基于异质图神经网络的学者研究主题推荐方法研究

doi:10.3772/j.issn.1000-0135.2026.03.003

情报学报

2026, Vol. 45

Issue (3): 350-362 DOI: 10.3772/j.issn.1000-0135.2026.03.003

情报理论与方法

本期目录 | 过刊浏览 | 高级检索

基于异质图神经网络的学者研究主题推荐方法研究

霍朝光^1,2, 但婷婷¹, 逄增瑶¹

1.中国人民大学信息资源管理学院，北京 100872
2.中国人民大学图书馆，北京 100872

Research Topic Recommendation for Scholars Based on Heterogeneous Graph Neural Networks

Huo Chaoguang^1,2, Dan Tingting¹, Pang Zengyao¹

1.School of Information Resource Management, Renmin University of China, Beijing 100872
2.Renmin University of China Libraries, Beijing 100872

摘要
图/表
参考文献
相关文章 (13)

全文: PDF (2667 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要研究主题的选择对于学者科研生涯发展至关重要，但如何从海量学术资源中筛选出契合学者研究基础和研究兴趣的主题仍是一大难题。为此，本文构建了一个面向学者的个性化主题推荐模型，旨在帮助学者快速筛选契合其研究基础和研究兴趣的主题。针对现有推荐方法在学习网络中节点类型与关系类型异质性方面的不足，本文提出一种基于异质图神经网络的学者研究主题推荐模型，构建基于HAN（heterogeneous graph attention network）、HGT（heterogeneous graph transformer）、HGCL（heterogeneous graph contrastive learning）的三种学者和主题特征聚合模式，强调利用消息传递与聚合机制等学习学者与主题间的复杂交互模式，刻画主题扩散与学者选题的规律，在特征聚合基础上，通过逻辑回归、随机森林和多层感知机等分类器进行推荐判别。以Scopus数据库中6521名中国人民大学学者及其涉猎的3万多个研究主题数据为例进行实证检验，研究发现，基于HGCL整合多层感知机的推荐模型精确率最高，达到88.25%，相对于基线模型SVD提升了9.29个百分点；基于HAN整合多层感知机的推荐模型在召回率和F1值上的表现最佳，分别达到96.41%和91.92%，相对于基线模型SVD分别提升了17.21和12.56个百分点。本文首次构建学者研究主题推荐模型，强调对学者与主题节点异质性和关系异质性的表征与学习，为学者个性化选题以及主题层面的学术资源推荐提供了参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	霍朝光
	但婷婷
	逄增瑶

关键词 ：研究主题推荐, 学者选题推荐, 主题推荐, 异质图神经网络, 链路预测

收稿日期: 2025-06-11

基金资助:国家自然科学基金面上项目“基于图机器学习的学科交叉主题识别与预测研究”（72374202）；国家自然科学基金青年科学基金项目“基于广度学习的学科主题演化预测研究”（72004221）。

作者简介: 霍朝光，1990年生，博士，副教授，主要研究方向为科学预测与系统推荐；但婷婷，通信作者，2002年生，硕士研究生，主要研究方向为科学计量与图机器学习，E-mail：dantingting_ruc@126.com；逄增瑶，1993年生，硕士，主要研究方向为科技情报与图机器学习；

引用本文:

霍朝光, 但婷婷, 逄增瑶. 基于异质图神经网络的学者研究主题推荐方法研究[J]. 情报学报, 2026, 45(3): 350-362.
Huo Chaoguang, Dan Tingting, Pang Zengyao. Research Topic Recommendation for Scholars Based on Heterogeneous Graph Neural Networks. 情报学报, 2026, 45(3): 350-362.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2026.03.003 或 https://qbxb.istic.ac.cn/CN/Y2026/V45/I3/350

1 霍朝光, 张斌, 董克. 复杂网络视域下的学术行为预测研究述评: 选题、合作与引用[J]. 情报理论与实践, 2021, 44(6): 180-188, 27.
2 Amjad T, Daud A, Song M. Measuring the impact of topic drift in scholarly networks[C]// Companion Proceedings of the Web Conference 2018. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2018: 373-378.
3 Ma Y H, Ji Z X, Song L. A two-layer network model reveals the adhesion scientist career stage and research topic in China[J]. IEEE Access, 2020, 8: 52726-52737.
4 Ledford H. How to solve the world’s biggest problems[J]. Nature, 2015, 525(7569): 308-311.
5 Zeng A, Shen Z S, Zhou J L, et al. Increasing trend of scientists to switch between topics[J]. Nature Communications, 2019, 10: Article No.3439.
6 蒲姗姗, 何燕. 个性化学术资源推荐研究: 现状、特点及展望[J]. 图书馆学研究, 2019(16): 9-17.
7 张晓娟, 刘怡均, 刘杰, 等. 个性化学术论文推荐研究综述[J]. 情报学报, 2024, 43(1): 106-126.
8 霍朝光, 但婷婷, 罗飞, 等. 基于图神经网络的跨学科引文推荐方法研究[J]. 情报理论与实践, 2025, 48(7): 189-198.
9 Huo C G, Li W J, Han Y J. Recommendation for scholar interdisciplinary collaboration[C]// Proceedings of the Eighteenth International ISKO Conference. Würzburg: Ergon-Verlag, 2024: 371-378.
10 Malhotra R, Taneja A, Arora A. Temporal recommendations for discovering author interests[C]// Proceedings of the 2019 Twelfth International Conference on Contemporary Computing. Piscataway: IEEE, 2019: 1-6.
11 Jelodar H, Wang Y L, Xiao G, et al. Recommendation system based on semantic scholar mining and topic modeling on conference publications[J]. Soft Computing, 2021, 25: 3675-3696.
12 Paul D, Chakdar D, Saha S, et al. Online research topic modeling and recommendation utilizing multiview autoencoder-based approach[J]. IEEE Transactions on Computational Social Systems, 2024, 11(1): 1013-1022.
13 李跃艳, 王昊, 邓三鸿, 等. 近十年信息检索领域的研究热点与演化趋势研究——基于SIGIR会议论文的分析[J]. 数据分析与知识发现, 2021, 5(4): 13-24.
14 Parvatikar S, Joshi B. Online book recommendation system by using collaborative filtering and association mining[C]// Proceedings of the 2015 IEEE International Conference on Computational Intelligence and Computing Research. Piscataway: IEEE, 2015: 1-4.
15 Zhang C X, Song D J, Huang C, et al. Heterogeneous graph neural network[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM Press, 2019: 793-803.
16 Nascimento C, Laender A H F, da Silva A S, et al. A source independent framework for research paper recommendation[C]// Proceedings of the 11th Annual International ACM/IEEE Joint Conference on Digital Libraries. New York: ACM Press, 2011: 297-306.
17 Amami M, Pasi G, Stella F, et al. An LDA-based approach to scientific paper recommendation[C]// Proceedings of 21st International Conference on Applications of Natural Language to Information Systems. Cham: Springer, 2016: 200-210.
18 李晓敏, 王昊, 李跃艳. 基于细粒度语义实体的学术论文推荐研究[J]. 情报科学, 2022, 40(4): 156-165.
19 屈冰洋, 王亚民. 基于深度学习的科技信息文献推荐模型研究[J]. 情报理论与实践, 2021, 44(11): 160-165.
20 杨秀璋, 武帅, 杨琪, 等. 多视图融合TextRCNN的论文自动推荐算法[J]. 计算机工程与应用, 2023, 59(2): 110-119.
21 Tan S C, Zhang T, Zhao S, et al. Self-supervised scientific document recommendation based on contrastive learning[J]. Scientometrics, 2023, 128(9): 5027-5049.
22 Di Rocco J, Di Ruscio D, Di Sipio C, et al. TopFilter: an approach to recommend relevant GitHub topics[C]// Proceedings of the 14th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement. New York: ACM Press, 2020: Article No.21.
23 Pennock D M, Horvitz E J, Lawrence S, et al. Collaborative filtering by personality diagnosis: a hybrid memory- and model-based approach[C]// Proceedings of the 16th Uncertainty in Artificial Intelligence. San Francisco: Morgan Kaufmann, 2000: 473-480.
24 Wang W, Tang T, Xia F, et al. Collaborative filtering with network representation learning for citation recommendation[J]. IEEE Transactions on Big Data, 2022, 8(5): 1233-1246.
25 Izadi M, Nejati M, Heydarnoori A. Semantically-enhanced topic recommendation systems for software projects[J]. Empirical Software Engineering, 2023, 28(2): Article No.50.
26 Gupta S, Varma V. Scientific article recommendation by using distributed representations of text and graph[C]// Proceedings of the 26th International Conference on World Wide Web Companion. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2017: 1267-1268.
27 Sedhain S, Menon A K, Sanner S, et al. AutoRec: autoencoders meet collaborative filtering[C]// Proceedings of the 24th International Conference on World Wide Web. New York: ACM Press, 2015: 111-112.
28 Cao S S, Lu W, Xu Q K. Deep neural networks for learning graph representations[C]// Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2016: 1145-1152.
29 Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
30 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.
31 Wang X, Ji H Y, Shi C, et al. Heterogeneous graph attention network[C]// Proceedings of the World Wide Web Conference. New York: ACM Press, 2019: 2022-2032.
32 霍朝光. 科学预测——预见科学之美[M]. 北京: 清华大学出版社, 2025: 57-60.
33 Huo C G, Han Y J, Huo F F, et al. An approach for interdisciplinary knowledge discovery: link prediction between topics[J]. Physica A: Statistical Mechanics and Its Applications, 2025, 665: 130517.
34 Zaheer M, Guruganesh G, Dubey A, et al. BigBird: transformers for longer sequences[C]// Proceedings of the 34th Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2020: 17283-17297.
35 Schuster M, Paliwal K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681.
36 Hu Z N, Dong Y X, Wang K S, et al. Heterogeneous graph transformer[C]// Proceedings of the Web Conference 2020. New York: ACM Press, 2020: 2704-2710.
37 Chen M R, Huang C, Xia L H, et al. Heterogeneous graph contrastive learning for recommendation[C]// Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. New York: ACM Press, 2023: 544-552.
38 He X R, Liu S, Keung J, et al. Co-clustering for federated recommender system[C]// Proceedings of the ACM Web Conference 2024. New York: ACM Press, 2024: 3821-3832.
39 Ba Q L, Li X Y, Bai Z Y. Clustering collaborative filtering recommendation system based on SVD algorithm[C]// Proceedings of the 2013 IEEE 4th International Conference on Software Engineering and Service Science. Piscataway: IEEE, 2013: 963-967.
40 Lemire D, Maclachlan A. Slope One predictors for online rating-based collaborative filtering[C]// Proceedings of the 5th SIAM International Conference on Data Mining. Philadelphia: SIAM, 2005: 471-475.