Exploring the Side-Information Fusion for Sequential Recommendation
Side information fusion for sequential recommendation aims to mitigate the data sparsity problems by leveraging the additional knowledge besides item ID. While most state-of-the-art methods devised elaborate fusion methods to incorporate side-information, they overlooked that there are distinct char...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824815/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592952843567104 |
|---|---|
| author | Seunghwan Choi Donghoon Lee Hyeoungguk Kang Hyunsouk Cho |
| author_facet | Seunghwan Choi Donghoon Lee Hyeoungguk Kang Hyunsouk Cho |
| author_sort | Seunghwan Choi |
| collection | DOAJ |
| description | Side information fusion for sequential recommendation aims to mitigate the data sparsity problems by leveraging the additional knowledge besides item ID. While most state-of-the-art methods devised elaborate fusion methods to incorporate side-information, they overlooked that there are distinct characteristics of the side-information, which can be grouped into two types: item attribute (e.g., category and brand) and user behavior (e.g., position and rating). In this paper, we argue that attribute information and behavior information are fundamentally different in relation to the item. The former is inherent to the item, whereas the latter is not. Based on this intuition, we systematically analyzed the previous fusion approach and introduced a comprehensive framework for two types of side information. Finally, we devise self-supervised objectives fitting for each type of side-information in a multi-task training scheme. To validate the effectiveness of our proposed method, we conduct experiments across various domains. |
| format | Article |
| id | doaj-art-baede1d377754ed9951147b856d425e5 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-baede1d377754ed9951147b856d425e52025-01-21T00:01:55ZengIEEEIEEE Access2169-35362025-01-01138839885010.1109/ACCESS.2025.352581210824815Exploring the Side-Information Fusion for Sequential RecommendationSeunghwan Choi0https://orcid.org/0009-0007-5742-1243Donghoon Lee1https://orcid.org/0000-0001-7435-9567Hyeoungguk Kang2Hyunsouk Cho3https://orcid.org/0000-0002-9134-1921Department of Artificial Intelligence, Ajou University, Suwon-si, Republic of KoreaDepartment of Artificial Intelligence, Ajou University, Suwon-si, Republic of KoreaDepartment of Artificial Intelligence, Ajou University, Suwon-si, Republic of KoreaDepartment of Artificial Intelligence, Ajou University, Suwon-si, Republic of KoreaSide information fusion for sequential recommendation aims to mitigate the data sparsity problems by leveraging the additional knowledge besides item ID. While most state-of-the-art methods devised elaborate fusion methods to incorporate side-information, they overlooked that there are distinct characteristics of the side-information, which can be grouped into two types: item attribute (e.g., category and brand) and user behavior (e.g., position and rating). In this paper, we argue that attribute information and behavior information are fundamentally different in relation to the item. The former is inherent to the item, whereas the latter is not. Based on this intuition, we systematically analyzed the previous fusion approach and introduced a comprehensive framework for two types of side information. Finally, we devise self-supervised objectives fitting for each type of side-information in a multi-task training scheme. To validate the effectiveness of our proposed method, we conduct experiments across various domains.https://ieeexplore.ieee.org/document/10824815/Side-information fusionself-supervised learningsequential recommendation |
| spellingShingle | Seunghwan Choi Donghoon Lee Hyeoungguk Kang Hyunsouk Cho Exploring the Side-Information Fusion for Sequential Recommendation IEEE Access Side-information fusion self-supervised learning sequential recommendation |
| title | Exploring the Side-Information Fusion for Sequential Recommendation |
| title_full | Exploring the Side-Information Fusion for Sequential Recommendation |
| title_fullStr | Exploring the Side-Information Fusion for Sequential Recommendation |
| title_full_unstemmed | Exploring the Side-Information Fusion for Sequential Recommendation |
| title_short | Exploring the Side-Information Fusion for Sequential Recommendation |
| title_sort | exploring the side information fusion for sequential recommendation |
| topic | Side-information fusion self-supervised learning sequential recommendation |
| url | https://ieeexplore.ieee.org/document/10824815/ |
| work_keys_str_mv | AT seunghwanchoi exploringthesideinformationfusionforsequentialrecommendation AT donghoonlee exploringthesideinformationfusionforsequentialrecommendation AT hyeounggukkang exploringthesideinformationfusionforsequentialrecommendation AT hyunsoukcho exploringthesideinformationfusionforsequentialrecommendation |