Curriculum–Vacancy–Course Recommendation Model Based on Knowledge Graphs, Sentence Transformers, and Graph Neural Networks
Abstract
1. Introduction
2. Methods
2.1. Dataset
2.2. Methods
3. Results and Discussions
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; Yu, P.S. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2020, 32, 4–24. [Google Scholar] [CrossRef]
- Ju, W.; Wu, X.; Liu, X.; Zhou, T.; Chen, Q.; Huang, J.; Wang, Y. A survey of graph neural networks in real world: Imbalance, noise, privacy and OOD challenges. arXiv 2024, arXiv:2403.04468. Available online: https://arxiv.org/pdf/2403.04468 (accessed on 30 July 2025).
- Dai, E.; Wang, X.; Liu, Y.; Wu, Y.; Yu, P.S. A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability. Front. Comput. Sci. 2024, 18, 1510. [Google Scholar] [CrossRef]
- Wang, Y.; Xu, Z.; Zhang, H.; Xu, C.; Tao, D. A survey on graph neural networks for time series: Forecasting, classi-fication, imputation, and anomaly detection. arXiv 2023, arXiv:2307.03759. Available online: https://arxiv.org/pdf/2307.03759 (accessed on 30 July 2025).
- Khemani, B.; Patil, S.; Kotecha, K.; Tanwar, S. A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions. J. Big Data 2024, 11, 18. [Google Scholar] [CrossRef]
- Chen, J.; Tang, Y.; Gu, Q.; Xu, J. Rewiring techniques to mitigate oversquashing and oversmoothing in GNNs: A survey. arXiv 2024, arXiv:2411.17429. Available online: https://arxiv.org/pdf/2411.17429 (accessed on 30 July 2025).
- Akansha, S. Over-squashing in Graph Neural Networks: A comprehensive survey. Neurocomputing 2025, 642, 130389. [Google Scholar] [CrossRef]
- Wu, S.; Sun, F.; Zhang, W.; Xie, X.; Cui, B. Graph neural networks in recommender systems: A survey. ACM Comput. Surv. 2022, 55, 1–37. [Google Scholar] [CrossRef]
- Gao, C.; Zheng, Y.; Li, N.; Li, Y.; Qin, Y.; Piao, J.; Quan, Y.; Chang, J.; Jin, D.; He, X.; et al. A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Trans. Recomm. Syst. 2023, 1, 1–51. [Google Scholar] [CrossRef]
- Duricic, T.; Kowald, D.; Lacic, E.; Lex, E. Beyond-accuracy: A review on diversity, serendipity, and fairness in recommender systems based on graph neural networks. Front. Big Data 2023, 6, 1251072. [Google Scholar] [CrossRef]
- Wu, B.; Wang, Y.; Zeng, Y.; Liu, J.; Zhao, J.; Yang, C.; Li, Y.; Xia, L.; Yin, D.; Shi, C. Graph Foundation Models for Recommendation: A Comprehensive Survey. arXiv 2025, arXiv:2502.08346. Available online: https://arxiv.org/pdf/2502.08346 (accessed on 30 July 2025).
- Gharizadeh, A.; Abbasi, K.; Ghareyazi, A.; Mofrad, M.R.K.; Rabiee, H.R. HGTDR: Advancing drug repurposing with heterogeneous graph transformers. Bioinformatics 2024, 40, btae349. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Liu, C.; Han, Y.; Xu, H.; Yang, S.; Wang, K.; Su, Y. A community detection and graph-neural-network-based link prediction approach for scientific literature. Mathematics 2024, 12, 369. [Google Scholar] [CrossRef]
- Qin, M.; Yeung, D.-Y. Temporal link prediction: A unified framework, taxonomy, and review. ACM Comput. Surv. 2023, 56, 1–40. [Google Scholar] [CrossRef]
- Liang, J.; Pu, C.; Shu, X.; Xia, Y.; Xia, C. Line graph neural networks for link weight prediction. Phys. A Stat. Mech. Its Appl. 2025, 661, 130406. [Google Scholar] [CrossRef]
- Hou, Y.; Holder, L.B. Link weight prediction with node embeddings. arXiv 2018, arXiv:1805.07312. [Google Scholar]
- Zulaika, U.; Sánchez-Corcuera, R.; Almeida, A.; López-De-Ipiña, D. LWP-WL: Link weight prediction based on CNNs and the Weisfeiler-Lehman algorithm. Appl. Soft Comput. 2022, 120, 108657. [Google Scholar] [CrossRef]
- Fan, W.; Ma, Y.; Li, Q.; He, Y.; Zhao, E.; Tang, J.; Yin, D. Graph Neural Networks for Social Recommendation. In Proceedings of The World Wide Web Conference (WWW ‘19), New York, NY, USA, 13–17 May 2019; Association for Computing Machinery: New York, NY, USA, 2019; pp. 417–426. [Google Scholar]
- Wang, X.; Ji, H.; Shi, C.; Wang, B.; Ye, Y.; Cui, P.; Yu, P.S. Heterogeneous graph attention network. In Proceedings of the World Wide Web Conference, New York, NY, USA, 13–17 May 2019; pp. 2022–2032. [Google Scholar]
- Hu, Z.; Dong, Y.; Wang, K.; Sun, Y. Heterogeneous graph transformer. In Proceedings of the Web Conference, Taipei, Taiwan, 20–24 April 2020; pp. 2704–2710. [Google Scholar]
- Ramazanova, V.; Sambetbayeva, M.; Serikbayeva, S.; Sadirmekova, Z.; Yerimbetova, A. Development of a Knowledge Graph-Based Model for Recommending MOOCs to Supplement University Educational Programs in Line With Employer Requirements. IEEE Access 2024, 12, 193313–193331. [Google Scholar] [CrossRef]
- Guo, Y.; Li, S.; Lerman, G. The effect of Leaky ReLUs on the training and generalization of overparameterized net-works. arXiv 2024, arXiv:2402.11942. [Google Scholar]
- Pytorch-Geometric. Link Regression on MovieLens. Available online: https://colab.research.google.com/drive/1N3LvAO0AXV4kBPbTMX866OwJM9YS6Ji2?usp=sharing#scrollTo=Ptk1J307IVn8 (accessed on 30 July 2025).
- Zhong, M.; Wu, Z.; Honda, N. Deep Learning Based Dense Retrieval: A Comparative Study. arXiv 2024, arXiv:2410.20315. [Google Scholar]
- Jakobs, M.; Liebig, T. AALF: Almost Always Linear Forecasting. arXiv 2024, arXiv:2409.10142. [Google Scholar]
- Yu, T.; Wang, Y.; Cheng, F.; Liang, T.; Liu, H. Service recommendation method based on text view and interaction view. Sci. Rep. 2025, 15, 11679. [Google Scholar] [CrossRef]
- StellarGraph. HinSAGE Link Prediction Demonstration. Available online: https://stellargraph.readthedocs.io/en/stable/demos/link-prediction/hinsage-link-prediction.html (accessed on 30 July 2025).
- Giabelli, A.; Malandri, L.; Mercorio, F.; Mezzanzanica, M.; Seveso, A. Skills2Job: A recommender system that encodes job offer embeddings on graph databases. Appl. Soft Comput. 2021, 101, 107049. [Google Scholar] [CrossRef]
- Zhu, G.; Chen, Y.; Wang, S. Graph-Community-Enabled personalized course-job recommendations with cross-domain data integration. Sustainability 2022, 14, 7439. [Google Scholar] [CrossRef]
- Weichselbraun, A.; Waldvogel, R.; Fraefel, A.; van Schie, A.; Kuntschik, P. Building knowledge graphs and recommender systems for suggesting reskilling and upskilling options from the web. Information 2022, 13, 510. [Google Scholar] [CrossRef]
- Fettach, Y.; Ghogho, M.; Benatallah, B. Knowledge graphs in education and employability: A survey on applications and techniques. IEEE Access 2022, 10, 80174–80183. [Google Scholar] [CrossRef]
- Troussas, C.; Krouska, A.; Tselenti, P.; Kardaras, D.K.; Barbounaki, S. Enhancing Personalized Educational Content Recommendation through Cosine Similarity-Based Knowledge Graphs and Contextual Signals. Information 2023, 14, 505. [Google Scholar] [CrossRef]
- Li, X.; Henriksson, A.; Duneld, M.; Nouri, J.; Wu, Y. Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation. Futur. Internet 2024, 16, 12. [Google Scholar] [CrossRef]
- Wei, L.; Li, Y.; Wang, W.; Zhu, Y. Enhancing Knowledge-Concept Recommendations with Heterogeneous Graph-Contrastive Learning. Mathematics 2024, 12, 2324. [Google Scholar] [CrossRef]
- Chamieh, I.; Zesch, T.; Giebermann, K. LLMs in Short Answer Scoring: Limitations and Promise of Zero-Shot and Few-Shot Approaches. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), Mexico City, Mexico, 20 June 2024; Association for Computational Linguistics: Stroudsburg, PA, USA, 2024; pp. 309–315. Available online: https://aclanthology.org/2024.bea-1.25.pdf (accessed on 30 July 2025).
Node Type | Description | Numbers of Nodes | |
---|---|---|---|
From Training Set | From the Test Set | ||
CUA | User Competency | 125 | 30 |
SkillMastered | Job Skill Already Acquired by the User | 371 | |
Vacancy | Job Vacancy from the Labor Market | 3478 | |
Skill | Unacquired Skill Required for Job Vacancies | 2676 | |
MSkill | Online Course Skill | 791 | |
MCourse | Massive Open Online Course (MOOC) | 877 |
Edge Type | Direction | Number of Edges (Train) | Number of Edges (Test) |
---|---|---|---|
IS_SIMILAR_TO | CUA → SkillMastered | 155 | 37 |
GROUPED_WITH_SKILL | SkillMastered–SkillMastered | 778 | |
REQUIRE_SKILL | SkillMastered ← Vacancy | 7600 | |
Vacancy → Skill | 17,749 | ||
IS_SIMILAR_TO2 | Skill → MSkill | 299 | |
GROUPED_WITH_MSKILL | MSkill–MSkill | 2622 | |
DEVELOPED_BY | MSkill → MCourse | 6074 | |
metapath_0 | CUA → SkillMastered–SkillMastered → Vacancy → Skill → MSkill–MSkill → MCourse CUA → SkillMastered ↔ SkillMastered → Vacancy → Skill → MSkill → MCourse CUA → SkillMastered → Vacancy → Skill → MSkill ↔ MSkill → MCourse CUA → SkillMastered → Vacancy → Skill → MSkill → MCourse | 12,274 | 1886 |
metapath_1 | 7659 | 1267 | |
metapath_2 | 17,856 | 2710 | |
metapath_3 | 10,195 | 1615 | |
CONNECTED_TO | CUA → MCourse (training scores) | 24,108 | 4875 |
Element | Description | Dimension/Quantity |
---|---|---|
Node type | CUA, SkillMastered, Vacancy, Skill, MSkill, MCourse | 6 |
Edge type | IS_SIMILAR_TO, GROUPED_WITH_SKILL, REQUIRE_SKILL, IS_SIMILAR_TO2, GROUPED_WITH_MSKILL, DEVELOPED_BY, rev_IS_SIMILAR_TO, rev_REQUIRE_SKILL, rev_IS_SIMILAR_TO2, rev_DEVELOPED_BY | 10, 6 forward edges, 4 reverse edges |
Node features X | эмбeддинги paraphrase-multilingual-mpnet-base-v2 | 768 |
Target edges | CONNECTED_TO | [0, 1] |
Matrices | Feature matrix (embeddings) for type , from the set of all matrices of size , where is the number of nodes of type e in the graph |
Element | Description | Dimension/Quantity |
---|---|---|
Node types | CUA, SkillMastered, Vacancy, Skill, MSkill, MCourse | 6 |
Edge types | IS_SIMILAR_TO, GROUPED_WITH_SKILL, REQUIRE_SKILL, IS_SIMILAR_TO2, GROUPED_WITH_MSKILL, DEVELOPED_BY, rev_IS_SIMILAR_TO, rev_REQUIRE_SKILL, rev_IS_SIMILAR_TO2, rev_DEVELOPED_BY metapath_0, metapath_1, metapath_2, metapath_3, rev_metapath_0, rev_metapath_1, rev_metapath_2, rev_metapath_3 | 18, 10 forward edges, 6 reverse edges |
HGT-Based | GraphSAGE-Based | HAN-Based | ||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dataset Type | k | RMSE | Precision@ k | Recall@ k | MAP@ k | NDCG@k | RMSE | Precision@ k | Recall@ k | MAP@ k | NDCG@k | RMSE | Precision @k | Recall@ k | MAP@ k | NDCG@k |
training | 5 | 0.0952 | 0.8177 | 0.481 | 0.8334 | 0.8911 | 0.1893 | 0.3858 | 0.1866 | 0.3042 | 0.543 | 0.1549 | 0.4637 | 0.207 | 0.3788 | 0.5715 |
10 | 0.0952 | 0.6487 | 0.626 | 0.795 | 0.8983 | 0.1893 | 0.4071 | 0.341 | 0.3517 | 0.6033 | 0.1549 | 0.431 | 0.3426 | 0.3955 | 0.6123 | |
15 | 0.0952 | 0.5676 | 0.7377 | 0.7944 | 0.9067 | 0.1893 | 0.4165 | 0.5129 | 0.3991 | 0.6498 | 0.1549 | 0.4012 | 0.4663 | 0.4032 | 0.6435 | |
20 | 0.0952 | 0.5097 | 0.8252 | 0.8001 | 0.9127 | 0.1893 | 0.373 | 0.584 | 0.3991 | 0.6648 | 0.1549 | 0.3726 | 0.5579 | 0.4096 | 0.6632 | |
testing | 5 | 0.259 | 0.5571 | 0.3056 | 0.5739 | 0.6973 | 0.2211 | 0.3071 | 0.2169 | 0.2957 | 0.5397 | 0.2039 | 0.4 | 0.2328 | 0.3873 | 0.5812 |
10 | 0.259 | 0.4857 | 0.4265 | 0.5508 | 0.7139 | 0.2211 | 0.2929 | 0.3021 | 0.3083 | 0.59 | 0.2039 | 0.3107 | 0.3065 | 0.3446 | 0.614 | |
15 | 0.259 | 0.4286 | 0.5022 | 0.524 | 0.7319 | 0.2211 | 0.3167 | 0.4394 | 0.3428 | 0.6379 | 0.2039 | 0.2786 | 0.362 | 0.3397 | 0.6332 | |
20 | 0.259 | 0.3839 | 0.5921 | 0.5226 | 0.7388 | 0.2211 | 0.2821 | 0.477 | 0.336 | 0.6503 | 0.2039 | 0.2661 | 0.4198 | 0.34 | 0.6523 |
Meta-Paths | CUA–MasteredSkill–Vacancy, CUA–MasteredSkill–MasteredSkill–Vacancy | Vacancy–Skill–Mskill–Mcourse, Vacancy–Skill–Skill–Mskill–Mcourse, Vacancy–Skill–Mskill–Mskill–Mcourse, Vacancy–Skill–Skill–Mskill–Mskill–Mcourse | Metapath_0, Metapath_1, Metapath_2, Metapath_3 | |||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dataset Type | k | RMSE | Precision@k | Recall@k | MAP@k | NDCG@k | RMSE | Precision@k | Recall@k | MAP@k | NDCG@k | RMSE | Precision@k | Recall@k | MAP@k | NDCG@k |
training | 5 | 0.0581 | 0.7632 | 0.6177 | 0.9803 | 0.9878 | 0.0793 | 0.7463 | 0.6515 | 0.9553 | 0.9718 | 0.0916 | 0.8372 | 0.5017 | 0.8613 | 0.9080 |
10 | 0.0581 | 0.6176 | 0.7375 | 0.9797 | 0.9904 | 0.0793 | 0.5888 | 0.7988 | 0.9505 | 0.9757 | 0.0916 | 0.6690 | 0.6605 | 0.8309 | 0.9145 | |
15 | 0.0581 | 0.5323 | 0.7994 | 0.9792 | 0.9926 | 0.0793 | 0.4987 | 0.8769 | 0.9516 | 0.9785 | 0.0916 | 0.5841 | 0.7640 | 0.8321 | 0.9188 | |
20 | 0.0581 | 0.4684 | 0.8307 | 0.9771 | 0.9927 | 0.0793 | 0.4375 | 0.9313 | 0.9554 | 0.9813 | 0.0916 | 0.5142 | 0.8390 | 0.8300 | 0.9196 | |
testing | 5 | 0.1084 | 0.7933 | 0.5781 | 0.9667 | 0.9804 | 0.1419 | 0.7283 | 0.6048 | 0.9205 | 0.9587 | 0.2098 | 0.5500 | 0.3053 | 0.5698 | 0.7159 |
10 | 0.1084 | 0.6467 | 0.7335 | 0.9667 | 0.9871 | 0.1419 | 0.5884 | 0.7549 | 0.9179 | 0.9635 | 0.2098 | 0.4857 | 0.4229 | 0.5578 | 0.7414 | |
15 | 0.1084 | 0.5378 | 0.7798 | 0.9667 | 0.9909 | 0.1419 | 0.5097 | 0.8503 | 0.9191 | 0.9675 | 0.2098 | 0.4452 | 0.5154 | 0.5425 | 0.7588 | |
20 | 0.1084 | 0.4733 | 0.8147 | 0.9613 | 0.9906 | 0.1419 | 0.4508 | 0.9121 | 0.9224 | 0.9711 | 0.2098 | 0.4107 | 0.6223 | 0.5395 | 0.7728 |
Author | Task | Datasets | Model | Graph View | Metrics | MSE | RMSE |
---|---|---|---|---|---|---|---|
[12] | Link prediction | PrimeKG diseases | BioBERT, ChemBERTa, HGT | heterogeneous semi-weighted graph | AUROC, AUPR | - | - |
[13] | Link prediction | Science articles | GCN, GAT, GraphSAGELouvain method | heterogeneous unweighted graph | P, R, F-1, AUC | - | - |
[15] | Link weight prediction | Neurons, metabolites, article authors, blogs, users | Line Graph-Based Link Weight Prediction | homogeneous weighted graph | RMSE | - | 0.06–0.18 |
[16] | Link weight prediction | airports, nations, US Congress, forum users, coauthors, committees | Fully connected neural network, Model R | homogeneous weighted graph | MSE | 0.02 | - |
[17] | Link weight prediction | airports, nations, US Congress, forum users, coauthors, committees | Linked Weight Prediction Weisfeiler-Lehman | homogeneous weighted graph | MSE | 0.007–0.019 | - |
[7] | Rating prediction | Social communication | GraphRec | heterogeneous weighted graph | MAE, RMSE | - | 0.24–0.26 |
[23] | Link regression | IMDB ratings | SBERT, GraphSAGE | heterogeneous weighted graph | RMSE | - | 0.22 |
[27] | Link attribute inference | IMDB ratings | HinSAGE | heterogeneous weighted graph | RMSE | - | 0.25 |
Our work | Link regression | Cross-domain competencies–job–educational dataset | SBERT, HAN | heterogeneous semi-weighted graph | RMSE, P, R, MAP, NDCG | 0.04 | 0.2 |
Our work | Link regression | User competencies–skills– vacancies courses | SBERT, HGT | heterogeneous semi-weighted graph | RMSE, P, R, MAP, NDCG | 0.02–0.04 | 0.1–0.2 |
Authors | University Courses | MOOC | Additional Learning Resources | Classifiers SOC, ESCO, DWA | Vacancies | Language | KG | Language Models | Recommendation Mechanism |
---|---|---|---|---|---|---|---|---|---|
[28] | - | - | - | + | + | English, German, French | + | FastText | KG |
[29] | + | + | - | - | + | English | + | BM25, Word2Vec, Bert | MetaPath2vec |
[30] | + | - | - | + | - | English | + | SBert: distilbert-base- german-cased | KG, semantic search |
[31] | - | + | - | - | + | English | + | - | KG |
[32] | + | - | + | - | - | English | + | - | Cosine similarity, KG |
[33] | - | - | + | - | - | Swedish | + | sentence KB-BERT, LLM text-embedding-ada-002, ConceptNet Numberbatch | MLP |
[34] | - | + | - | - | - | English | + | - | GCN, contructive learning |
Our approach | + | + | - | - | + | Kazakh, Russian, English | + | SBert: paraphrase-multilingual-mpnet-base-v2 | HGT-based recommendation model |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ramazanova, V.; Sambetbayeva, M.; Serikbayeva, S.; Yerimbetova, A.; Lamasheva, Z.; Sadirmekova, Z.; Kalman, G. Curriculum–Vacancy–Course Recommendation Model Based on Knowledge Graphs, Sentence Transformers, and Graph Neural Networks. Technologies 2025, 13, 340. https://doi.org/10.3390/technologies13080340
Ramazanova V, Sambetbayeva M, Serikbayeva S, Yerimbetova A, Lamasheva Z, Sadirmekova Z, Kalman G. Curriculum–Vacancy–Course Recommendation Model Based on Knowledge Graphs, Sentence Transformers, and Graph Neural Networks. Technologies. 2025; 13(8):340. https://doi.org/10.3390/technologies13080340
Chicago/Turabian StyleRamazanova, Valiya, Madina Sambetbayeva, Sandugash Serikbayeva, Aigerim Yerimbetova, Zhanar Lamasheva, Zhanna Sadirmekova, and Gulzhamal Kalman. 2025. "Curriculum–Vacancy–Course Recommendation Model Based on Knowledge Graphs, Sentence Transformers, and Graph Neural Networks" Technologies 13, no. 8: 340. https://doi.org/10.3390/technologies13080340
APA StyleRamazanova, V., Sambetbayeva, M., Serikbayeva, S., Yerimbetova, A., Lamasheva, Z., Sadirmekova, Z., & Kalman, G. (2025). Curriculum–Vacancy–Course Recommendation Model Based on Knowledge Graphs, Sentence Transformers, and Graph Neural Networks. Technologies, 13(8), 340. https://doi.org/10.3390/technologies13080340