@inproceedings{le-etal-2025-multi,
    title = "Multi-Surrogate-Objective Optimization for Neural Topic Models",
    author = "Le, Tue  and
      Vuong, Hoang Tran  and
      Nguyen, Tung  and
      Van, Linh Ngo  and
      Sang, Dinh Viet  and
      Le, Trung  and
      Nguyen, Thien Huu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.9/",
    doi = "10.18653/v1/2025.findings-emnlp.9",
    pages = "135--151",
    ISBN = "979-8-89176-335-7",
    abstract = {Neural topic modeling has substantially improved topic quality and document topic distribution compared to traditional probabilistic methods. These models often incorporate multiple loss functions. However, the disparate magnitudes of these losses can make hyperparameter tuning for these loss functions challenging, potentially creating obstacles for simultaneous optimization. While gradient-based Multi-objective Optimization (MOO) algorithms offer a potential solution, they are typically applied to shared parameters in multi-task learning, hindering their broader adoption, particularly in Neural Topic Models (NTMs). Furthermore, our experiments reveal that na{\"i}ve MOO applications on NTMs can yield suboptimal results, even underperforming compared to implementations without the MOO mechanism. This paper proposes a novel approach to integrate MOO algorithms, independent of hard-parameter sharing architectures, and effectively optimizes multiple NTMs loss functions. Comprehensive evaluations on widely used benchmark datasets demonstrate that our approach significantly enhances baseline topic model performance and outperforms direct MOO applications on NTMs.}
}