International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 18, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 1372KB)
A Hybrid Attribute Enhanced Graph Neural Framework for Mitigating Data Sparsity and Cold Start Recommendations
PDF (1372KB), PP.130-151
Views: 0 Downloads: 0
Author(s)
Index Terms
Sparsity, Cold Start Recommendation, Heterogeneous Graph Embedding, Collaborative Filtering, Neural graph Collaborative Learning, Representation Learning
Abstract
Recommender system commonly suffers from data sparsity and cold-start problems, where user-item interactions hinder reliable preference learning. While recent Graph Neural Network based models such as LightGCN and NGCF effectively capture higher-order collaborative signals, they primarily rely on interaction-derived embeddings and remain sensitive to sparse environments. This paper Attribute Enabled Graph Neural Framework (AE-GNF) proposes a Semantic-Aware Graph Refinement Framework that integrates attribute-driven representation learning with graph-based collaborative propagation to address these limitations. The proposed method first encodes heterogeneous user and item attributes using semantic embedding modules to generate informative initial representations independent of interaction density. Dense sematic embeddings are generated using modality specific neural encoders including transformer based text encoder for descriptive attributes, a recurrent attention network for behavioral interaction sequences and temporal contextual feature encoder for metadata signals. These embeddings are then refined through a normalized graph propagation mechanism that jointly models structural connectivity and semantic similarity, enabling robust higher-order preference learning. Unlike conventional recommenders, the framework preserves attribute semantics during message passing and enables inductive cold-start recommendations, where embeddings for newly introduced users or items are generated directly from attributes without requiring prior interaction edges. Experimental evaluation conducted on publicly available benchmark datasets including MovieLens-1M, Amazon Electronics, Amazon Books, and Amazon Prime Movies and LastFM360 demonstrates consistent performance improvements over Matrix Factorization, content-based models, GraphSAGE and Neural Graph Collaborative Filtering (NGCF). Results show notable gains in ranking accuracy, diversity and robustness under varying sparsity levels. The proposed AE-GNF achieves improved recommendation performance reducing RMSE by 3.5 to 6.2% and improving NDCG@10 by 6-11% compared to graph-based baselines across benchmark datasets. The findings confirm that integrating semantic attribute encoding with graph refinement provides a scalable and effective solution for next-generation recommendation systems operating in sparse and heterogeneous environments.
Cite This Paper
Alwin Infant P., P. Mohan Kumar, "A Hybrid Attribute Enhanced Graph Neural Framework for Mitigating Data Sparsity and Cold Start Recommendations", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.3, pp.130-151, 2026. DOI:10.5815/ijitcs.2026.03.09
Reference
[1]Y. Koren, R. Bell and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems", Computer, vol. 42, no. 8, pp. 30-37, Aug. 2009, DOI: 10.1109/MC.2009.263
[2]Dheeraj Bokde, Sheetal Girase, Debajyoti Mukhopadhyay, “Matrix Factorization Model in Collaborative Filtering Algorithms: A Survey”, Procedia Computer Science, ISSN 1877-0509, Vol. 49, pp.136-146, 2015, DOI:10.1016/j.procs.2015.04.237
[3]Isinkaye, F. O, “Matrix Factorization in Recommender Systems: Algorithms, Applications, and Peculiar Challenges”, IETE Journal of Research, Vol. 69 No.9, pp. 6087–6100, 2023, DOI: 10.1080/03772063.2021.1997357.
[4]Sarwar, B., Karypis, G., Konstan, J., & Riedl, J, “Item-Based Collaborative Filtering Recommendation Algorithms”, In Proceedings of the 10th International Conference on World Wide Web (WWW), pp.285–295, 2001, DOI: 10.1145/371920.37207
[5]Lops, P., de Gemmis, M., Semeraro, G, “Content-based Recommender Systems: State of the Art and Trends”, In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds) Recommender Systems Handbook. Springer, Boston, MA., 2011, DOI:10.1007/978-0-387-85820-3_3
[6]Zhang, F., Yuan, N. J., Lian, D., Xie, X., & Ma, W.-Y, “Collaborative Knowledge Base Embedding for Recommender Systems”, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 353–362, 2016, DOI:10.1145/2939672.2939673
[7]McAuley, J., & Leskovec, J, “Hidden Factors and Hidden Topics: Understanding Rating Dimensions with Review Text”, Proceedings of the 7th ACM Conference on Recommender Systems (RecSys), pp.165–172, 2013, DOI: 10.1145/2507157.250716
[8]Burke, R., “Hybrid Recommender Systems: Survey and Experiments”, User Modeling and User-Adapted Interaction, Vol.12, pp. 331–370, 2002, DOI:10.1023/A:1021240730564.
[9]Rendle, Steffen. "Factorization machines.", 2010 IEEE International Conference on Data Mining, pp. 995-1000, 2010, DOI:10.1109/ICDM.2010.1
[10]Kwon Y, Bak G, Bae Y, “A Hybrid Recommendation System Based on Similar-Price Content in a Large-Scale E-Commerce Environment”, Applied Sciences, Vol.15(19), pp.10758, 2025, DOI:10.3390/app151910758
[11]Singh, Ajit P., and Geoffrey J. Gordon, "Relational Learning Via Collective Matrix Factorization", Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 650-658. 2008, DOI:10.1145/1401890.1401969
[12]Wu, Yao, Christopher DuBois, Alice X. Zheng, and Martin Ester, "Collaborative Denoising Auto-Encoders for Top-N Recommender Systems", Proceedings of the ninth ACM International Conference on Web Search and Data Mining, pp. 153-162, 2016, DOI:10.1145/2835776.2835837
[13]He, Xiangnan, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua, "Neural Collaborative Filtering", Proceedings of the 26th International Conference on World Wide Web, pp. 173-182, 2017, DOI:10.1145/3038912.3052569
[14]Chen, Wanyu, Fei Cai, Honghui Chen, and Maarten De Rijke, "Joint Neural Collaborative Filtering for Recommender Systems", ACM Transactions on Information Systems (TOIS), Vol. 37, No. 4, pp. 1-30, 2019, DOI:10.1145/3343117
[15]Hamilton, W. L., Ying, R., & Leskovec, J, “Inductive Representation Learning on Large Graph”, In Advances in Neural Information Processing Systems”, pp. 1024–1034, 2017, DOI:10.48550/arXiv.1706.02216
[16]Berg, R., Kipf, T. N., Welling, M, “Graph Convolutional Matrix Completion”, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), pp. 1073–1082, 2018, DOI: 10.48550/arXiv.1706.02263
[17]Wang, X., He, X., Wang, M., Feng, F., Chua, T.S, “Neural Graph Collaborative Filtering”, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 165–174, 2019, DOI: 10.1145/3331184.3331267
[18]Wang, X., Jin, H., Zhang, A., He, X., Chua, T.S, “Disentangled Graph Collaborative Filtering”, Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 1001–1010, 2020, DOI:10.1145/3397271.3401137
[19]He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M, “LightGCN: Simplifying and Powering Graph Convolution Network For Recommendation”, Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 639–648, 2020, DOI: 10.1145/3397271.3401063
[20]Ding, Jingtao, Guanghui Yu, Xiangnan He, Fuli Feng, Yong Li, and Depeng Jin, "Sampler Design For Bayesian Personalized Ranking By Leveraging View Data", IEEE Transactions on Knowledge and Data Engineering, Vol.33, No. 2, pp. 667-681, 2019, DOI: 10.1109/TKDE.2019.2931327
[21]Hu, Hongsheng, Gillian Dobbie, Zoran Salcic, Meng Liu, Jianbing Zhang, and Xuyun Zhang, "A Locality Sensitive Hashing Based Approach for Federated Recommender System", 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), pp. 836-842, 2020, DOI:10.1109/CCGrid49817.2020.000-1
[22]W. Lin et al., "A Locality-Sensitive-Hashing-Based Collaborative Recommendation Method for Responsible AI-Driven Recommender Systems", IEEE Transactions on Artificial Intelligence, Vol. 6, No. 2, pp. 393-404, 2025, DOI:10.1109/TAI.2024.3381571
[23]Zhao, Xiangyu, Long Xia, Liang Zhang, Zhuoye Ding, Dawei Yin, and Jiliang Tang, "Deep Reinforcement Learning for Page-Wise Recommendations", Proceedings of the 12th ACM conference on recommender systems, pp. 95-103, 2018, DOI:10.1145/3240323.3240374
[24]Lin, Jianghao, Xinyi Dai, Rong Shan, Bo Chen, Ruiming Tang, Yong Yu, and Weinan Zhang, "Large language models make sample-efficient recommender systems", Frontiers of Computer Science, Vol.19, No. 4, pp. 194328, 2025, DOI:10.48550/arXiv.2406.02368.
[25]Yang, S., Ma, W., Sun, P., Zhang, M., Ai, Q., Liu, Y. and Cai, M., “Common Sense Enhanced Knowledge-Based Recommendation With Large Language Model”, International Conference on Database Systems for Advanced Applications, Singapore: Springer Nature Singapore, pp. 381-390, 2024, DOI:10.1007/978-981-97-5569-1_25
[26]Wu, Jiahao, Wenqi Fan, Shengcai Liu, Qijiong Liu, Rui He, Qing Li, and Ke Tang, "Dataset condensation for recommendation", arXiv preprint arXiv: 2310.01038, 2023, DOI:10.48550/arXiv.2310.01038
[27]Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, Tat-Seng Chua, "KGAT: Knowledge graph attention network for recommendation", Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD '19), pp. 950–958, 2019. DOI: 10.1145/3292500.3330989
[28]Kangpeng Huang, Feng Feng, "Enhancing Recommendation Quality in Dense Data Environments: An Improved Collaborative Filtering Approach", International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), SPIE, Article. 12941, pp. 531-537, 2023, DOI: 10.1117/12.3011661.
[29]Liangcai Su, Fan Yan, Jieming Zhu, Xi Xiao, Haoyi Duan, Zhou Zhao, Zhenhua Dong, and Ruiming Tang, "Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation", Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 548-557, 2023. DOI:10.1145/3539618.3591643
[30]Simone Borg Bruun, Kacper Kenji Lesniak, Mirko Biasini, Vittorio Carmignani, Panagiotis Filianos, Christina Lioma, Maria Maistro, "Graph-Based Recommendation for Sparse and Heterogeneous User Interactions", Advances in Information Retrieval: 45th European Conference on Information Retrieval, pp. 182–199, 2023, DOI:10.1007/978-3-031-28244-7_12.
[31]Choi, S.-M., Lee, D., Jang, K., Park, C., & Lee, S., "Improving Data Sparsity in Recommender Systems Using Matrix Regeneration with Item Features", Mathematics, Vol.11, No.2, pp.292, 2023. DOI:10.3390/math11020292.
[32]Vasileios Perifanis, Pavlos S. Efraimidis, "Federated Neural Collaborative Filtering", Knowledge-Based Systems, ISSN 0950-7051, Vol.242, pp.108441, 2022, DOI: 10.1016/j.knosys.2022.108441.
[33]Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars Schmidt-Thieme, "BPR: Bayesian Personalized Ranking from Implicit Feedback", Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 452–461, 2009, DOI: https://dl.acm.org/doi/10.5555/1795114.1795167.