Coupled nominal similarity in unsupervised learning

Wang, Can; Cao, Longbing; Wang, Mingchun; Li, Jinjiu; Wei, Wei; Ou, Yuming

doi:10.1145/2063576.2063715

Cited by 75 publications

(82 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Content-based methods often assume item's attributes are independent which is not always held in reality. Actually, several research outcomes such as [25] [26] [27] have been proposed to handle the challenging issues. Yu.…”

Section: Recommendation Methodsmentioning

confidence: 99%

Two-level matrix factorization for recommender systems

Cao

2015

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Many existing recommendation methods such as Matrix Factorization (MF) mainly rely on user-item rating matrix, which sometimes is not informative enough, often suffering from the cold start problem. To solve this challenge, complementary textual relations between items are incorporated into Recommender Systems (RS) in this paper. Specifically, we first apply a novel Weighted Textual Matrix Factorization (WTMF) approach to compute the semantic similarities between items, then integrate the inferred item semantic relations into MF and propose a Two-level Matrix Factorization (TLMF) model for RS. Experimental results on two open data sets not only demonstrate the superiority of TLMF model over benchmark methods, but also show the effectiveness of TLMF for solving the cold start problem.

show abstract

Section: Recommendation Methodsmentioning

confidence: 99%

Two-level matrix factorization for recommender systems

Cao

2015

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

show abstract

“…L. Cao proposed the non-IIDness learning which thinks attribute values and attributes are usually coupled [1]. Wang et al put forward the coup nominal similarity in unsupervised learning [4], and analyzed coupled attribute on numerical data [5]. Cheng et al analyzed the coupled term-term relation for document clustering [6].…”

Section: Related Workmentioning

confidence: 99%

Reliability Analysis Based on Coupled Relationship

Pan¹,

Wang²

2015

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Abstract-In the usual reliability analysis, researchers often acquire the reliability information about a product by reliability tests and usually regard the product as a whole object to study. Also, the relationships between the attributes of the product are usually ignored. Base on the non-IIDness learning, the attributes of objects are more or less interacted and coupled. Thus, this paper analyzes the coupled relationships between each pair of product attributes and the coupled relationships between each product attribute and reliability lifetime of the product. Specifically, the attributes we analyzed are continuous. The level of interplay between each pair of attributes and between each attribute and product lifetime can be observed by coupled correlation matrices.

show abstract

“…al. [2] proposed a similarity definition composed of two types of coupled similarities-intra-coupled and intercoupled similarities. They define Intra-coupled Attribute Value Similarity (IaAVS) for the former, and Inter-coupled Relative Similarity based on Interaction Set (IRSI) for the latter.…”

Section: Related Workmentioning

confidence: 99%

Similarity Search of Human Behavior Processes Using Extended Linked Data Semantic Distance

Zuo

Huang

Kawagoe

2014

2014 25th International Workshop on Database and Expert Systems Applications

View full text Add to dashboard Cite

Large amounts of sensed data on human behaviors have been collected, and technologies for modeling human behavior have recently been developed. However, the data collected are difficult to analyze and reuse. Thus, in order to mine various aspects of human behaviors, development of an appropriate semantic similarity measure of human behaviors is essential. In this paper, we propose a novel similarity search method that, given a particular behavior, searches for a similar behavior. The proposed method extends the semantic distance calculation method Linked Data Semantic Distance (LDSD) and applies it to human behavior distance calculations. Semantic distance measures for similarity search of human behaviors has, to the best of our knowledge, never been studied before, whereas many studies on similarity measures for linked data, graphs, and processes have been proposed. Our extended LDSD extends distance calculation from three standpoints: temporal, granularity, and content. We present the details of these extensions along with examples, and compare our extended LDSD to the original LDSD and another existing method.

show abstract

Coupled nominal similarity in unsupervised learning

Cited by 75 publications

References 9 publications

Two-level matrix factorization for recommender systems

Two-level matrix factorization for recommender systems

Reliability Analysis Based on Coupled Relationship

Similarity Search of Human Behavior Processes Using Extended Linked Data Semantic Distance

Contact Info

Product

Resources

About