ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2021-02-18 16:15
A Note on Cross-domain Recommendation Based on Multilayer Graph Analysis with Visual Features
Taisei Hirakawa, Keisuke Maeda, Takahiro Ogawa (Hokkaido Univ.), Satoshi Asamizu (NIT, Kushiro College), Miki Haseyama (Hokkaido Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we improve the accuracy of cross-domain recommendation methods, which have been recently studied as a solution to the cold-start problem, by introducing visual features obtained from product images. The proposed method, first calculates the item features considering the visual features of product images. Next, we construct graphs using the calculated item features and the user embedding obtained from the users' purchase histories and estimate the embedding features based on a graph neural network. Specifically, the proposed method adopts visual features as the initialization of the network, and consideration of visual features becomes feasible. Based on the relationship between the embedding features of each domain, item recommendation can be realized. The effectiveness of the proposed method is confirmed through experiments using a large dataset based on purchase histories.
Keyword (in Japanese) (See Japanese page) 
(in English) Cross-domain Recommendation / multi-layer graph analysis / visual features / graph neural network / / / /  
Reference Info. ITE Tech. Rep., vol. 45, no. 4, ME2021-12, pp. 59-63, Feb. 2021.
Paper # ME2021-12 
Date of Issue 2021-02-11 (MMS, ME, AIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2021-02-18 - 2021-02-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2021-02-IE-ITS-MMS-ME-AIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A Note on Cross-domain Recommendation Based on Multilayer Graph Analysis with Visual Features 
Sub Title (in English)  
Keyword(1) Cross-domain Recommendation  
Keyword(2) multi-layer graph analysis  
Keyword(3) visual features  
Keyword(4) graph neural network  
1st Author's Name Taisei Hirakawa  
1st Author's Affiliation Hokkaido University (Hokkaido Univ.)
2nd Author's Name Keisuke Maeda  
2nd Author's Affiliation Hokkaido University (Hokkaido Univ.)
3rd Author's Name Takahiro Ogawa  
3rd Author's Affiliation Hokkaido University (Hokkaido Univ.)
4th Author's Name Satoshi Asamizu  
4th Author's Affiliation National Institute of Technology, Kushiro College (NIT, Kushiro College)
5th Author's Name Miki Haseyama  
5th Author's Affiliation Hokkaido University (Hokkaido Univ.)
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2021-02-18 16:15:00 
Presentation Time 25 minutes 
Registration for ME 
Paper # MMS2021-12, ME2021-12, AIT2021-12 
Volume (vol) vol.45 
Number (no) no.4 
Page pp.59-63 
Date of Issue 2021-02-11 (MMS, ME, AIT) 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan