Vol. 1 No. 4 (2026)

Articles

Self-Supervised Cluster Discovery Under Imbalanced and Drifting Concept Distributions

Published 2026-10-01

  • Leah Hughes
    • ,
  • Charlotte E. Johnson
    • ,
  • Mia Martinez

Leah Hughes
Department of Advanced Computing, Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA

Charlotte E. Johnson
Department of Advanced Computing, Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA

Mia Martinez
Department of Computer Science, School of Engineering and Applied Science, Yale University, New Haven, Connecticut, USA

Machine Learning and Applied Artificial Intelligence, Volume 1, Issue 4, 2026 cover

Abstract

The exponential growth of unlabeled streaming data in contemporary digital ecosystems has necessitated the development of robust unsupervised learning paradigms. Traditional clustering algorithms assume static data distributions and balanced class representations, assumptions that are systematically violated in real-world scenarios characterized by concept drift and severe class imbalance. This paper presents a comprehensive investigation into self-supervised cluster discovery mechanisms operating under these challenging dynamic conditions. We propose a novel conceptual framework that integrates contrastive representation learning with an adaptive memory bank and an imbalance-aware cluster assignment mechanism. By leveraging temporal coherence and dynamically adjusting margin boundaries based on estimated cluster densities, the proposed approach identifies emerging concepts while preserving knowledge of minority clusters that are highly susceptible to being overshadowed by majority classes during distribution shifts. The research meticulously dissects the theoretical underpinnings of dynamic representation learning, evaluating the interplay between catastrophic forgetting and rapid adaptation. Extensive theoretical analysis and simulated experimental validations demonstrate the efficacy of integrating density-based pseudo-labeling with drift-resilient self-supervision. The findings underscore the critical importance of decoupling representation learning from cluster assignment in non-stationary environments, offering a scalable solution for continuous data stream mining.

Keywords

Self-Supervised Learning, Concept Drift, Imbalanced Data, Data Stream Mining, Cluster Discovery.

PDF

Author Biography

Leah Hughes

Editorial correspondence on behalf of the authors

References

  1. Hu, H., Yang, Y., Zhao, Q., & Zhang, C. (2022, June). On the role of discount factor in offline reinforcement learning. In International conference on machine learning (pp. 9072-9098). PMLR.
  2. Fan, J., Rosu, P., Wang, A. T., Carin, L., & Cheng, X. (2026). In context semi-supervised learning. In Proceedings of the International Conference on Learning Representations. https://openreview.net/forum?id=lqrpmqrTnH
  3. Sang, Y. (2026, March). Adaptive Quantization Strategies for Robust ML Inference Under Distribution Shift. In Proceedings of the 2026 5th International Conference on Cyber Security, Artificial Intelligence and Digital Economy (pp. 362-368).
  4. Kelley, D. R., Snoek, J., & Rinn, J. L. (2016). Basset: Learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Research, 26(7), 990–999.
  5. Meng, X., & Lin, J. (2026). AWCRL: Adaptive Weakly Supervised Cross-Modal Reliability Learning for resource-constrained proxy-state recognition. Pattern Recognition, 114998.
  6. Zou, Y., & Chou, C. A. (2022). A combinatorial optimization approach for multi-label associative classification. Knowledge-Based Systems, 240, 108088.
  7. Zhang, F., Gao, S., & Song, J. (2024, August). Offline Contextual Learning with Correlated Bayesian Beliefs. In 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) (pp. 2496-2500). IEEE.
  8. Yu, Z., Dai, L., Xu, S., Gao, S., & Ho, C. P. (2023). Fast bellman updates for wasserstein distributionally robust mdps. Advances in Neural Information Processing Systems, 36, 30554-30578.
  9. Zhou, J., & Troyanskaya, O. G. (2015). Predicting effects of noncoding variants with deep learning-based sequence model. Nature Methods, 12(10), 931–934.
  10. Li, Q., Luo, T., Jiang, M., Liao, J., & Jiang, Z. (2024, October). Deep incomplete multi-view network semi-supervised multi-label learning with unbiased loss. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 9048-9056).
  11. Obite, C. P., Chang, Z., Wu, K., & Lan, S. (2025, May). Bayesian regularization of latent representation. In International Conference on Learning Representations (Vol. 2025, pp. 12805-12823).
  12. Chai, L.; Zhang, J.; Li, H.; Cui, C.; Jiang, J.; Zheng, B.; Wu, L.; Jiang, L. Investigation of thermomorphogenesis-related genes for a multi-silique trait in Brassica napus by comparative transcriptome analysis. Front. Genet. 2021, 12, 678804.
  13. Zhang, Z., Yin, Z., Wen, J., Sun, L., Su, S., & Yu, P. S. (2021). DeepBlue: Bi-layered LSTM for tweet popularity estimation. IEEE Transactions on Knowledge and Data Engineering, 34(10), 4737-4752.
  14. Zhang, J., & Tang, H. (2025). Resolving Task Objective Conflicts in Unified Model via Task-Aware Mixture-of-Experts. arXiv preprint arXiv:2506.03591.
  15. Li, Q., Luo, T., & Liao, J. (2025). Theory-inspired deep multi-view multi-label learning with incomplete views and noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20706-20715).
  16. Zhang, J., Luo, H., Yang, H., Xu, X., Wu, Q., Shi, Y., ... & Wang, J. (2023). Neuraldome: A neural modeling pipeline on multi-view human-object interactions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8834-8845).
  17. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. In Advances in Neural Information Processing Systems.
  18. Dai, Y., Ji, Y., Zhang, X., Wang, Y., Chu, X., & Lu, Z. (2026). Harder is better: Boosting mathematical reasoning via difficulty-aware grpo and multi-aspect question reformulation. arXiv preprint arXiv:2601.20614.
  19. Ouyang, Z., & Mayne, P. W. (2017, September). Spherical cavity expansion nexus between CPTu and DMT in soft-firm clays. In 19th International Conference on Soil Mechanics and Geotechnical Engineering (pp. 631-634). Korea Geotechnical Society, Seoul, Korea.
  20. Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
  21. Li, Q., Luo, T., Jiang, M., Jiang, Z., Hou, C., & Li, F. (2025, April). Semi-supervised multi-view multi-label learning with view-specific transformer and enhanced pseudo-label. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 17, pp. 18430-18438).
  22. M. Emani et al., ‘‘A comprehensive evaluation of novel AI accelerators for deep learning workloads,’’ in Proc. IEEE/ACM Int. Workshop Perform. Modeling, Benchmarking Simulation High Perform. Comput. Syst. (PMBS), Nov. 2022, pp. 13–25.
  23. Cong, P., Xu, Y., Ren, Y., Zhang, J., Xu, L., Wang, J., ... & Ma, Y. (2023, June). Weakly supervised 3d multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 1, pp. 461-469).
  24. Luo, T., Li, Q., Jiang, M., & Hou, C. (2025). Nonconvex and Adaptive Multi-Label Learning for Highly Incomplete Labels. Knowledge-Based Systems, 114784.
  25. Liu, Y., Cai, Q., Wang, C., Yang, J., Fan, H., Dong, J., & Chen, S. (2024). Geometry-enhanced attentive multi-view stereo for challenging matching scenarios. IEEE Transactions on Circuits and Systems for Video Technology, 34(8), 7401-7416.
  26. Gao, S., Li, C., & Du, J. (2019, December). Rate analysis for offline simulation online application. In 2019 Winter Simulation Conference (WSC) (pp. 3468-3479). IEEE.
  27. Zhao, J., Zhang, C., Qin, M., & Yang, P. (2025). QuantFactor REINFORCE: mining steady formulaic alpha factors with variance-bounded REINFORCE. IEEE Transactions on Signal Processing, 73, 2448-2463.
  28. Lyu, S., Mao, S., & Ma, Y. (2025). Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising. arXiv preprint arXiv:2511.03272.
  29. Sha, L., Wang, Y., Meng, P., Deng, Y., Chen, T., Zhang, X., ... & Xu, Q. (2025). Pharmacological inhibition of PSPH reduces serine levels and epileptic seizures. Nature Chemical Biology, 21(11), 1742-1753.
  30. Huang, Y., Roth, K., Bouniot, Q., Xu, W., & Akata, Z. (2026). Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers. arXiv preprint arXiv:2601.20796.