paper-with-me

홈 › Papers

TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning

2020-07-14 · ECCV 2020 8 · Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang

Fusing data from multiple modalities provides more information to train machine learning systems. However, it is prohibitively expensive and time-consuming to label each modality with a large amount of data, which leads to a crucial problem of semi-supervised multi-modal learning. Existing methods suffer from either ineffective fusion across modalities or lack of theoretical guarantees under proper assumptions. In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i.e., the ground truth posteriors of all modalities. Specifically, by maximizing TC-induced loss (namely TC gain) over classifiers of all modalities, these classifiers can cooperatively discover the equivalent class of ground-truth classifiers; and identify the unique ones by leveraging limited percentage of labeled data. We apply our method to various tasks and achieve state-of-the-art results, including news classification, emotion recognition and disease prediction.

📄 PDF Abstract BibTeX arXiv:2007.06793

Code (0)

등록된 구현이 없습니다.

Tasks

Disease PredictionEmotion RecognitionNews Classification

Similar Papers 제목 키워드 기반

Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation

2021-12-17 · Sophie Steger, Bernhard C. Geiger, Marek Smieja

We connect the problem of semi-supervised clustering to constrained Markov aggregation, i.e., the task of partitioning the state space of a Markov chain. We achieve this connection by considering every data point in the …

Clustering

An Information-Theoretic Framework for Identifying Age-Related Genes Using Human Dermal Fibroblast Transcriptome Data

2021-11-04 · Salman Mohamadi, Donald Adjeroh

Investigation of age-related genes is of great importance for multiple purposes, for instance, improving our understanding of the mechanism of ageing, increasing life expectancy, age prediction, and other healthcare appl…

An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift

2022-02-24 · Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni 외

A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution. However, this assumption is not satisfied in many applications. In many scenarios, the d…

Rethinking Weak Supervision in Helping Contrastive Learning

2023-06-07 · Jingyi Cui, Weiran Huang, Yifei Wang, Yisen Wang

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noi…

Contrastive LearningDenoisingWeakly-supervised Learning

Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomalies

2025-06-16 · Matthew Lau, Tian-Yi Zhou, Xiangchi Yuan, Jizhou Chen 외

Anomaly detection (AD) is a critical task across domains such as cybersecurity and healthcare. In the unsupervised setting, an effective and theoretically-grounded principle is to train classifiers to distinguish normal …

Anomaly DetectionSemi-supervised Anomaly DetectionSupervised Anomaly Detection