Multi-Surrogate-Objective Optimization for Neural Topic Models

Tue Le, Hoang Tran Vuong, Tung Nguyen, Linh Ngo Van, Dinh Viet Sang, Trung Le, Thien Huu Nguyen


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 naïve 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.
Anthology ID:
2025.findings-emnlp.9
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
135–151
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.9/
DOI:
Bibkey:
Cite (ACL):
Tue Le, Hoang Tran Vuong, Tung Nguyen, Linh Ngo Van, Dinh Viet Sang, Trung Le, and Thien Huu Nguyen. 2025. Multi-Surrogate-Objective Optimization for Neural Topic Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 135–151, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Multi-Surrogate-Objective Optimization for Neural Topic Models (Le et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.9.pdf
Checklist:
 2025.findings-emnlp.9.checklist.pdf