In scientific social networks, academic groups play a significant role in facilitating collaboration between researchers and promoting the dissemination of papers, which provides unique opportunities for paper recommendation. However, existing paper recommendation methods rarely consider the valuable group information, which limits their potential for improving recommendation performance. In this article, a novel multi-graph fusion network with attention mechanism (GI-MFA) is proposed for paper recommendation considering group information. First, the group-researcher bipartite graph, the researcher-paper bipartite graph and the group-paper bipartite graph are constructed to model the relationships between researchers, papers and groups. Graph neural networks are used to learn the embeddings of researchers and papers at both the individual and group levels across these bipartite graphs. Second, to effectively fuse the individual-level and group-level embeddings, we introduce researcher-wise attention and paper-wise attention mechanisms. To verify the effectiveness of GI-MFA, experiments are conducted on a real-world dataset CiteULike. The experimental results demonstrate the superiority of GI-MFA over all baselines.
JengWHeDJiangJ. User participation in an academic social networking service: a survey of open group users on Mendeley. J Assoc Inf Sci Technol2015; 66: 890–904.
2.
LiYWangRNanG, et al. A personalized paper recommendation method considering diverse user preferences. Decis Support Syst2021; 146: 113546.
3.
BogersTVan den BoschA. Recommending scientific articles using CiteULike. In: Proceedings of the 2008 ACM conference on recommender systems, Lausanne, 23–25 October 2008, pp. 287–290. New York: Association for Computing Machinery.
4.
EmamyKCameronR. CiteULike: a researcher’s social bookmarking service. Ariadne2007; 51: 8.
5.
SunJJiangYChengX, et al. A hybrid approach for article recommendation in research social networks. J Inf Sci2018; 44: 696–711.
6.
WangGZhangXWangH, et al. Group-oriented paper recommendation with probabilistic matrix factorization and evidential reasoning in scientific social network. IEEE Trans Syst Man Cybern Syst2022; 52: 3757–3771.
7.
ZhaoWWuRLiuH. Paper recommendation based on the knowledge gap between a researcher’s background knowledge and research target. Inf Process Manag2016; 52: 976–988.
8.
GuoLYinHChenT, et al. Hierarchical hyperedge embedding-based representation learning for group recommendation. ACM Trans Inf Syst2021; 40: 1–27.
9.
Le Nguyen HoaiN. Towards comprehensive profile aggregation methods for group recommendation based on the latent factor model. Expert Syst Appl2021; 185: 115585.
10.
Zahra MohammadT. A POI group recommendation method in location-based social networks based on user influence. Expert Syst Appl2021; 171: 114593.
11.
AbolghasemiRViedmaEHEngelstadP, et al. A graph neural approach for group recommendation system based on pairwise preferences. Inf Fusion2024; 107: 102343.
12.
WangCWangWYangC, et al. Group-to-group recommendation with neural graph matching. World Wide Web2024; 27: 19.
13.
TianZLiuYSunJ, et al. Exploiting group information for personalized recommendation with graph neural networks. ACM Trans Inf Syst2021; 40: Article 27.
14.
AdomaviciusGTuzhilinA. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng2005; 17: 734–749.
15.
BeelJGippBLangerS, et al. Research-paper recommender systems: a literature survey. Int J Digit Libr2016; 17: 305–338.
16.
JavedUShaukatKAHameedI, et al. A review of content-based and context-based recommendation systems. Int J Emerg Technol Learn2021; 16: 274–306.
17.
PazzaniMJBillsusD. Content-based recommendation systems. In: BrusilovskyPKobsaANejdlW (eds) The adaptive web: methods strategies of web personalization. Berlin: Springer, 2007, pp. 325–341.
18.
ZhangQWuJZhangQ, et al. Dual influence embedded social recommendation. World Wide Web2017; 21: 849–874.
19.
ChenL-SHsuF-HChenM-C, et al. Developing recommender systems with the consideration of product profitability for sellers. Inf Sci2008; 178: 1032–1048.
20.
KangYHouAZhaoZ, et al. A hybrid approach for paper recommendation. IEICE Trans Inf Syst2021; 104: 1222–1231.
21.
WangGHeXIshugaCI. Social and content aware One-Class recommendation of papers in scientific social networks. PLoS ONE2017; 12: e0181380.
22.
WuLHeXWangX, et al. A survey on accuracy-oriented neural recommendation: from collaborative filtering to information-rich recommendation. IEEE Trans Knowl Data Eng2023; 35: 4425–4445.
23.
ZhangSYaoLSunA, et al. Deep learning based recommender system: a survey and new perspectives. ACM Comput Surv2019; 52: 1–38.
24.
DuZTangJDingY. POLAR++: active one-shot personalized article recommendation. IEEE Trans Knowl Data Eng2021; 33: 2709–2722.
25.
ZhengMLiX. A hybrid neural network based on multi-feature fusion for paper recommendation. In: 2023 15th international conference on advanced computational intelligence (ICACI), Seoul, Republic of Korea, 6–9 May 2023, pp. 1–5. New York: IEEE.
26.
LuY-SShihW-YGauH-Y, et al. On successive point-of-interest recommendation. World Wide Web2018; 22: 1151–1173.
27.
SunHXuJZhouR, et al. HOPE: a hybrid deep neural model for out-of-town next POI recommendation. World Wide Web2021; 24: 1749–1768.
28.
WangDWangXXiangZ, et al. Attentive sequential model based on graph neural network for next poi recommendation. World Wide Web2021; 24: 2161–2184.
29.
WangJZhouJWuZ, et al. MARec: a multi-attention aware paper recommendation method. Expert Syst Appl2023; 232: 120847.
30.
NairAMBennyOGeorgeJ. Content based scientific article recommendation system using deep learning technique. In: SumaVChenJIZBaigZ, et al. (eds) Inventive systems and control. Lecture notes in networks and systems. Singapore: Springer, 2021, pp. 965–977.
31.
ChenXXieRQiuZ, et al. Group-based social diffusion in recommendation. World Wide Web2022; 26: 1775–1792.
32.
HaoLLiuSPanL. Paper recommendation based on author-paper interest and graph structure. In: 2021 IEEE 24th international conference on computer supported cooperative work in design (CSCWD), Dalian, China, 5–7 May 2021, pp. 256–261. New York: IEEE.
LiMMicheliAWangYG, et al. Guest editorial: deep neural networks for graphs: theory, models, algorithms, and applications. IEEE Trans Neural Netw Learn Syst2024; 35: 4367–4372.
35.
TaoYWangCYaoL, et al. Item trend learning for sequential recommendation system using gated graph neural network. Neural Comput Appl2021; 35: 13077–13092.
36.
ChaudhuriASarmaMSamantaD. SHARE: designing multiple criteria-based personalized research paper recommendation system. Inf Sci2022; 617: 41–64.
37.
LiMZhangLCuiL, et al. BLoG: bootstrapped graph representation learning with local and global regularization for recommendation. Pattern Recognit2023; 144: 109874.
38.
LiuYYangLSunJ, et al. Collaborative matrix factorization mechanism for group recommendation in big data-based library systems. Libr Hi Tech2018; 36: 458–481.
39.
WangNLiuDZengJ, et al. HGRec: group recommendation with hypergraph convolutional networks. IEEE Trans Comput Soc Syst2024; 11: 4214–4225.
40.
KreutzCKSchenkelR. Scientific paper recommendation systems: a literature review of recent publications. Int J Digit Libr2022; 23: 335–369.
41.
HongKJeonHJeonC. Personalized research paper recommendation system using keyword extraction based on UserProfile. J Converg Inf Technol2013; 8: 106–116.
42.
NascimentoCLaenderASilvaA, et al. A source independent framework for research paper recommendation. In: JCDL ’11: proceedings of the 11th annual international ACM/IEEE joint conference on digital libraries. Ottawa, ON, Canada: Association for Computing Machinery, 2011, pp. 297–306.
43.
BasuCHirshHCohenW, et al. Technical paper recommendation: a study in combining multiple information sources. J Artif Intell Res (JAIR)2001; 14: 231–252.
44.
DesrosiersCKarypisGJR. A comprehensive survey of neighborhood-based recommendation methods. In: RicciFRokachLShapiraB (eds) Recommender systems handbook. New York: Springer, 2010, pp. 107–144.
45.
McNeeSMAlbertICosleyD, et al. On the recommending of citations for research papers. In: Proceedings of the 2002 ACM conference on computer supported cooperative work. New York: Association for Computing Machinery, 2002, pp. 116–125.
46.
TangTMcCallaG. Utilizing artificial learners to help overcome the cold-start problem in a pedagogically-oriented paper recommendation system. In: Adaptive hypermedia and adaptive web-based systems: third international conference, Eindhoven, 23–26 August 2004, pp. 245–254. Cham: Springer.
47.
WangCBleiDM. Collaborative topic modeling for recommending scientific articles. In: Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining, San Diego, CA, 21–24 August 2011, pp. 448–456. New York: Association for Computing Machinery.
48.
HwangS-YWeiC-PHuangY-C, et al. Combining coauthorship network and content for literature recommendation. In: Proceedings of the PACIS, Taipei, 9–12 July 2010, p. 40. Atlanta: Association for Information Systems.
49.
WangGHeXIshugaCI. HAR-SI: a novel hybrid article recommendation approach integrating with social information in scientific social network. Knowl Based Syst2018; 148: 85–99.
50.
JebariCHerrera-ViedmaECoboMJ. Context-aware citation recommendation of scientific papers: comparative study, gaps and trends. Scientometrics2023; 128: 4243–4268.
51.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems. Long Beach, CA: Curran Associates Inc., 2017, pp. 6000–6010.
52.
HuangWLiuBWangZ. Paper recommendation via correlation pattern mining and attention mechanism. J Sens2023; 2023: 3311363.
53.
LuYHeYCaiY, et al. Time-aware neural collaborative filtering with multi-dimensional features on academic paper recommendation. In: 2021 IEEE 24th international conference on computer supported cooperative work in design (CSCWD), Dalian, China, 5–7 May 2021, pp. 1052–1057. New York: IEEE.
54.
ZhuYLinQLuH, et al. Recommending scientific paper via heterogeneous knowledge embedding based attentive recurrent neural networks. Knowl Based Syst2021; 215: 106744.
55.
LiMZhouSChenY, et al. EduCross: dual adversarial bipartite hypergraph learning for cross-modal retrieval in multimodal educational slides. Inf Fusion2024; 109: 102428.
56.
BaiLCuiLWangY, et al. HAQJSK: hierarchical-aligned quantum Jensen-Shannon kernels for graph classification. IEEE Trans Knowl Data Eng2024; 36: 6370–6384.
57.
HuangCLiMCaoF, et al. Are graph convolutional networks with random weights feasible?IEEE Trans Pattern Anal Mach Intell2023; 45: 2751–2768.
58.
WangYWangCZhanJ, et al. Text FCG: fusing contextual information via graph learning for text classification. Expert Syst Appl2023; 219: 119658.
59.
LiMZhuangXBaiL, et al. Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement prediction. Inf Fusion2024; 105: 102224.
60.
ZhouJCuiGHuS, et al. Graph neural networks: a review of methods and applications. AI Open2020; 1: 57–81.
61.
LiJZhengRFengH, et al. Permutation equivariant graph framelets for heterophilous graph learning. IEEE Trans Neural Netw Learn Syst2024; 35: 11634–11648.
62.
KipfTNWellingM. Semi-supervised classification with graph convolutional networks. arXiv:029072016.
63.
VelickovicPCucurullGCasanovaA, et al. Graph attention networks. Stat2017; 1050: 10.48550.
64.
XiaoXXuJHuangJ, et al. TCRec: a novel paper recommendation method based on ternary coauthor interaction. Knowl Based Syst2023; 280: 111065.
65.
TangHLiuBQianJ. Content-based and knowledge graph-based paper recommendation: exploring user preferences with the knowledge graphs for scientific paper recommendation. Concurr Comput Pract Exp2021; 33: e6227.
66.
MeiXCaiXXuS, et al. Mutually reinforced network embedding: an integrated approach to research paper recommendation. Expert Syst Appl2022; 204: 117616.
67.
SonJKimSB. Academic paper recommender system using multilevel simultaneous citation networks. Decis Support Syst2018; 105: 24–33.
68.
XiaFLiuHLeeI, et al. Scientific article recommendation: exploiting common author relations and historical preferences. IEEE Trans Big Data2016; 2: 101–112.
69.
SunZGuoQYangJ, et al. Research commentary on recommendations with side information: a survey and research directions. Electron Commer Res Appl2019; 37: 100879.
70.
WangZLiangJLiR, et al. An approach to cold-start link prediction: establishing connections between non-topological and topological information. IEEE Trans Knowl Data Eng2016; 28: 2857–2870.
71.
HeXDengKWangX, et al. 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, Virtual Event, China, July 25–30 2020, pp. 639–648. New York: Association for Computing Machinery.
72.
ShiCHanXSongL, et al. Deep collaborative filtering with multi-aspect information in heterogeneous networks. IEEE Trans Knowl Data Eng2019; 33: 1413–1425.
73.
WeiYChengZYuX, et al. Personalized hashtag recommendation for micro-videos. In: Proceedings of the 27th ACM international conference on multimedia, Nice, France, October 21–25 2019, pp. 1446–1454. New York: Association for Computing Machinery.
74.
WangHZhangFZhangM, et al. Knowledge-aware graph neural networks with label smoothness regularization for recommender systems. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, Anchorage, Alaska, USA, August 4–8 2019, pp. 968–977. New York: Association for Computing Machinery.
75.
HeXHeZSongJ, et al. NAIS: neural attentive item similarity model for recommendation. IEEE Trans Knowl Data Eng2018; 30: 2354–2366.
76.
Del OlmoFHGaudiosoE. Evaluation of recommender systems: a new approach. Expert Syst Appl2008; 35: 790–804.
77.
WilkinsonJReinschCGolubG, et al. Singular value decomposition and least squares solutions. Linear Algebra1971; 656: 134–151.
78.
GaoLWuJQiaoZ, et al. Collaborative social group influence for event recommendation. In: Proceedings of the 25th ACM international on conference on information and knowledge management, Indianapolis, Indiana, USA, October 24–28 2016, pp. 1941–1944. New York: Association for Computing Machinery.
79.
HeXLiaoLZhangH, et al. Neural collaborative filtering. In: Proceedings of the 26th international conference on world wide web, Perth, Australia, April 3–7 2017, pp. 173–182. New York: Association for Computing Machinery.
80.
CaoDHeXMiaoL, et al. Attentive group recommendation. In: The 41st international ACM SIGIR conference on research & development in information retrieval, Ann Arbor Michigan, USA, July 8–12 2018, pp. 645–654. New York: Association for Computing Machinery.
81.
KimC-HChoiY-RParkJ-D, et al. Leveraging member-group relations via multi-view graph filtering for effective group recommendation. arXiv:2502.090502025.
82.
SaidABerkovskySLucaEWD, et al. Challenge on context-aware movie recommendation: CAMRa2011. In: Proceedings of the fifth ACM conference on recommender systems. Chicago, IL: Association for Computing Machinery, 2011, pp. 385–386.
