paper-with-me

Papers

Challenging the Semi-Supervised VAE Framework for Text Classification

2021-09-27 · EMNLP (insights) 2021 11 · Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two sources of overcomplexity for which we provide simplifications. These simplifications to SSVAEs preserve their theoretical soundness while providing a number of practical advantages in the semi-supervised setup where the result of training is a text classifier. These simplifications are the removal of (i) the Kullback-Liebler divergence from its objective and (ii) the fully unobserved latent variable from its probabilistic model. These changes relieve users from choosing a prior for their latent variables, make the model smaller and faster, and allow for a better flow of information into the latent variables. We compare the simplified versions to standard SSVAEs on 4 text classification tasks. On top of the above-mentioned simplification, experiments show a speed-up of 26%, while keeping equivalent classification scores. The code to reproduce our experiments is public.

📄 PDF Abstract BibTeX arXiv:2109.12969

Code (1)

ghazi-f/challenging-ssvaes 공식 구현 pytorch

Tasks

Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder

2020-07-01 · ACL 2020 6 · Fan Zhou, Shengming Zhang, Yi Yang

Operational risk management is one of the biggest challenges nowadays faced by financial institutions. There are several major challenges of building a text classification system for automatic operational risk prediction…

ClassificationGeneral ClassificationManagementSemi-Supervised Text Classification+3

Universal Semi-Supervised Learning for Medical Image Classification

2023-04-08 · Lie Ju, Yicheng Wu, Wei Feng, Zhen Yu 외

Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning methods. However, traditional SSL is built …

ClassificationDomain Adaptationimage-classificationImage Classification+2

Understanding Social Support Needs in Questions: A Hybrid Approach Integrating Semi-Supervised Learning and LLM-based Data Augmentation

2025-03-21 · Junwei Kuang, Liang Yang, Shaoze Cui, Weiguo Fan

Patients are increasingly turning to online health Q&A communities for social support to improve their well-being. However, when this support received does not align with their specific needs, it may prove ineffective or…

Data Augmentation

Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy

2023-09-14 · Jiaren Xiao, Quanyu Dai, Xiao Shen, Xiaochen Xie 외

Label scarcity in a graph is frequently encountered in real-world applications due to the high cost of data labeling. To this end, semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a la…

Contrastive LearningDomain AdaptationNode ClassificationSemi-supervised Domain Adaptation

Colour augmentation for improved semi-supervised semantic segmentation

2021-10-09 · Geoff French, Michal Mackiewicz

Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, a numbe…

ClassificationSegmentationSelf-Supervised LearningSemantic Segmentation+1