Supervised topic models for multi-label classification

Li, Ximing; Ouyang, Jian; Zhou, Xiaotang

doi:10.1016/j.neucom.2014.07.053

Cited by 47 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User topic model construction 3.1. The LDA topic model The LDA topic model is a kind of hierarchical Bayesian model [15]. It is composed of three levels, such as documents, topics and words.…”

Section: Related Workmentioning

confidence: 99%

An Indirected Recommendation Model for Chinese Microblog

Duan

Dong

Mei

2016

Cybernetics and Information Technologies

View full text Add to dashboard Cite

Microblog is a browser-based platform for web user's information sharing and communication. With the rapidly increasing of microblog population, its recommendation function becomes necessary. This paper proposes the recommendation by the Latent Dirichlet Allocation topic model, which combines the user interests into the model to meet their needs. We also conduct a comparative analysis between indirect and direct recommendation algorithms. The experimental resultsshow that the indirect recommendation is more effective for the micro-blog recommendation.

show abstract

Section: Related Workmentioning

confidence: 99%

An Indirected Recommendation Model for Chinese Microblog

Duan

Dong

Mei

2016

Cybernetics and Information Technologies

View full text Add to dashboard Cite

show abstract

“…Or a related news article can be simultaneously annotated as "Sports", "Politics" and "Brazil". Multi-label learning aims to accurately allocate a group of labels to unseen examples with the knowledge harvested from the training data, and it has been widely-used in many applications, such as document categorization Yang et al (2009) ;Li et al (2015), image/videos classification/annotation ; Wang et al (2016); Bappy et al (2016), gene function classification Cesa-Bianchi et al (2012) and image retrieval Ranjan et al (2015).…”

Section: Introductionmentioning

confidence: 99%

Privileged Multi-label Learning

You

Wang

et al. 2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

This paper presents privileged multi-label learning (PrML) to explore and exploit the relationship between labels in multi-label learning problems. We suggest that for each individual label, it cannot only be implicitly connected with other labels via the low-rank constraint over label predictors, but also its performance on examples can receive the explicit comments from other labels together acting as an Oracle teacher. We generate privileged label feature for each example and its individual label, and then integrate it into the framework of low-rank based multi-label learning. The proposed algorithm can therefore comprehensively explore and exploit label relationships by inheriting all the merits of privileged information and low-rank constraints. We show that PrML can be efficiently solved by dual coordinate descent algorithm using iterative optimization strategy with cheap updates. Experiments on benchmark datasets show that through privileged label features, the performance can be significantly improved and PrML is superior to several competing methods in most cases.

show abstract

“…Multi-label learning [8,13,14,20,25,33,34,35,37,38] is a very challenging problem in machine learning, data mining, and information retrieval. It studies the problem where each object is associated with multiple concepts simultaneously.…”

Section: Introductionmentioning

confidence: 99%