于知识图谱增强的领域多模态实体识别[J]. 计算机工程, 2024, 50(8): 31-39.
[4]	王夙喆, 张雪英, 陈晓玉, 李凤莲, 吴泽林. 基于有效注意力和GAN结合的脑卒中EEG增强算法[J]. 计算机工程, 2024, 50(8): 336-344.
[5]	李惠乾, 钟柏昌. 教育知识图谱: 研究进展与未来发展——基于2013—2023年中文核心期刊载文的分析[J]. 计算机工程, 2024, 50(7): 1-12.
[6]	王炼红, 林飞鹏, 李潇瑶, 谌桂枝, 周莉. 融入课程知识图谱的KMAKT预测[J]. 计算机工程, 2024, 50(7): 23-31.
[7]	刘娟, 段友祥, 陆誉翕, 张鲁. 引入知识增强和对比学习的知识图谱补全[J]. 计算机工程, 2024, 50(7): 112-122.
[8]	陈佳玉, 王元龙, 张虎. 基于文本知识增强的问题生成模型[J]. 计算机工程, 2024, 50(6): 86-93.
[9]	胡庆. 多尺度融合与双输出U-Net网络的行人重识别[J]. 计算机工程, 2024, 50(6): 102-109.
[10]	张慧妍, 梁勇, 兰景宏, 赵强. 基于记忆模块与过滤式生成对抗网络的入侵检测方法[J]. 计算机工程, 2024, 50(6): 197-207.
[11]	江惠珍, 孙艳春, 黄罡. 基于知识图谱的GitHub层次化学习和检索服务[J]. 计算机工程, 2024, 50(5): 16-25.
[12]	李田芳, 普园媛, 赵征鹏, 徐丹, 钱文华. 基于CLIP和双空间自适应归一化的图像翻译[J]. 计算机工程, 2024, 50(5): 229-240.
[13]	王明虎, 石智奎, 苏佳, 张新生. 基于RoBERTa和图增强Transformer的序列推荐方法[J]. 计算机工程, 2024, 50(4): 121-131.
[14]	张洪程, 李林育, 杨莉, 伞晨峻, 尹春林, 颜冰, 于虹, 张璇. 基于对比学习与语言模型增强嵌入的知识图谱补全[J]. 计算机工程, 2024, 50(4): 168-176.
[15]	刘帅威, 李智, 王国美, 张丽. 基于Transformer和GAN的对抗样本生成算法[J]. 计算机工程, 2024, 50(2): 180-187.

选择文件类型/文献管理软件名称

选择包含的内容