Hypergraph Neural Reservoir with Lyapunov‑Adaptive Attention for Robust Context‑Aware Tourism Recommendation

Year 2025, Volume: 7 Issue: 3, 207 - 220, 30.11.2025

Mohamed Badouch , Fawaz Khaled Alarfaj Hikmat Ullah Khan Mehdi Boutaounte

https://doi.org/10.51537/chaos.1768281

https://izlik.org/JA66ZZ77HR

Abstract

Tourism experiences are shaped by rapidly changing conditions such as weather, local events, and visitor flows, yet most recommendation systems assume stable patterns, limiting their ability to adapt in real time. This study introduces a robust context‑aware tourism recommendation framework that integrates a Hypergraph Neural Network, an Echo State Network reservoir tuned to operate at the edge of chaos, and a transformer with Lyapunov‑adaptive attention. The hypergraph encoder models complex, multi‑entity relationships among users, destinations, and contextual factors; the reservoir captures evolving context signals with high sensitivity; and the Lyapunov‑adaptive attention mechanism adjusts focus based on online estimates of the largest Lyapunov exponent, enabling the system to detect and respond to sudden regime shifts. The framework is trained and evaluated on the publicly available Travel Recommendation Dataset from IEEE DataPort, enriched with historical weather records and local event schedules. Comparative experiments against strong context‑aware, graph‑based, and sequence‑based baselines show consistent improvements in accuracy, measured by hit rate and normalized discounted cumulative gain, and in diversity, measured by intra‑list diversity and serendipity, particularly under simulated disruptions such as abrupt weather changes. These results demonstrate that combining graph learning, recurrent dynamics, and chaos‑aware attention can substantially increase the resilience of personalization in volatile environments, paving the way for recommendation systems that remain both relevant and exploratory despite unpredictable shifts in user context.

Keywords

Chaos‑aware recommendation , Hypergraph neural network , Lyapunov exponent , Reservoir computing , Tourism personalization

Ethical Statement

The Travel Recommendation Dataset used in this study is openly available at \url{https://ieee-dataport.org/documents/travel-recommendation-dataset}, DOI : https://dx.doi.org/10.21227/7c29-tt74 The authors declare that there is no conflict of interest regarding the publication of this paper.

Supporting Institution

King Faisal University

Thanks

This work was supported by the Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia [Grant No. KFU253811].

References

• Adomavicius, G. and A. Tuzhilin, 2011 Context-aware recommender systems. In Recommender Systems Handbook, edited by F. Ricci, L. Rokach, and B. Shapira, pp. 217–253, Springer, Boston, MA.
• Bonner, S. and F. Vasile, 2022 Causal inference in recommender systems: A survey and future research directions. In Proceedings of the 16th ACM Conference on Recommender Systems, pp. 234–244, ACM.
• Ekstrand, M. D., A. Das, R. Burke, F. Diaz, L. Li, et al., 2022 Fairness in information access systems: Metrics, methods, and research directions. Foundations and Trends in Information Retrieval 16: 1–185.
• Fan, W., C. Ma, X. Li, J. Chen, J. Tang, et al., 2023 A survey on self-supervised learning for recommendation. IEEE Transactions on Knowledge and Data Engineering 35: 5716–5735.
• Feng, Y., H. You, Z. Zhang, R. Ji, and Y. Gao, 2019 Hypergraph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp. 3558–3565.
• Gauthier, D. J., E. Bollt, A. Griffith, andW. S. Barbosa, 2021 Next generation reservoir computing. Nature Communications 12: 5564.
• He, X., K. Deng, X. Wang, Y. Li, Y. Zhang, et al., 2020a 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, pp. 639–648.
• He, X., K. Deng, X. Wang, Y. Li, Y. Zhang, et al., 2020b 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, pp. 639–648, ACM.
• He, X., K. Deng, X.Wang, Y. Li, Y. Zhang, et al., 2020c 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 (SIGIR), pp. 639–648.
• Jaeger, H., 2001 The “echo state” approach to analysing and training recurrent neural networks. Technical Report GMD Report 148, German National Research Center for Information Technology.
• Jannach, D., M. Zanker, A. Felfernig, and G. Friedrich, 2010 Recommender Systems: An Introduction. Cambridge University Press, Cambridge, UK.
• Järvelin, K. and J. Kekäläinen, 2002 Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems 20: 422–446.
• Koren, Y. and R. Bell, 2015 Advances in collaborative filtering. Recommender Systems Handbook pp. 77–118.
• Lee, J., D. Kim, and H. Kim, 2021 Dual-regularized matrix factorization for robust recommendation under distribution shifts. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2994–3002, ACM.
• Li, P., X. Zhao, and J. McAuley, 2021 Addressing distribution shift in recommender systems: A survey and benchmark. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 849–857, ACM.
• Liu, F., R. Xie, L. Zhang, F. Zhang, J. Xu, et al., 2023 Towards robust recommendation under continual distribution shifts. ACM Transactions on Information Systems 41: 1–28.
• Maass,W., T. Natschläger, and H. Markram, 2002 Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14: 2531– 2560.
• Qiu, Z.-H., Q. Hu, Y. Zhong, W.-W. Tu, L. Zhang, et al., 2025 Optimal large-scale stochastic optimization of ndcg surrogates for deep learning. Machine Learning 114: 1–38.
• Quadrana, M., P. Cremonesi, and D. Jannach, 2018 Sequence-aware recommender systems. ACM Computing Surveys 51: 66:1–66:36.
• Rosenstein, M. T., J. J. Collins, and C. J. De Luca, 1993 A practical method for calculating largest lyapunov exponents from small data sets. Physica D: Nonlinear Phenomena 65: 117–134.
• Rossi, E., H. Kenlay, M. Gorinova, M. Bronstein, B. P. Chamberlain, et al., 2020 Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637 .
• Rössler, O. E., 1976 An equation for continuous chaos. Physics Letters A 57: 397–398.
• Schlichtkrull, M., F. Esposito, J. G. Simonsen, T. Alstrøm, A. Kirkedal, et al., 2021 Modeling out-of-session user preferences for session-based recommendation. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 488–497, ACM.
• Shani, G. and A. Gunawardana, 2011 Evaluating recommendation systems. In Recommender Systems Handbook, edited by F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, pp. 257–297, Springer, Boston, MA.
• Sprott, J. C., 2000 A new class of chaotic circuit. Physics Letters A 266: 19–23.
• Vaswani, A., N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, et al., 2017 Attention is all you need. In Advances in Neural Information Processing Systems, volume 30, pp. 5998–6008.
• Wang, X., X. He, M. Wang, F. Yu, and T.-S. Chua, 2020 Disentangled graph collaborative filtering. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1001–1010, ACM.
• Wei, T., X. Liu, B. Xiang, andW. Jiang, 2021 Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 824–833, ACM.
• Wu, C., F. Sun, Q. Hu, and Y. Chen, 2022a A critical review of offline evaluation metrics for recommender systems. Information Processing & Management 59: 103069.
• Wu, J., J. Xiao, C. Gao, and X. He, 2021 Self-supervised graph learning for recommendation. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2896–2905, ACM.
• Wu, L., L. Chen, P. Li, X. He, Z. Gao, et al., 2022b Graph neural networks in recommender systems: A survey. ACM Computing Surveys 55: 1–37.
• Yu, J., H. Yin, X. Song, J.Wang, and X. Zhang, 2021 Self-supervised hypergraph contrastive collaborative filtering. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 726–735, ACM.
• Zhang, S., J. Zhang, F. Yuan, and J. Tang, 2020 Dual channel hypergraph collaborative filtering. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management, pp. 1525–1534, ACM.
• Zhang, Y. and X. Chen, 2020 Explainable recommendation: A survey and new perspectives. Foundations and Trends in Information Retrieval 14: 1–101.
• Zhou, K., H. Wang, W. X. Zhao, and J.-R. Wen, 2021 Knowledge graphs in recommender systems: A survey. IEEE Transactions on Knowledge and Data Engineering 33: 2495–2512.