Probe-Enhanced Drift-Aware Model Updating for Compute-Efficient Sequential Recommendation

Zoe Huang

doi:10.54097/m7gp5307

Authors

Zoe Huang School of Computing and Information, University of Pittsburgh, PA, USA

DOI:

https://doi.org/10.54097/m7gp5307

Keywords:

Sequential recommendation, Concept drift, Continual learning, Adaptive training budget, Recency replay, Update admission

Abstract

Sequential recommenders must adapt to new interactions without repeatedly paying the cost of full-history retraining. Strict drift-triggered updating appears attractive, but can inadvertently suppress useful learning when marginal item frequencies are stable. We develop DAGR-P, a probe-enhanced update scheduler that performs a one-epoch new-data probe when a permutation drift screen is negative and allocates a longer, drift-dependent fine-tuning or recency-replay update otherwise. Candidate deployment follows a paired per-user validation rule. We implement the recency-replay update and the paired admission gate of the SPROUT compute-aware framework, and examine an additional user-matched drift detector. Five independent random seeds are evaluated on each of three explicitly synthetic, globally ordered interaction processes (22,680 interactions, 420 users, and 144 items per seed). Under stationary and abrupt processes, DAGR-P improves over a strict-gate policy from 0.1756 to 0.1857 and from 0.2540 to 0.2588 NDCG@10, respectively. Under gradual drift it obtains 0.2773, compared with 0.2689 for full retraining, with 32.93M versus 118.39M normalized training-score equivalents. A strong new-only updater remains more accurate in all three processes. The study identifies when low-budget probes counteract missed updates, and also shows why matched-user drift tests can be overly conservative. These results support a transparent compute–accuracy analysis, not a claim of field-scale effectiveness.

Downloads

Download data is not yet available.

References

[1] Kang, W.-C., & McAuley, J. (2018). Self-attentive sequential recommendation. In Proceedings of the IEEE International Conference on Data Mining (ICDM) (pp. 197-206). IEEE. https://doi.org/10.1109/ICDM.2018.00035

[2] Teng, D. (2025). TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows. World Journal of Engineering Research, 3(6), 55-66.

[3] Hidasi, B., Karatzoglou, A., Baltrunas, L., & Tikk, D. (2016). Session-based recommendations with recurrent neural networks. In Proceedings of the International Conference on Learning Representations (ICLR). arXiv, arXiv:1511.06939. https://doi.org/10.48550/arXiv.1511.06939

[4] Tang, J., & Wang, K. (2018). Personalized top-N sequential recommendation via convolutional sequence embedding. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining (WSDM) (pp. 565-573). ACM. https://doi.org/10.1145/3159652.3159656

[5] Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J. M., & He, X. (2019). A simple convolutional generative network for next item recommendation. In Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM) (pp. 582-590). ACM. https://doi.org/10.1145/3289600.3290975

[6] Li, J., Wang, Y., & McAuley, J. (2020). Time interval aware self-attention for sequential recommendation. In Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM) (pp. 322-330). ACM. https://doi.org/10.1145/3336191.3371786

[7] Zhou, K., Wang, H., Zhao, W. X., Zhu, Y., Wang, S., Zhang, F., Wang, Z., & Wen, J.-R. (2020). S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM) (pp. 1893-1902). ACM. https://doi.org/10.1145/3340531.3411954

[8] Xie, X., Sun, F., Liu, Z., Wu, S., Gao, J., Zhang, J., Ding, B., & Cui, B. (2022). Contrastive learning for sequential recommendation. In Proceedings of the IEEE 38th International Conference on Data Engineering (ICDE) (pp. 1259-1273). IEEE. https://doi.org/10.1109/ICDE53745.2022.00099

[9] Koren, Y. (2009). Collaborative filtering with temporal dynamics. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (pp. 447-456). ACM. https://doi.org/10.1145/1557019.1557072

[10] Meng, Z., McCreadie, R., Macdonald, C., & Ounis, I. (2020). Exploring data splitting strategies for the evaluation of recommendation models. In Proceedings of the 14th ACM Conference on Recommender Systems (RecSys) (pp. 681-686). ACM. https://doi.org/10.1145/3383313.3418479

[11] Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM Computing Surveys, 46(4), Article 44. https://doi.org/10.1145/2523813

[12] Bifet, A., & Gavaldà, R. (2007). Learning from time-changing data with adaptive windowing. In Proceedings of the SIAM International Conference on Data Mining (SDM) (pp. 443-448). SIAM. https://doi.org/10.1137/1.9781611972771.42

[13] Chang, S., Zhang, Y., Tang, J., Yin, D., Chang, Y., Hasegawa-Johnson, M. A., & Huang, T. S. (2017). Streaming recommender systems. In Proceedings of the 26th International Conference on World Wide Web (WWW) (pp. 381-389). ACM. https://doi.org/10.1145/3038912.3052627

[14] Zhang, Y., Yin, H., Chen, T., Zhang, C., Yu, B., Zhang, W., & Li, X. (2020). How to retrain recommender system? A sequential meta-learning method. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (pp. 1479-1488). ACM. https://doi.org/10.1145/3397271.3401167

[15] Mi, F., Lin, X., & Faltings, B. (2020). ADER: Adaptively distilled exemplar replay towards continual learning for session-based recommendation. In Proceedings of the 14th ACM Conference on Recommender Systems (RecSys) (pp. 408-413). ACM. https://doi.org/10.1145/3383313.3412218

[16] Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T. P., & Wayne, G. (2019). Experience replay for continual learning. Advances in Neural Information Processing Systems, 32, 350-360.

[17] Li, Z., & Hoiem, D. (2018). Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2935-2947. https://doi.org/10.1109/TPAMI.2017.2773081

[18] Chen, J., Han, X., Zhang, X., & Yang, Y. (2023). Exact concept-level explanations for early detection of financial misstatements. Eurasia Journal of Science and Technology, 5(2), 34-48.

[19] Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. d. L., Hendricks, L. A., Welbl, J., Clark, A., Hennigan, B., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., … & Sifre, L. (2022). Training compute-optimal large language models. Advances in Neural Information Processing Systems, 35, 30016-30030.

[20] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998-6008.

[21] Chen, T., Goodfellow, I. J., & Shlens, J. (2016). Net2Net: Accelerating learning via knowledge transfer. In Proceedings of the International Conference on Learning Representations (ICLR).

[22] Chen, C., Zhong, Y., Guo, Z., Zhang, X., & Li, J. (2022). bert2BERT: Towards reusable pretrained language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL) (pp. 2134-2148). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.acl-long.151

[23] Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR). arXiv, arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980

[24] Lin, J. (1991). Divergence measures based on the Shannon entropy. IEEE Transactions on Information Theory, 37(1), 145-151. https://doi.org/10.1109/18.61115

[25] Shen, A. (2023). Compute-efficient scaling of large sequential recommendation models under dynamic user behavior. World Journal of Information Technology, 1(1), 62-71. https://doi.org/10.61784/wjit4126

[26] Harper, F. M., & Konstan, J. A. (2015). The MovieLens datasets: History and context. ACM Transactions on Interactive Intelligent Systems, 5(4), Article 19. https://doi.org/10.1145/2827872

[27] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27-41.

[28] Mo, T., Zhang, Y., Li, H., Wang, J., & Chen, X. (2026). Self-evolving AI agents with dual memory for automated software testing and bug localization. IEEE Access, 14, 1-15. https://doi.org/10.1109/ACCESS.2026.3713401