HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation

Knowledge graph (KG) plays an increasingly important role to improve the recommendation performance and interpretability. A recent technical trend is to design end-to-end models based on information propagation mechanism. However, existing propagationbased methods fail to (1) model the underlying hi...

Full description

Saved in:
Bibliographic Details
Main Authors: DU, Yuntao, ZHU, Xinjun, CHEN, Lu, ZHENG, Baihua, GAO, Yunjun
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7181
https://ink.library.smu.edu.sg/context/sis_research/article/8184/viewcontent/_Submit__HAKG__Hierarchy_Aware_Knowledge_Gated_Network_for_Recommendation.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8184
record_format dspace
spelling sg-smu-ink.sis_research-81842023-08-04T05:00:39Z HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation DU, Yuntao ZHU, Xinjun CHEN, Lu ZHENG, Baihua GAO, Yunjun Knowledge graph (KG) plays an increasingly important role to improve the recommendation performance and interpretability. A recent technical trend is to design end-to-end models based on information propagation mechanism. However, existing propagationbased methods fail to (1) model the underlying hierarchical structures and relations, and (2) capture the high-order collaborative signals of items for learning high-quality user and item representations. In this paper, we propose a new model, called Hierarchy-Aware Knowledge Gated Network (HAKG), to tackle the aforementioned problems. Technically, we model users and items (that are captured by a user-item graph), as well as entities and relations (that are captured in a KG) in hyperbolic space, and design a hyperbolic aggregation scheme to gather relational contexts over KG. Meanwhile, we introduce a novel angle constraint to preserve characteristics of items in the embedding space. Furthermore, we propose a novel dual item embeddings design to represent and propagate collaborative signals and knowledge associations separately, and leverage the gated aggregation to distill discriminative information for better capturing user behavior patterns. Experimental results on three benchmark datasets show that, HAKG achieves significant improvement over the state-of-the-art methods like CKAN, Hyper-Know, and KGIN. Further analyses on the learned hyperbolic embeddings confirm that HAKG offers meaningful insights into the hierarchies of data. 2022-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7181 info:doi/10.1145/3477495.3531987 https://ink.library.smu.edu.sg/context/sis_research/article/8184/viewcontent/_Submit__HAKG__Hierarchy_Aware_Knowledge_Gated_Network_for_Recommendation.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Recommendation Graph Neural Network Knowledge Graph Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Recommendation
Graph Neural Network
Knowledge Graph
Databases and Information Systems
spellingShingle Recommendation
Graph Neural Network
Knowledge Graph
Databases and Information Systems
DU, Yuntao
ZHU, Xinjun
CHEN, Lu
ZHENG, Baihua
GAO, Yunjun
HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
description Knowledge graph (KG) plays an increasingly important role to improve the recommendation performance and interpretability. A recent technical trend is to design end-to-end models based on information propagation mechanism. However, existing propagationbased methods fail to (1) model the underlying hierarchical structures and relations, and (2) capture the high-order collaborative signals of items for learning high-quality user and item representations. In this paper, we propose a new model, called Hierarchy-Aware Knowledge Gated Network (HAKG), to tackle the aforementioned problems. Technically, we model users and items (that are captured by a user-item graph), as well as entities and relations (that are captured in a KG) in hyperbolic space, and design a hyperbolic aggregation scheme to gather relational contexts over KG. Meanwhile, we introduce a novel angle constraint to preserve characteristics of items in the embedding space. Furthermore, we propose a novel dual item embeddings design to represent and propagate collaborative signals and knowledge associations separately, and leverage the gated aggregation to distill discriminative information for better capturing user behavior patterns. Experimental results on three benchmark datasets show that, HAKG achieves significant improvement over the state-of-the-art methods like CKAN, Hyper-Know, and KGIN. Further analyses on the learned hyperbolic embeddings confirm that HAKG offers meaningful insights into the hierarchies of data.
format text
author DU, Yuntao
ZHU, Xinjun
CHEN, Lu
ZHENG, Baihua
GAO, Yunjun
author_facet DU, Yuntao
ZHU, Xinjun
CHEN, Lu
ZHENG, Baihua
GAO, Yunjun
author_sort DU, Yuntao
title HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
title_short HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
title_full HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
title_fullStr HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
title_full_unstemmed HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
title_sort hakg: hierarchy-aware knowledge gated network for recommendation
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7181
https://ink.library.smu.edu.sg/context/sis_research/article/8184/viewcontent/_Submit__HAKG__Hierarchy_Aware_Knowledge_Gated_Network_for_Recommendation.pdf
_version_ 1773551432341913600