MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation
- Authors
- Kim, Taeri; Lee, Yeon-Chang; Shin, Kijung; Kim, Sang-Wook
- Issue Date
- Oct-2022
- Publisher
- ACM CIKM 2022
- Keywords
- multimedia recommendation; modality-specific properties
- Citation
- ACM Conference on Information and Knowledge Management, pp.993 - 1002
- Indexed
- OTHER
- Journal Title
- ACM Conference on Information and Knowledge Management
- Start Page
- 993
- End Page
- 1002
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188584
- DOI
- 10.1145/3511808.3557387
- Abstract
- We address the multimedia recommendation problem, which utilizes items’ multimodal features, such as visual and textual modalities, in addition to interaction information. While a number of existing multimedia recommender systems have been developed for this problem, we point out that none of these methods individually capture the influence of each modality at the interaction level. More importantly, we experimentally observe that the learning procedures of existing works fail to preserve the intrinsic modality-specific properties of items. To address above limitations, we propose an accurate multimedia recommendation framework, named MARIO, based on modality-aware attention and modality-preserving decoders. MARIO predicts users’ preferences by considering the individual influence of each modality on each interaction while obtaining item embeddings that preserve the intrinsic modality-specific properties. The experiments on four real-life datasets demonstrate that MARIO consistently and significantly outperforms seven competitors in terms of the recommendation accuracy: MARIO yields up to 14.61% higher accuracy, compared to the best competitor
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188584)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.