Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18 2018
DOI: 10.1145/3184558.3186904
|View full text |Cite
|
Sign up to set email alerts
|

Network Embedding Based Recommendation Method in Social Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
22
0

Year Published

2018
2018
2021
2021

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 47 publications
(22 citation statements)
references
References 4 publications
0
22
0
Order By: Relevance
“…[19,38] use regularization to constrain the neighbor users' embedding vectors to be similar and [8,17,36] adopt matrix factorization to incorporate the adjacent matrix into user embedding. Since the above methods can only capture linear information, some recent studies like [4,31] and [16,32,41] leverage deep neural networks and network embedding approaches, respectively, to learn a more complex representation for graph structures. However, comparing with dual GATs used in this paper, the common limitations of existing studies lie in: i) they assume neighbors' in uences to be equally important or statically constrained, ii) they ignore the social e ects from related items, iii) modeling of social e ects lacks interpretability.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…[19,38] use regularization to constrain the neighbor users' embedding vectors to be similar and [8,17,36] adopt matrix factorization to incorporate the adjacent matrix into user embedding. Since the above methods can only capture linear information, some recent studies like [4,31] and [16,32,41] leverage deep neural networks and network embedding approaches, respectively, to learn a more complex representation for graph structures. However, comparing with dual GATs used in this paper, the common limitations of existing studies lie in: i) they assume neighbors' in uences to be equally important or statically constrained, ii) they ignore the social e ects from related items, iii) modeling of social e ects lacks interpretability.…”
Section: Related Workmentioning
confidence: 99%
“…A user's preference for one item could be impacted by her friends, which motivates us to probe into such social e ect to improve recommendation quality. Previous studies for social recommendation a empt to model social e ects in various ways, such as by trust propagation [5,12,21], regularization loss [19,38], matrix factorization [8,17,36], network embedding [16,32,41], and deep neural network [4,31]. Figure 1: Illustration of the two-fold social e ects, i.e., homophily e ect and in uence e ect, in user social networks as well as among related items.…”
Section: Introductionmentioning
confidence: 99%
“…The low-dimensional representation learning of recommendation objects is a classic approach to the recommendation system [16,26,27], for example, one of the most efficient and best used recommend methods is matrix factorization in which users and items are represented in a low-dimensional latent factors space [26]. Network embedding aims at learning low-dimensional vectors for the vertices of a network [27][28][29], such that the proximities among the original network are preserved in the low-dimensional space [30].…”
Section: Network Embeddingmentioning
confidence: 99%
“…Based on user and item interaction graph, Dai et al [38] proposed a novel deep coevolutionary network model to capture complex mutual relationship between users and items, and their evolution. Wen et al [39] proposed a novel recommendation method in social networks based on user link network embedding mechanism.…”
Section: Similar Relationship Discoverymentioning
confidence: 99%