English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Multi-modal adversarial autoencoders for recommendations of citations and subject labels

Galke, L., Mai, F., & Vagliano, I. (2018). Multi-modal adversarial autoencoders for recommendations of citations and subject labels. In T. Mitrovic, J. Zhang, L. Chen, & D. Chin (Eds.), UMAP '18: Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization (pp. 197-205). New York: ACM. doi:10.1145/3209219.3209236.

Item is

 

show all

Basic

hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0009-F879-8 Version Permalink: https://hdl.handle.net/21.11116/0000-0009-F87A-7
Genre: Conference Paper

Files

hide Files
:
Galke_etal_2018_Multi modal adversarial.....pdf (Publisher version), 2MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0009-F87B-6
Name:
Galke_etal_2018_Multi modal adversarial.....pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

hide
 Creators:
Galke, Lukas1, Author           
Mai, Florian, Author
Vagliano, Iacopo, Author
Affiliations:
1Kiel University, Kiel, Germany, ou_persistent22              

Content

hide
Free keywords: -
 Abstract: We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.

Details

hide
Language(s): eng - English
 Dates: 2018
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1145/3209219.3209236
 Degree: -

Event

hide
Title: the 26th Conference on User Modeling, Adaptation and Personalization (UMAP 2018)
Place of Event: Singapore
Start-/End Date: 2018-07-08 - 2018-07-11

Legal Case

show

Project information

show

Source 1

hide
Title: UMAP '18: Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization
Source Genre: Proceedings
 Creator(s):
Mitrovic, T., Editor
Zhang, J., Editor
Chen, L., Editor
Chin, D., Editor
Affiliations:
-
Publ. Info: New York : ACM
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 197 - 205 Identifier: ISBN: 978-1-4503-5589-6