Survey on Applications of Knowledge Graph Embedding in Recommendation Tasks

doi:10.3778/j.issn.1673-9418.2112070

Abstract

Abstract:

Recommendation systems are designed to recommend personalized content to improve user experience. At present, the recommendation systems still face some challenges such as poor interpretability, cold start problem and serialized recommendation modeling. Recently, the knowledge graph (KG) containing a large amount of semantic and structural information has been widely used in a variety of different recommendation tasks to alleviate the above problems. This paper systematically reviews the innovative applications of knowledge graph embedding (KGE) in different recommendation tasks. It first summarizes three common recommendation tasks and four applying goals of knowledge graph embedding. Then, it generalizes four types of knowledge graph embedding methods according to specific technologies, including traditional embedding method, embedding propagation method, heterogeneous graph embedding method and graph neural network based method. It further elaborates on the applying characteristics and strategies of the above four methods in different recommendation tasks, and evaluates advantages and limitations of each method. Also, it conducts qualitative and quantitative analysis of the associations and differences of four methods from multiple aspects. Finally, it puts forward some views on the development trend of applying knowledge graph embedding for recommendation systems, and proposes several noteworthy development directions in the future from multiple perspectives.

Key words: knowledge graph embedding (KGE), recommendation tasks, explainable recommendation, cold start, serialization recommendation, application of knowledge graph embedding

摘要：

推荐系统旨在为用户推荐个性化内容以提升用户体验，但目前仍面临着诸如可解释性差、冷启动问题和序列化推荐建模等挑战。近年来，蕴含大量结构化知识和语义信息的知识图谱（KG）被广泛应用于各种推荐任务中以期缓解上述问题。对不同推荐任务中知识图谱嵌入（KGE）的创新应用进行系统性综述。首先梳理出采用知识图谱嵌入的三类常见推荐任务以及知识图谱嵌入应用的四种目的;然后根据技术不同归纳总结出四类知识图谱嵌入方法，包括传统嵌入方法、嵌入传播方法、异质图嵌入方法和基于图神经网络的方法;进一步详细阐述了每类方法在不同推荐任务中的使用特点及应用策略，评价其优点和局限性等，并从多个方面对方法间的联系与区别进行定性和定量分析;最后，针对面向不同推荐任务中知识图谱嵌入应用的发展趋势提出一些看法，从多个角度展望了该领域未来值得关注的几个发展方向。

关键词: 知识图谱嵌入（KGE）, 推荐任务, 可解释推荐, 冷启动, 序列化推荐, 知识图谱嵌入应用

CLC Number:

TP319

TIAN Xuan, CHEN Hangxue. Survey on Applications of Knowledge Graph Embedding in Recommendation Tasks[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(8): 1681-1705.

田萱, 陈杭雪. 推荐任务中知识图谱嵌入应用研究综述[J]. 计算机科学与探索, 2022, 16(8): 1681-1705.

Figures/Tables 16

References 117

[1]	ADOMAVICIUS G, TUZHILIN A. Towards the next genera-tion of recommender systems: a survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Know-ledge and Data Engineering, 2005, 17(6): 734-749.
[2]	DU X Y, HE X N, YUAN F J, et al. Modeling embedding dimension correlations via convolutional neural collabo- rative filtering[J]. ACM Transactions on Information Sys-tems, 2019, 37(4): 47.
[3]	ZHANG F Z, NICHOLAS Y J, LIAN D F, et al. Collabora-tive knowledge base embedding for recommender systems[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 353-362.
[4]	WANG H W, ZHANG F Z, HOU M, et al. SHINE: signed heterogeneous information network embedding for senti-ment link prediction[C]// Proceedings of the 11th ACM International Conference on Web Search and Data Mining, Marina Del Rey, Feb 5-9, 2018. New York: ACM, 2018: 592-600.
[5]	BOLLACKER K, EVANS C, PARITOSH P, et al. Freebase: a collaboratively created graph database for structuring human knowledge[C]// Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, Van-couver, Jun 10-12, 2008. New York: ACM, 2008: 1247-1250.
[6]	LEHMANN J, ISELE R, JAKOB M, et al. DBpedia—a large-scale, multilingual knowledge base extracted from Wikipedia[J]. Semantic Web, 2015, 6(2): 167-195.
[7]	SUCHANEK F M, KASNECI G, WEIKUM G. YAGO: a core of semantic knowledge[C]// Proceedings of the 16th Inter-national Conference on World Wide Web, Banff, May 8-12, 2007. New York: ACM, 2007: 697-706.
[8]	CARLSON A, BETTERIDGE J, KISIEL B, et al. Toward an architecture for never-ending language learning[C]// Proceedings of the 24th AAAI Conference on Artificial Intelligence, Atlanta, Jul 11-15, 2010. Menlo Park:AAAI, 2010: 1306-1313.
[9]	NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[C]// Procee-dings of the 28th International Conference on Machine Learning, Bellevue, Jun 28-Jul 2, 2011. Madison:Omni-Press, 2011: 809-816.
[10]	WANG Z, ZHANG J W, FENG J L, et al. Knowledge graph embedding by translating on hyperplanes[C]// Proceedings of the 28th AAAI Conference on Artificial Intelligence, Québec, Jul 27-31, 2014. Menlo Park: AAAI, 2014: 1112-1119.
[11]	LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, Jan 25-30, 2015. Menlo Park: AAAI, 2015: 2181-2187.
[12]	田萱, 丁琪, 廖子慧, 等. 基于深度学习的新闻推荐算法研究综述[J]. 计算机科学与探索, 2021, 15(6): 971-998.
	TIAN X, DING Q, LIAO Z H, et al. Survey on deep learning based news recommendation algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 971-998.
[13]	PALUMBO E, RIZZO G, TRONCY R.Entity2rec: learning user-item relatedness from knowledge graphs for top-n item recommendation[C]// Proceedings of the 11th ACM Confer-ence on Recommender Systems, Como, Aug 27-31, 2017. New York: ACM, 2017: 32-36.
[14]	WANG X Y, ZHANG Y, WANG X L, et al. A knowledge graph enhanced topic modeling approach for herb recom-mendation[C]// LNCS 11446: Proceedings of the 24th Inter-national Conference on Database Systems for Advanced Applications, Chiang Mai, Apr 22-25, 2019. Cham: Springer, 2019: 709-724.
[15]	HUANG H H. An MPD player with expert knowledge-based single user music recommendation[C]// Proceedings of the 2019 International Conference on Web Intelligence, Thessaloniki, Oct 14-17, 2019. New York: ACM, 2019: 318-321.
[16]	WANG Q, MAO Z D, WANG B, et al. Knowledge graph embedding: a survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724-2743.
[17]	秦川, 祝恒书, 庄福振, 等. 基于知识图谱的推荐系统研究综述[J]. 中国科学: 信息科学, 2020, 50(7): 937-956.
	QIN C, ZHU H S, ZHUANG F Z, et al. A survey on knowledge graph-based recommender systems[J]. Scientia Sinica Informationis, 2020, 50(7): 937-956.
[18]	朱冬亮, 文奕, 万子琛. 基于知识图谱的推荐系统研究综述[J]. 数据分析与知识发现, 2021, 5(12): 1-13.
	ZHU D L, WEN Y, WAN Z C. A survey on knowledge graph-based recommender systems[J]. Data Analysis and Knowledge Discovery, 2021, 5(12): 1-13.
[19]	TINTAREV N, MASTHOFF J. Designing and evaluating explanations for recommender systems[M]// Recommender Systems Handbook. Boston: Springer, 2011: 479-510.
[20]	QUADRANA M, KARATZOGLOU A, HIDASI B, et al. Personalizing session-based recommendations with hiera-rchical recurrent neural networks[C]// Proceedings of the 11th ACM Conference on Recommender Systems, Como, Aug 27-31, 2017. New York: ACM, 2017: 130-137.
[21]	HUANG J, ZHAO W X, DOU H J, et al. Improving se-quential recommendation with knowledge-enhanced memory networks[C]// Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Infor-mation Retrieval, Ann Arbor, Jul 8-12, 2018. New York: ACM, 2018: 505-514.
[22]	ZHANG Y F, CHEN X. Explainable recommendation: a survey and new perspectives[J]. Foundations and Trends in Information Retrieval, 2020, 14(1): 1-101.
[23]	WANG S J, HU L, WANG Y, et al. Sequential recom-mender systems: challenges, progress and prospects[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, Aug 10-16, 2019: 6332-6338.
[24]	WANG H W, ZHANG F Z, WANG J L, et al. Exploring high-order user preference on the knowledge graph for recommender systems[J]. ACM Transactions on Informa- tion Systems, 2019, 37(3): 1-26.
[25]	HUANG X W, FANG Q, QIAN S S, et al. Explainable interaction-driven user modeling over knowledge graph for sequential recommendation[C]// Proceedings of the 27th ACM International Conference on Multimedia, Nice, Oct 21-25, 2019. New York: ACM, 2019: 548-556.
[26]	KAELBLING L P, LITTMAN M L, MOORE A W. Moore, reinforcement learning: a survey[J]. Journal of Artificial Intelligence Research, 1996, 4: 237-285.
[27]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[28]	KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Dec 3-6, 2012. Red Hook: Curran Associates, 2012: 1106-1114.
[29]	BORDES A, USUNIER N, GARCÍA-DURÁN A, et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 27th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Dec 5-8, 2013. Red Hook: Curran Associates, 2013: 2787-2795.
[30]	JI G L, HE S Z, XU L H, et al. Knowledge graph embedding via dynamic mapping matrix[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Beijing, Jul 26-31, 2015. Stroudsburg: ACL, 2015: 687-696.
[31]	XIAN Y K, FU Z H, MUTHUKRISHNAN S, et al. Rein-forcement knowledge graph reasoning for explainable recommendation[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, Jul 21-25, 2019. New York: ACM, 2019: 285-294.
[32]	SHA X, SUN Z, ZHANG J. Attentive knowledge graph embedding for personalized recommendation[J]. arXiv:1910.08288, 2019.
[33]	SHI C, LI Y T, ZHANG J W, et al. A survey of heterogen-eous information network analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(1): 17-37.
[34]	CAI H Y, ZHENG V W, CHANG C C. A comprehensive survey of graph embedding: problems, techniques and app-lications[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(9): 1616-1637.
[35]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]// Proceedings of the 5th International Conference on Learning Representations, Toulon, Apr 24-26, 2017: 1-14.
[36]	VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]// Proceedings of the 6th Inter-national Conference on Learning Representations, Vancouver, Apr 30-May 3, 2018: 1-12.
[37]	AI Q Y, AZIZI V, CHEN X, et al. Learning heterogeneous knowledge base embeddings for explainable recommenda-tion[J]. Algorithms, 2018, 11(9): 137.
[38]	TIAN Y, YANG Y H, REN X D, et al. Joint knowledge pruning and recurrent graph convolution for news recom-mendation[C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Infor-mation Retrieval. New York: ACM, 2021: 51-60.
[39]	ZHANG Y F, AI Q Y, CHEN X, et al. Learning over knowledge-base embeddings for recommendation[J]. arXiv:1803.06540, 2018.
[40]	LIU D Y, LIAN J X, WANG S Y, et al. KRED: knowledge-aware document representation for news recommendations[C]// Proceedings of the 14th ACM Conference on Recom-mender Systems. New York: ACM, 2020: 200-209.
[41]	MA C, MA L H, ZHANG Y X, et al. Knowledge-enhanced top-K recommendation in poincaré ball[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence, 33rd Conference on Innovative Applications of Artificial Intelli-gence, the 11th Symposium on Educational Advances in Artificial Intelligence. Menlo Park: AAAI, 2021: 4285-4293.
[42]	NICKEL M, KIELA D. Poincaré embeddings for learning hierarchical representations[C]// Proceedings of the 31st Annual Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 6338-6347.
[43]	CAO Y X, WANG X, HE X N, et al. Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences[C]// Proceedings of the 28th International World Wide Web Conference, San Fran-cisco, May 13-17, 2019. New York: ACM, 2019: 151-161.
[44]	MA W Z, ZHANG M, CAO Y, et al. Jointly learning explain-able rules for recommendation with knowledge graph[C]// Proceedings of the 2019 World Wide Web Conference, San Francisco, May 13-17, 2019. New York: ACM, 2019: 1210-1221.
[45]	PALUMBO E, MONTI D, RIZZO G, et al. Entity2rec: property-specific knowledge graph embeddings for item recommendation[J]. Expert Systems with Applications, 2020, 151: 113235.
[46]	GROVER A, LESKOVEC J.Node2vec: scalable feature learning for networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 855-864.
[47]	WANG H W, ZHANG F Z, WANG J L, et al. RippleNet: propagating user preferences on the knowledge graph for recommender systems[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Oct 22-26, 2018. New York: ACM, 2018: 417-426.
[48]	LIN Y, XU B, FENG J J, et al. Knowledge-enhanced recom-mendation using item embedding and path attention[J]. Knowledge-Based Systems, 2021, 233: 107484.
[49]	WANG X, WANG D X, XU C R, et al. Explainable rea-soning over knowledge graphs for recommendation[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park:AAAI, 2019: 5329-5336.
[50]	FU Z H, XIAN Y K, GAO R Y, et al. Fairness-aware exp-lainable recommendation over knowledge graphs[C]// Pro-ceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 69-78.
[51]	WANG X, XU Y K, HE X N, et al. Reinforced negative sampling over knowledge graph for recommendation[C]// Proceedings of the 2020 World Wide Web Conference, Taipei, China, Apr 20-24, 2020. New York: ACM, 2020: 99-109.
[52]	ZHAO K Z, WANG X T, ZHANG Y R, et al. Leveraging demonstrations for reinforcement recommendation reasoning over knowledge graphs[C]// Proceedings of the 43rd Inter-national ACM SIGIR Conference on Research and Deve-lopment in Information Retrieval. New York: ACM, 2020: 239-248.
[53]	TAO S H, QIU R H, PING Y, et al. Multi-modal knowledge-aware reinforcement learning network for explainable reco-mmendation[J]. Knowledge-Based Systems, 2021, 227: 107217.
[54]	LIU D Y, LIAN J X, LIU Z, et al. Reinforced anchor know-ledge graph generation for news recommendation reasoning[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2021: 1055-1065.
[55]	YANG Z X, DONG S B. HAGERec: hierarchical attention graph convolutional network incorporating knowledge graph for explainable recommendation[J]. Knowledge-Based Sys-tems, 2020, 204: 106194.
[56]	LIU N H, GE Y, LI L, et al. Explainable recommender sys-tems via resolving learning representations[C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 895-904.
[57]	CAO X S, SHI Y L, YU H, et al. DEKR: description enhanced knowledge graph for machine learning method recommenda-tion[C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2021: 203-212.
[58]	LIN X, QUAN Z, WANG Z J, et al. KGNN: knowledge graph neural network for drug-drug interaction prediction[C]// Proceedings of the 29th International Joint Conference on Artificial Intelligence, Yokohama, 2020: 2739-2745.
[59]	ZHANG L S, KANG Z, SUN X X, et al. KCRec: knowledge-aware representation graph convolutional network for recom-mendation[J]. Knowledge-Based Systems, 2021, 230: 107399.
[60]	XIA L H, HUANG C, XU Y, et al. Knowledge-enhanced hierarchical graph transformer network for multi-behavior recommendation[C]// Proceedings of the 35th AAAI Confe-rence on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intellig-ence. Menlo Park: AAAI, 2021: 4486-4493.
[61]	TAI C Y, HUANG L Y, HUANG C K, et al. User-centric path reasoning towards explainable recommendation[C]// Proceedings of the 44th International ACM SIGIR Con-ference on Research and Development in Information Re-trieval. New York: ACM, 2021: 879-889.
[62]	JIA Z Y, WU M D, YANG H, et al. Temporal sensitive he-terogeneous graph neural network for news recommenda-tion[J]. Future Generation Computer Systems, 2021, 125: 324-333.
[63]	WANG X, HE X N, CAO Y X, et al. KGAT: knowledge graph attention network for recommendation[C]// Procee-dings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 950-958.
[64]	WANG X, HUANG T L, WANG D X, et al. Learning intents behind interactions with knowledge graph for recommenda-tion[C]// Proceedings of the 2021 World Wide Web Confer-ence. New York: ACM, 2021: 878-887.
[65]	CAO Z Y, QIAO X H, JIANG S, et al. An efficient knowledge-graph-based Web service recommendation algorithm[J]. Symmetry-Basel, 2019, 11(3): 392.
[66]	MENG W J, YANG D Q, XIAO Y H. Incorporating user micro-behaviors and item knowledge into multi-task learning for session-based recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 1091-1100.
[67]	LI Y J, TARLOW D, BROCKSCHMIDT M, et al. Gated graph sequence neural networks[C]// Proceedings of the 4th International Conference on Learning Representations, San Juan, May 2-4, 2016: 1-20.
[68]	TANG X L, WANG T Y, YANG H Z, et al. AKUPM: attention-enhanced knowledge-aware user preference model for recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 1891-1899.
[69]	ZHOU Z L, LIU S W, XU G D, et al. Knowledge-based recommendation with hierarchical collaborative embedding[C]// LNCS 10938: Proceedings of the 22nd Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Melbourne, Jun 3-6, 2018. Cham: Springer, 2018: 222-234.
[70]	HE M, WANG B, DU X K. HI2Rec: exploring knowledge in heterogeneous information for movie recommendation[J]. IEEE Access, 2019, 7: 30276-30284.
[71]	ZHANG M W, ZHAO J W, DONG H, et al. A knowledge graph based approach for mobile application recomme-ndation[C]// LNCS 2020: Proceedings of the 18th Inter-national Conference on Service-Oriented Computing, Dubai, Dec 14-17, 2020. Cham: Springer, 2020: 355-369.
[72]	WANG H W, ZHANG F Z, ZHAO M, et al. Multi-task feature learning for knowledge graph enhanced recomm-endation[C]// Proceedings of the 2019 World Wide Web Conference, San Francisco, May 13-17, 2019. New York: ACM, 2019: 2000-2010.
[73]	SHI C, HU B B, ZHAO W X, et al. Heterogeneous infor-mation network embedding for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(2): 357-370.
[74]	HE Y F, ZHANG Y W, QI L Y, et al. Outer product enhanced heterogeneous information network embedding for recom-mendation[J]. Expert Systems with Applications, 2021, 169: 114359.
[75]	YAN S R, WANG H S, LI Y X, et al. Attention-aware metapath-based network embedding for HIN based recom-mendation[J]. Expert Systems with Applications, 2021, 174: 114601.
[76]	WANG Y F, TANG S Y, LEI Y T, et al. disenHAN: disen-tangled heterogeneous graph attention network for recom-mendation[C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 1605-1614.
[77]	WANG R R, MA X, JIANG C, et al. Heterogeneous infor-mation network-based music recommendation system in mobile networks[J]. Computer Communications, 2020, 150: 429-437.
[78]	GONG F, WANG M, WANG H F, et al. SMR: medical know-ledge graph embedding for safe medicine recommendation[J]. Big Data Research, 2021, 23: 100174.
[79]	JOHNSON A E W, POLLARD T J, SHEN L, et al. MIMIC-III, a freely accessible critical care database[J]. Scientific Data, 2016, 3: 160035.
[80]	SCHRIML L M, ARZE C, NADENDLA S, et al. Disease ontology: a backbone for disease semantic integration[J]. Nucleic Acids Research, 2012, 40(D1): D940-D946.
[81]	LAW V, KNOX C, DJOUMBOU Y, et al. Drugbank 4.0: shedding new light on drug metabolism[J]. Nucleic Acids Research, 2014, 42(D1): D1091-D1097.
[82]	WANG H F, WANG Z J, HU S H, et al. DUSKG: a fine-grained knowledge graph for effective personalized service recommendation[J]. Future Generation Computer Systems-the International Journal of Escience, 2019, 100: 600-617.
[83]	WANG H W, ZHAO M, XIE X, et al. Knowledge graph convolutional networks for recommender systems[C]// Pro-ceedings of the 2019 World Wide Web Conference, San Fran-cisco, May 13-17, 2019. New York: ACM, 2019: 3307-3313.
[84]	ZHOU S J, DAI X Y, CHEN H K, et al. Interactive recom-mender system via knowledge graph-enhanced reinforce-ment learning[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 179-188.
[85]	MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-533.
[86]	ZHAO M Y, HUANG X W, ZHU L X, et al. Knowledge graph-enhanced sampling for conversational recommender system[J]. arXiv:2110.06637, 2021.
[87]	ZHOU K, ZHAO W X, BIAN S Q, et al. Improving conver-sational recommender systems via knowledge graph based semantic fusion[C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 1006-1014.
[88]	TAI C Y, WU M R, CHU Y W, et al. MVIN: learning multi-view items for recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 99-108.
[89]	ZHAO J, ZHOU Z, GUAN Z Y, et al. IntentGC: a scalable graph convolution framework fusing heterogeneous infor-mation for recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 2347-2357.
[90]	LEI S, XU M, QIAN S S, et al. Knowledge graph enhanced neural collaborative recommendation[J]. Expert Systems with Applications, 2021, 164: 113992.
[91]	TU K, CUI P, WANG D X, et al. Conditional graph attention networks for distilling and refining knowledge graphs in recommendation[C]// Proceedings of the 30th ACM Inter-national Conference on Information and Knowledge Man-agement. New York: ACM, 2021: 1834-1843.
[92]	CHEN C, ZHANG M, MA W Z, et al. Jointly non-sampling learning for knowledge graph enhanced recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 189-198.
[93]	ZHANG Z Y, ZHANG L, YANG D Q, et al. KRAN: know-ledge refining attention network for recommendation[J]. ACM Transactions on Knowledge Discovery from Data, 2021, 16(2): Article 39.
[94]	WANG Z, LIN G Y, TAN H B, et al. CKAN: collaborative knowledge-aware attentive network for recommender sys-tems[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 219-228.
[95]	SUN R, CAO X Z, ZHAO Y, et al. Multi-modal knowledge graphs for recommender systems[C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 1405-1414.
[96]	LEE D, OH B, SEO S, et al. News recommendation with topic-enriched knowledge graphs[C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 695-704.
[97]	WANG H W, ZHANG F Z, ZHANG M D, et al. Knowledge-aware graph neural networks with label smoothness regu-larization for recommender systems[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 968-977.
[98]	TOGASHI R, OTANI M, SATOH S. Alleviating cold-start problems in recommendation through pseudo-labelling over knowledge graph[C]// Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York: ACM, 2021: 931-939.
[99]	LONG X L, HUANG C, XU Y, et al. Social recommendation with self-supervised metagraph informax network[C]// Pro-ceedings of the 30th ACM International Conference on Information and Knowledge Management. New York: ACM, 2021: 1160-1169.
[100]	MILLER A H, ADAM F, DODGE J, et al. Key-value memory networks for directly reading documents[C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Nov 1-4, 2016. Stroudsburg: ACL, 2016: 1400-1409.
[101]	WANG B, CAI W. Knowledge-enhanced graph neural net-works for sequential recommendation[J]. Information, 2020, 11(8): 388.
[102]	WANG C Y, ZHANG M, NA W Z, et al. Make it a chorus: knowledge and time-aware item modeling for sequential recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 109-118.
[103]	LIU Y, LI B H, ZANG Y L, et al. A knowledge-aware reco-mmender with attention-enhanced dynamic convolutional network[C]// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York: ACM, 2021: 1079-1088.
[104]	WANG P F, FAN Y, XIA L, et al. KERL: a knowledge-guided reinforcement learning model for sequential recom-mendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Infor-mation Retrieval. New York: ACM, 2020: 209-218.
[105]	CHOWDHURY G, SRILAKSHMI M, CHAIN M, et al. Neural factorization for offer recommendation using know-ledge graph embeddings[C]// Proceedings of the SIGIR 2019 Workshop on eCommerce, Co-located with the 42nd Inter-national ACM SIGIR Conference on Research and Deve-lopment in Information Retrieval, Paris,Jul 25, 2019. New York:ACM, 2019: 1-6.
[106]	HE X N, CHUA T S. Neural factorization machines for sparse predictive analytics[C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Aug 7-11, 2017. New York: ACM, 2017: 355-364.
[107]	WANG T, SHI D Q, WANG Z D, et al. MRP2Rec: exploring multiple-step relation path semantics for knowledge graph-based recommendations[J]. IEEE Access, 2020, 8: 134817-134825.
[108]	RUDER S. An overview of multi-task learning in deep neural networks[J]. arXiv:1706.05098, 2017.
[109]	XIONG X, QIAO S J, HAN N, et al. Where to go: an effective point-of-interest recommendation framework for heterogeneous social networks[J]. Neurocomputing, 2020, 373: 56-69.
[110]	SALAKHUTDINOV R R, MNIH A. Bayesian probabili- stic matrix factorization using Markov chain Monte Carlo[C]// Proceedings of the 25th ACM International Conference on Machine Learning, Helsinki, Jun 5-9, 2008. New York: ACM, 2008: 880-887.
[111]	WANG H W, ZHANG F Z, XIE X, et al. DKN: deep knowledge-aware network for news recommendation[C]// Proceedings of the 2018 World Wide Web Conference on World Wide Web, Lyon, Apr 23-27, 2018. New York: ACM, 2018: 1835-1844.
[112]	QI T, WU F Z, WU C H, et al. Personalized news recom-mendation with knowledge-aware interactive matching[C]// Proceedings of the 44th International ACM SIGIR Confer-ence on Research and Development in Information Retrieval. New York: ACM, 2021: 61-70.
[113]	KIM Y. Convolutional neural networks for sentence class-ification[C]// Proceedings of the 2014 Conference on Em-pirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1746-1751.
[114]	WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[115]	刘佳玮, 石川, 杨成, 等. 基于异质信息网络的推荐系统研究综述[J]. 信息安全学报, 2021, 6(5): 1-16.
	LIU J W, SHI C, YANG C, et al. Heterogeneous infor-mation network based recommender systems: a survey[J]. Journal of Information Security, 2021, 6(5): 1-16.
[116]	XIA F, SUN K, YU S, et al. Graph learning: a survey[J]. IEEE Transactions on Artificial Intelligence, 2021, 2(2): 109-127.
[117]	涂存超, 杨成, 刘知远, 等. 网络表示学习综述[J]. 中国科学: 信息科学, 2017, 47(8): 980-996.
	TU C C, YANG C, LIU Z Y, et al. Network representation learning: an overview[J]. Scientia Sinica Informationis, 2017, 47(8): 980-996.

嵌入方法	模型框架	会议	时间	创新应用	优点	局限性	应用场景
传统嵌入方法	ECFGK^[37]	Algorithms	2018	TransE+软匹配算法	训练效率高，可灵活变化嵌入大小	不同数据集上的性能差距大	电子商务
	Kopra^[38]	SIGIR	2021	TransE+递归图卷积+剪枝	建模多样化的新闻语义和用户兴趣	忽略了新闻内容中的实体信息	新闻
	CFKG^[39]	CoRR	2018	TransE+扩展协同过滤	灵活处理多类型数据，且效率很高	难以建模 KG的高阶连通性	电子商务
	KRED^[40]	RecSys	2020	TransE+上下文感知	强调了新闻内容中实体的重要性	计算成本较高，训练时间较长	新闻
	Hyper-Know^[41]	AAAI	2021	TransE+双曲空间建模	参数少，计算量小，效率高	不包含用户信息，不够全面	音乐、图书
	KTUP^[43]	WWW	2019	TransH+TUP+联合学习	充分考虑了 KG的不完全性	存在冷启动问题	电影、图书
嵌入传播方法	RuleRec^[44]	WWW	2019	嵌入传播+规则学习	考虑项目间关系类型，泛化能力强	增加规则数量会降低推荐精度	电子商务
	entity2rec^[45]	ESWA	2020	嵌入传播+node2vec	可以生成推荐结果的丰富解释	参数较多聚合函数性能下降	电影、图书、新闻
	RippleNet^[47]	CIKM	2018	嵌入传播+多层注意力	有效挖掘用户潜在兴趣，性能显著	大规模迭代运算提高计算成本	电影、图书、新闻
	CIEPA^[48]	KBS	2021	嵌入传播+LSTM	计算开销小，且模型扩展性较好	高度依赖于丰富用户评分数据	电影、图书
	KPRN^[49]	AAAI	2019	嵌入传播+LSTM	显式地探索用户项目间复杂关系	训练时间长且模型复杂度高	电影、音乐
	公平性算法^[50]	SIGIR	2020	嵌入传播+公平感知	有效降低了推荐不公平性	缺乏对长路径的学习	电子商务
	KGPolicy^[51]	WWW	2020	嵌入传播+负采样	负样本的探索空间小，复杂度低	在交互稀疏场景下的性能较差	图书、音乐
	PGPR^[31]	SIGIR	2019	嵌入传播+MDP	结合 RL方法提供可靠、多样化的解释，且模型稳定性高	推理过程中易产生噪声，复杂度较高易受寻径策略的影响	电子商务
	ADAC^[52]	SIGIR	2020	嵌入传播+MDP	具有较好的可解释性和收敛性	忽略了路径长度对推荐的影响	电子商务
	MKRLN^[53]	KBS	2021	嵌入传播+MDP+分层路径	有效过滤冗余信息减小动作空间，可以从多个角度提供推荐解释	实体数量的大幅度降低对推荐性能影响较大	电影、图书、音乐
	AnchorKG^[54]	KDD	2021	嵌入传播+MDP	模型可扩展性强，适用于大规模 KG的实时新闻推荐服务	目前仅适用于新闻推荐场景	新闻
基于图神经网络	HAGERec^[55]	KBS	2020	GCN+分层注意力机制	可以更充分地挖掘用户潜在偏好	内存、训练难度和时间开销大	电影、图书、音乐
	可解释模型^[56]	CIKM	2020	GCN+因子联合学习	有效挖掘数据不同方面的特征	忽略了对关系类型的考虑，且时间复杂度和内存成本较高	电影、图书、音乐
	DEKR^[57]	SIGIR	2021	GCN+文本协同过滤	融合了与实体相关的文本描述信息	仅适用于机器学习领域的推荐	机器学习
	KCRec^[59]	KBS	2021	GCN+注意力机制	有效捕获用户特征和关系重要性	模型参数较多，计算量大	图书、音乐
	KHGT^[60]	AAAI	2021	GCN+时间感知	引入时间信息建模动态的用户偏好	内存需求和计算成本较高	电影、零售
	UCPR^[61]	SIGIR	2021	GNN+MDP	实现基于用户需求组合的复杂推理，具有较快的收敛速度	仅考虑和购买历史有关联的项目，对性能有较大影响	电影、图书、电子商务
	TSHGNN^[62]	FGCS	2021	GNN+CNN+Rein-LSTM	根据新闻内容及时间特征充分提取深度新闻特征	LSTM模型设计复杂，且嵌入维数对性能影响较大	新闻
	KGAT^[63]	KDD	2019	GAT+递归传播	有效增强了非活跃用户的表示	训练过程较为繁琐	电影、音乐、图书
	AKGE^[32]	CoRR	2019	GAT+最短路径算法+MLP	充分挖掘KG语义和拓扑信息	复杂度高且易产生过拟合问题	电影、音乐
	KGIN^[64]	WWW	2021	GAT+迭代聚合	全面刻画用户与项目间的关系并保留了路径的整体语义	挖掘路径多跳关系大大增加了模型复杂度	图书、音乐、电子商务

嵌入方法	模型框架	会议	时间	创新应用	优点	局限性	应用场景
传统嵌入方法	ECFGK^[37]	Algorithms	2018	TransE+软匹配算法	训练效率高，可灵活变化嵌入大小	不同数据集上的性能差距大	电子商务
	Kopra^[38]	SIGIR	2021	TransE+递归图卷积+剪枝	建模多样化的新闻语义和用户兴趣	忽略了新闻内容中的实体信息	新闻
	CFKG^[39]	CoRR	2018	TransE+扩展协同过滤	灵活处理多类型数据，且效率很高	难以建模 KG的高阶连通性	电子商务
	KRED^[40]	RecSys	2020	TransE+上下文感知	强调了新闻内容中实体的重要性	计算成本较高，训练时间较长	新闻
	Hyper-Know^[41]	AAAI	2021	TransE+双曲空间建模	参数少，计算量小，效率高	不包含用户信息，不够全面	音乐、图书
	KTUP^[43]	WWW	2019	TransH+TUP+联合学习	充分考虑了 KG的不完全性	存在冷启动问题	电影、图书
嵌入传播方法	RuleRec^[44]	WWW	2019	嵌入传播+规则学习	考虑项目间关系类型，泛化能力强	增加规则数量会降低推荐精度	电子商务
	entity2rec^[45]	ESWA	2020	嵌入传播+node2vec	可以生成推荐结果的丰富解释	参数较多聚合函数性能下降	电影、图书、新闻
	RippleNet^[47]	CIKM	2018	嵌入传播+多层注意力	有效挖掘用户潜在兴趣，性能显著	大规模迭代运算提高计算成本	电影、图书、新闻
	CIEPA^[48]	KBS	2021	嵌入传播+LSTM	计算开销小，且模型扩展性较好	高度依赖于丰富用户评分数据	电影、图书
	KPRN^[49]	AAAI	2019	嵌入传播+LSTM	显式地探索用户项目间复杂关系	训练时间长且模型复杂度高	电影、音乐
	公平性算法^[50]	SIGIR	2020	嵌入传播+公平感知	有效降低了推荐不公平性	缺乏对长路径的学习	电子商务
	KGPolicy^[51]	WWW	2020	嵌入传播+负采样	负样本的探索空间小，复杂度低	在交互稀疏场景下的性能较差	图书、音乐
	PGPR^[31]	SIGIR	2019	嵌入传播+MDP	结合 RL方法提供可靠、多样化的解释，且模型稳定性高	推理过程中易产生噪声，复杂度较高易受寻径策略的影响	电子商务
	ADAC^[52]	SIGIR	2020	嵌入传播+MDP	具有较好的可解释性和收敛性	忽略了路径长度对推荐的影响	电子商务
	MKRLN^[53]	KBS	2021	嵌入传播+MDP+分层路径	有效过滤冗余信息减小动作空间，可以从多个角度提供推荐解释	实体数量的大幅度降低对推荐性能影响较大	电影、图书、音乐
	AnchorKG^[54]	KDD	2021	嵌入传播+MDP	模型可扩展性强，适用于大规模 KG的实时新闻推荐服务	目前仅适用于新闻推荐场景	新闻
基于图神经网络	HAGERec^[55]	KBS	2020	GCN+分层注意力机制	可以更充分地挖掘用户潜在偏好	内存、训练难度和时间开销大	电影、图书、音乐
	可解释模型^[56]	CIKM	2020	GCN+因子联合学习	有效挖掘数据不同方面的特征	忽略了对关系类型的考虑，且时间复杂度和内存成本较高	电影、图书、音乐
	DEKR^[57]	SIGIR	2021	GCN+文本协同过滤	融合了与实体相关的文本描述信息	仅适用于机器学习领域的推荐	机器学习
	KCRec^[59]	KBS	2021	GCN+注意力机制	有效捕获用户特征和关系重要性	模型参数较多，计算量大	图书、音乐
	KHGT^[60]	AAAI	2021	GCN+时间感知	引入时间信息建模动态的用户偏好	内存需求和计算成本较高	电影、零售
	UCPR^[61]	SIGIR	2021	GNN+MDP	实现基于用户需求组合的复杂推理，具有较快的收敛速度	仅考虑和购买历史有关联的项目，对性能有较大影响	电影、图书、电子商务
	TSHGNN^[62]	FGCS	2021	GNN+CNN+Rein-LSTM	根据新闻内容及时间特征充分提取深度新闻特征	LSTM模型设计复杂，且嵌入维数对性能影响较大	新闻
	KGAT^[63]	KDD	2019	GAT+递归传播	有效增强了非活跃用户的表示	训练过程较为繁琐	电影、音乐、图书
	AKGE^[32]	CoRR	2019	GAT+最短路径算法+MLP	充分挖掘KG语义和拓扑信息	复杂度高且易产生过拟合问题	电影、音乐
	KGIN^[64]	WWW	2021	GAT+迭代聚合	全面刻画用户与项目间的关系并保留了路径的整体语义	挖掘路径多跳关系大大增加了模型复杂度	图书、音乐、电子商务

嵌入方法	模型框架	会议	时间	创新应用	优点	局限性	应用场景
传统嵌入方法	KG-WSR^[65]	Symmetry	2019	TransH+用户QoS偏好	数据密度对推荐性能影响小	计算量大，运行时间长	Web服务
	MKM-SR^[66]	SIGIR	2020	TransH+GGNN+GRU	生成更细粒度的会话和用户偏好	收敛性差，且模型复杂度较高	音乐、电商
	AKUPM^[68]	KDD	2019	TransR+注意力机制	降低了无关实体对推荐的影响	忽略了对输入长度可变的考虑	电影、图书
	CKE^[7]	KDD	2016	TransR+深度学习算法	统一联合结构、文本和图像等信息	仅探索了项目的一阶实体语义	电影、图书
	HCE^[69]	PAKDD	2018	TransR+CF+联合学习	能够增强 KG没有包含的项目语义	难以捕获实体间的高阶交互	GitHub
	KGEP^[71]	SOC	2020	TransD+卷积传播	可以充分捕获 KG高阶语义	计算开销大，仅用于 App推荐	App推荐
	MKR^[72]	WWW	2019	语义匹配+交叉压缩单元	利用多任务学习框架挖掘实体交互	数据过于稠密时性能下降明显	电影、图书、音乐、新闻
异质图嵌入	HERec^[73]	TKDE	2019	随机游走+矩阵分解	可以高效地从 KG中提取并利用信息	扩展性差且复杂性受路径影响	电影、图书、商业
	HopRec^[74]	ESWA	2021	HERec+特征交互矩阵	充分挖掘隐含交互信息，性能改善	复杂性高，数据密集易于过拟合	电影、图书、商业
	AMERec^[75]	ESWA	2021	随机游走+深度神经网络	更灵活地从 HIN中提取有效信息	模型的可解释性较差	电影、图书、商业
	DisenHAN^[76]	CIKM	2020	异质图嵌入+嵌入传播层	显式探索异质图的高阶连通性	结构复杂，且难以捕捉动态交互	电影、电商
	HIN-MRS^[77]	Comput	2020	歌曲异质图+主题提取	计算复杂度低，具有较好解释能力	数据集较小，仅适用于音乐推荐	音乐
	SHINE^[8]	WSDM	2018	实体级情感提取	精确抽取用户情感关系	映射到用户编码器中的性能低下	社交网络
	SMR^[78]	Big Data	2021	构建医学异质图+LINE	药物推荐的结果更安全可靠	缺乏临床结果等患者信息	医疗
	DUSKG^[82]	FGCS	2019	多类型服务数据+RAKE	计算效率高，具有良好可扩展性	关系数量对性能影响大，稳定性差	商业
基于图神经网络	KGCN^[83]	WWW	2019	GCN+个性化过滤器	可灵活应用于较大的数据集	聚合器忽略了实体的本身信息，相邻层间的信息无法对比	电影、图书、音乐
	KGQR^[84]	SIGIR	2020	GCN+强化学习	有效降低了样本复杂性和动作空间	难以建模用户的动态偏好	电影、图书
	KGenSam^[86]	TKDE	2021	GCN+MDP	实现了会话推荐的高效在线更新	忽略了多回合会话场景的研究	会话推荐
	KGSF^[87]	KDD	2020	GCN+KG语义融合	训练性能及稳定性较高	忽略历史交互信息且可解释性差	会话推荐
	MVIN^[88]	SIGIR	2020	GCN+多视图网络	高效聚合信息，灵活应用于不同领域	容易产生噪音和过拟合问题	电影、图书、音乐
	IntentGC^[89]	KDD	2019	GCN+IntentNet+堆叠卷积	时间复杂度低，适用于大规模数据集	难以建模动态的交互和用户兴趣	电子商务
	K-NCR^[90]	ESWA	2021	GCN+注意力网络+NCF	显式探索 KG语义，网络稳定性较好	训练时间长，时间复杂性高	电影、图书、音乐、商业
	KCAN^[91]	CIKM	2021	GCN+TransH+注意力机制	能够有效捕获细粒度的用户偏好	时间复杂度高且可解释性较差	电影、图书、音乐、商业
	JNSKR^[92]	SIGIR	2020	GAT+非采样方法	层次架构简单，参数少效率高	难以在细粒度上建模实体相关性	图书、商业
	KRAN^[93]	TKDD	2021	GAT+邻域剪枝	可灵活修改邻域实体的采样大小	还未解决用户冷启动问题	电影、图书、音乐、商业
	CKAN^[94]	SIGIR	2020	GAT+协同传播+KG传播	显式编码协作信息，稳定和灵活性高	不适用于数据过于密集的场景	电影、图书、音乐、商业
	MKGAT^[95]	CIKM	2020	GAT+多模态信息	利用多模态信息提升推荐性能	网络层数对推荐结果影响较大	电影、餐饮
	TEKGR^[96]	CIKM	2020	GAT+GRU	充分考虑新闻标题的主题特征，捕获用户多样化的阅读兴趣，稳定性高	忽略了对新闻摘要和主体内容中实体的考虑	新闻
	KGNN-LS^[97]	KDD	2019	GNN+标签平滑正则化	模型稳定性、泛化能力和扩展性很好	隐藏层维度过大易导致过拟合	电影、图书、音乐
	KGPL^[98]	WSDM	2021	GNN+伪标签标记	有效降低了流行度偏差的影响	难以灵活设置损失函数中的权值	电影、图书、音乐
	SMIN^[99]	CIKM	2021	GNN+自监督互信息学习	充分挖掘交互多维的高阶协作关系	信息传播层增加性能下降明显	社交网络

嵌入方法	模型框架	会议	时间	创新应用	优点	局限性	应用场景
传统嵌入方法	KG-WSR^[65]	Symmetry	2019	TransH+用户QoS偏好	数据密度对推荐性能影响小	计算量大，运行时间长	Web服务
	MKM-SR^[66]	SIGIR	2020	TransH+GGNN+GRU	生成更细粒度的会话和用户偏好	收敛性差，且模型复杂度较高	音乐、电商
	AKUPM^[68]	KDD	2019	TransR+注意力机制	降低了无关实体对推荐的影响	忽略了对输入长度可变的考虑	电影、图书
	CKE^[7]	KDD	2016	TransR+深度学习算法	统一联合结构、文本和图像等信息	仅探索了项目的一阶实体语义	电影、图书
	HCE^[69]	PAKDD	2018	TransR+CF+联合学习	能够增强 KG没有包含的项目语义	难以捕获实体间的高阶交互	GitHub
	KGEP^[71]	SOC	2020	TransD+卷积传播	可以充分捕获 KG高阶语义	计算开销大，仅用于 App推荐	App推荐
	MKR^[72]	WWW	2019	语义匹配+交叉压缩单元	利用多任务学习框架挖掘实体交互	数据过于稠密时性能下降明显	电影、图书、音乐、新闻
异质图嵌入	HERec^[73]	TKDE	2019	随机游走+矩阵分解	可以高效地从 KG中提取并利用信息	扩展性差且复杂性受路径影响	电影、图书、商业
	HopRec^[74]	ESWA	2021	HERec+特征交互矩阵	充分挖掘隐含交互信息，性能改善	复杂性高，数据密集易于过拟合	电影、图书、商业
	AMERec^[75]	ESWA	2021	随机游走+深度神经网络	更灵活地从 HIN中提取有效信息	模型的可解释性较差	电影、图书、商业
	DisenHAN^[76]	CIKM	2020	异质图嵌入+嵌入传播层	显式探索异质图的高阶连通性	结构复杂，且难以捕捉动态交互	电影、电商
	HIN-MRS^[77]	Comput	2020	歌曲异质图+主题提取	计算复杂度低，具有较好解释能力	数据集较小，仅适用于音乐推荐	音乐
	SHINE^[8]	WSDM	2018	实体级情感提取	精确抽取用户情感关系	映射到用户编码器中的性能低下	社交网络
	SMR^[78]	Big Data	2021	构建医学异质图+LINE	药物推荐的结果更安全可靠	缺乏临床结果等患者信息	医疗
	DUSKG^[82]	FGCS	2019	多类型服务数据+RAKE	计算效率高，具有良好可扩展性	关系数量对性能影响大，稳定性差	商业
基于图神经网络	KGCN^[83]	WWW	2019	GCN+个性化过滤器	可灵活应用于较大的数据集	聚合器忽略了实体的本身信息，相邻层间的信息无法对比	电影、图书、音乐
	KGQR^[84]	SIGIR	2020	GCN+强化学习	有效降低了样本复杂性和动作空间	难以建模用户的动态偏好	电影、图书
	KGenSam^[86]	TKDE	2021	GCN+MDP	实现了会话推荐的高效在线更新	忽略了多回合会话场景的研究	会话推荐
	KGSF^[87]	KDD	2020	GCN+KG语义融合	训练性能及稳定性较高	忽略历史交互信息且可解释性差	会话推荐
	MVIN^[88]	SIGIR	2020	GCN+多视图网络	高效聚合信息，灵活应用于不同领域	容易产生噪音和过拟合问题	电影、图书、音乐
	IntentGC^[89]	KDD	2019	GCN+IntentNet+堆叠卷积	时间复杂度低，适用于大规模数据集	难以建模动态的交互和用户兴趣	电子商务
	K-NCR^[90]	ESWA	2021	GCN+注意力网络+NCF	显式探索 KG语义，网络稳定性较好	训练时间长，时间复杂性高	电影、图书、音乐、商业
	KCAN^[91]	CIKM	2021	GCN+TransH+注意力机制	能够有效捕获细粒度的用户偏好	时间复杂度高且可解释性较差	电影、图书、音乐、商业
	JNSKR^[92]	SIGIR	2020	GAT+非采样方法	层次架构简单，参数少效率高	难以在细粒度上建模实体相关性	图书、商业
	KRAN^[93]	TKDD	2021	GAT+邻域剪枝	可灵活修改邻域实体的采样大小	还未解决用户冷启动问题	电影、图书、音乐、商业
	CKAN^[94]	SIGIR	2020	GAT+协同传播+KG传播	显式编码协作信息，稳定和灵活性高	不适用于数据过于密集的场景	电影、图书、音乐、商业
	MKGAT^[95]	CIKM	2020	GAT+多模态信息	利用多模态信息提升推荐性能	网络层数对推荐结果影响较大	电影、餐饮
	TEKGR^[96]	CIKM	2020	GAT+GRU	充分考虑新闻标题的主题特征，捕获用户多样化的阅读兴趣，稳定性高	忽略了对新闻摘要和主体内容中实体的考虑	新闻
	KGNN-LS^[97]	KDD	2019	GNN+标签平滑正则化	模型稳定性、泛化能力和扩展性很好	隐藏层维度过大易导致过拟合	电影、图书、音乐
	KGPL^[98]	WSDM	2021	GNN+伪标签标记	有效降低了流行度偏差的影响	难以灵活设置损失函数中的权值	电影、图书、音乐
	SMIN^[99]	CIKM	2021	GNN+自监督互信息学习	充分挖掘交互多维的高阶协作关系	信息传播层增加性能下降明显	社交网络

嵌入方法	模型框架	会议	时间	创新应用	优点	局限性	应用场景
传统嵌入方法	KSR^[21]	SIGIR	2018	TransE+KV-MN+GRU	同时具有GRU++和KV-MN的优点，性能稳定且推荐结果高度可解释	包含大量参数，结构较复杂，复杂性高且扩展性差	电影、图书、音乐
	会话推荐算法^[101]	Information	2020	TransE+GNN+KV-MN	充分挖掘用户的长期和短期偏好，在冷启动场景下仍保持较好性能	模型性能很大程度上受所构造会话图质量的影响	电影、图书（会话推荐）
	Chorus^[102]	SIGIR	2020	TransE+时间核函数	整合时间信息捕捉动态的用户需求和项目语义，具有较高的可解释性	当关系信息过于稀疏或过于复杂时模型性能较差，且稳定性差	电子商务
	KAeDCN^[103]	CIKM	2021	TransE+动态卷积网络	收敛速度和泛化性能较好	数据集大小对模型性能影响较大	电影、书籍、音乐、电商
	KERL^[104]	SIGIR	2020	TransE+MDP+GRU	高效利用知识信息实现序列化推荐	提升知识探索长度会降低性能	电影、书籍、音乐、电商
	因子分解模型^[105]	SIGIR	2019	TransE+NF+LSTM	充分挖掘用户项目之间更深层次的关联，且模型效率较高	实验集和测试集很小且基线较少，无法进行有力的对比分析	电子商务
	MRP2Rec^[106]	IEEE	2020	TransR+LSTM	能够充分利用 KG语义挖掘多关系路径，有效解决了数据稀疏性问题	路径长度会影响性能，忽略了对实体类型重要性的考虑	电影、图书
	MKM-SR^[66]	SIGIR	2020	TransH+GGNN+GRU	生成更细粒度的会话表示和用户偏好，在冷启动场景中仍具有较好性能	模型收敛性较差且复杂度高，联合训练的实验结果较差	电商、音乐（会话推荐）
异质图嵌入	HERec^[73]	TKDE	2019	异质图嵌入+矩阵分解	能够更有效地提取和利用KG信息，有利于改善冷启动问题	模型扩展性较差且其复杂性受路径质量的影响	电影、图书、商业
	HopRec^[74]	ESWA	2021	HERec+特征交互矩阵	在 HERec基础上融合交互特征挖掘更多的隐含信息	复杂性较高，当数据密集时特征交互项易于过拟合	电影、图书、商业
	HI-LDA^[109]	Neurocomputing	2020	多个社交网络异质信息+MCMC+IPO	利用文本信息挖掘用户潜在偏好	模型迭代采样和文本分析的计算复杂度高，训练时间较长	POI推荐
	SMR^[78]	BigData	2021	医学异质图+LINE	缓解冷启动问题，药物推荐结果可靠	缺乏充足患者信息，如临床结果	医疗
图神经网络	DKN^[111]	WWW	2018	GNN+卷积神经网络	高效学习新闻句子语义，保留单词与实体间关联，捕捉多样化的阅读兴趣	忽略了对新闻主体内容中实体的考虑，不适用于其他领域	新闻
图神经网络	KIM^[112]	SIGIR	2021	GAT+卷积神经网络+ 交互学习	充分挖掘新闻之间的语义关联，提升了用户和候选新闻的匹配度	性能稳定性受编码器网络层数的影响，且训练时间较长	新闻