.png){kind=icon}
.png){kind=icon}
Return
A multi-objective surrogate framework for training neural topic models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.133432.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural topic models have achieved notable advances in generating coherent topics and learning document-topic distributions, yet they commonly rely on multiple loss components that vary widely in scale. These imbalances make joint optimization difficult and often require extensive hyperparameter tuning. Multi-objective optimization (MOO) methods offer a promising direction, but their use has largely been limited to settings with shared-parameter architectures, restricting their applicability to many topic modeling frameworks. Moreover, applying standard MOO techniques directly to neural topic models can lead to degraded performance due to incompatibilities between the objectives. This work introduces a new strategy for integrating MOO into neural topic modeling without relying on hard parameter sharing. The proposed method enables effective coordination of multiple loss functions and facilitates stable optimization. Experiments on widely used benchmark corpora show that the approach yields substantial improvements over baseline neural topic models and consistently surpasses naïve MOO-based variants. Our code is publicly available at github 2
Keywords:
neural topic models
multi-objective optimization
surrogate framework
document-topic distributions
hyperparameter tuning
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W