Digital Library[ Search Result ]
Linear Sequential Recommendation Models using Textual Side Information
Dongcheol Lee, Minjin Choi, Jongwuk Lee
http://doi.org/10.5626/JOK.2025.52.6.529
Recently, research on leveraging auxiliary information in sequential recommendation systems is being actively conducted. Most approaches have focused on combining language models with deep neural networks. However, they often lead to high computational costs and latency issues. While linear recommendation models can serve as an efficient alternative, research on how to effectively incorporate auxiliary information is lacking. This study proposed a framework that could effectively utilize auxiliary information within a linear model. Since textual data cannot be directly used in linear model training, we transformed item texts into dense vectors using a pre-trained text encoder. Although these vectors contained rich information, they failed to capture relationships between items. To address this, we applied graph convolution to obtain enhanced item representations. These representations were then used alongside the user-item interaction matrix for linear model training. Extensive experiments showed that the proposed method improved the overall performance, particularly in recommending less popular items.
Graph Convolutional Networks with Elaborate Neighborhood Selection
Yeonsung Jung, Joyce Jiyoung Whang
http://doi.org/10.5626/JOK.2019.46.11.1193
Graph Convolutional Networks (GCNs) utilize the convolutional structure to obtain an effective insight on representation by aggregating the information from neighborhoods. In order to demonstrate high performance, it is necessary to select neighborhoods that can propagate important information to target nodes, and acquire appropriate filter values during training. Recent GCNs algorithms adopt simple neighborhood selection methods, such as taking all 1-hop nodes. In the present case, unnecessary information was propagated to the target node, resulting in degradation of the performance of the model. In this paper, we propose a GCN algorithm that utilizes valid neighborhoods by calculating the similarity between the target node and neighborhoods.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr