ระบบจัดเก็บและค้นหางานวิจัยอัจฉริยะ

BiG: Bidirectional Graph Convolutional Networks for Social and Sequential Recommendation

ผศ.ดร.นิกร กรรณิกากลาง | bidirectional graph graph convolutional network gate

จำนวนผู้เข้าชม

Creative Commons License

BiG: Bidirectional Graph Convolutional Networks for Social and Sequential Recommendation is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 Thailand License.

ดาวน์โหลดเอกสาร

ดาวน์โหลด: 0 ครั้ง

DOI Link EndNote OpenURL

Collection	RMUTK Research Repository (RMUTK IR) บทความประชุมวิชาการ — Proceedings
ID RMUTK Digital	RMUTK000115
Title	BiG: Bidirectional Graph Convolutional Networks for Social and Sequential Recommendation
Alternative title	BiG: Bidirectional Graph Convolutional Networks for Social and Sequential Recommendation
Authors	ผศ.ดร.นิกร กรรณิกากลาง ผู้แต่งหลัก
Faculty	คณะบริหารธุรกิจ
Volume / Issue / Pages	pp.1-6
Conference	2024 28th International Computer Science and Engineering Conference (ICSEC)
Conference Date	2024-11-06
Conference Location	Khon Kaen, Thailand
Year	2567
Level	ระดับนานาชาติ
DOI	10.1109/ICSEC62781.2024.10770627
ISBN / ISSN	979-8-3503-6687-7
Funding Source	มทร.กรุงเทพ
Abstract	Graph convolutional networks have obviously influenced recommender systems. However, we argue that previous research has limitations: 1) unidirectional approaches are not enough to explicitly capture the representation learning, 2) social influence is ignored to extract the user preference drifts, and 3) simple and crude fusion methods are not enough to seamlessly amalgamate the diverse behavioral perspective. To address these limitations, this research proposes a novelty of Bidirectional Graph convolutional networks for social and sequential recommendation (BiG). A novel graph convolutional networks are modified into bidirectional graphs to explicitly learn the representation of dynamic user preference at social level and sequential level. A novel Bidirectional Gate (BiGate) is designed to amalgamate the diverse preferences of social and sequential influences. Empirical experiment illustrates that BiG outperforms state-of-the-art methods.
Abstract (EN)	Graph convolutional networks have obviously influenced recommender systems. However, we argue that previous research has limitations: 1) unidirectional approaches are not enough to explicitly capture the representation learning, 2) social influence is ignored to extract the user preference drifts, and 3) simple and crude fusion methods are not enough to seamlessly amalgamate the diverse behavioral perspective. To address these limitations, this research proposes a novelty of Bidirectional Graph convolutional networks for social and sequential recommendation (BiG). A novel graph convolutional networks are modified into bidirectional graphs to explicitly learn the representation of dynamic user preference at social level and sequential level. A novel Bidirectional Gate (BiGate) is designed to amalgamate the diverse preferences of social and sequential influences. Empirical experiment illustrates that BiG outperforms state-of-the-art methods.
Keywords (TH)	bidirectional graph graph convolutional network gate sequential recommendation social recommendation
Keywords (EN)	bidirectional graph graph convolutional network gate sequential recommendation social recommendation
Access Level	Open Access (เปิดสาธารณะ)

เอกสารดิจิทัล

RMUTK000115_full.pdf

จำนวนดาวน์โหลด: 0 ครั้ง

Open Access

ดาวน์โหลด