Topic Modeling as Multi-Objective Contrastive Optimization

TL;DR

This paper introduces a multi-objective contrastive optimization framework for neural topic models that balances reconstruction and semantic generalization, leading to improved topic quality and diversity.

Contribution

It proposes a novel contrastive learning method for sets of topic vectors and formulates contrastive topic modeling as a multi-objective optimization problem to enhance model performance.

Findings

Improved topic coherence and diversity.

Better downstream task performance.

Consistent outperformance over baseline models.

Abstract

Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning objective that contrasts pairs of input documents. However, document-level contrastive learning might capture low-level mutual information, such as word ratio, which disturbs topic modeling. Moreover, there is a potential conflict between the ELBO loss that memorizes input details for better reconstruction quality, and the contrastive loss which attempts to learn topic representations that generalize among input documents. To address these issues, we first introduce a novel contrastive learning method oriented towards sets of topic vectors to capture useful semantics that are shared among a set of input documents. Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective. Extensive experiments demonstrate that our framework consistently produces higher-performing neural topic models in terms of topic coherence, topic diversity, and downstream performance.