Year: 2022
Type: preprint
Abstract: Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as probabilistic models are still largely unknown. In this paper, we focus on the context of topic modeling and highlight a key advantage of self-supervised learning - when applied to data generated by topic models, self-supervised learning can be oblivious to the specific model, and hence is less susceptible to model misspecification. In particular, we prove that commonly used self-supervised objectives based on reconstruction or contrastive samples can both recover useful posterior information for general topic models. Empirically, we show that the same objectives can perform on par with posterior inference using the correct model, while outperforming posterior inference using misspecified models.
Source: arXiv (Cornell University)
Authors: Luo, Zeping, Wu, Shiyou, Weng, Cindy, Zhou, Mo, Ge, Rong
Institution: Duke University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
Awards: Collaborative Research: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable Networks, HDR TRIPODS: Innovations in Data Science: Integrating Stochastic Modeling, Data Representations, and Algorithms, CAREER: Optimization Landscape for Non-convex Functions - Towards Provable Algorithms for Neural Networks, G6671297155
OpenAlex ID: W4221156854