Improving knowledge-aware recommendation with multi-level interactive contrastive learning

Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item in...

Full description

Saved in:
Bibliographic Details
Main Authors: ZOU, Ding, WEI, Wei, WANG, Ziyang, MAO, Xian-Ling, ZHU, Feida, FANG, Rui, CHEN, Dangyang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7751
https://ink.library.smu.edu.sg/context/sis_research/article/8754/viewcontent/improving.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-8754
record_format dspace
spelling sg-smu-ink.sis_research-87542023-01-19T10:12:45Z Improving knowledge-aware recommendation with multi-level interactive contrastive learning ZOU, Ding WEI, Wei WANG, Ziyang MAO, Xian-Ling ZHU, Feida FANG, Rui CHEN, Dangyang Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, from the following aspects: 1) the sparse interaction, itself, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) further results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring the non-local KG facts and making the knowledge extraction insufficient. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring contrastive learning in KGR and propose a novel multi-level interactive contrastive learning mechanism, to alleviate the aforementioned challenges. Different from traditional contrastive learning methods which contrast nodes of two generated graph views, interactive contrastive mechanism conducts layer-wise self-supervised learning by contrasting layers of different parts within graphs, which is also an "interaction" action. Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR. Then an intra-graph level interactive contrastive learning is performed within each local/non-local graph, which contrasts layers of the CF and KG parts, for more consistent information leveraging. Besides, an inter-graph level interactive contrastive learning is performed between the local and non-local graphs, for sufficiently and coherently extracting non-local KG signals. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/KGIC. 2022-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7751 info:doi/10.1145/3511808.3557358 https://ink.library.smu.edu.sg/context/sis_research/article/8754/viewcontent/improving.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 Knowledge Graph Recommendation Contrastive Learning 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 Knowledge Graph
Recommendation
Contrastive Learning
Databases and Information Systems
spellingShingle Knowledge Graph
Recommendation
Contrastive Learning
Databases and Information Systems
ZOU, Ding
WEI, Wei
WANG, Ziyang
MAO, Xian-Ling
ZHU, Feida
FANG, Rui
CHEN, Dangyang
Improving knowledge-aware recommendation with multi-level interactive contrastive learning
description Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, from the following aspects: 1) the sparse interaction, itself, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) further results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring the non-local KG facts and making the knowledge extraction insufficient. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring contrastive learning in KGR and propose a novel multi-level interactive contrastive learning mechanism, to alleviate the aforementioned challenges. Different from traditional contrastive learning methods which contrast nodes of two generated graph views, interactive contrastive mechanism conducts layer-wise self-supervised learning by contrasting layers of different parts within graphs, which is also an "interaction" action. Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR. Then an intra-graph level interactive contrastive learning is performed within each local/non-local graph, which contrasts layers of the CF and KG parts, for more consistent information leveraging. Besides, an inter-graph level interactive contrastive learning is performed between the local and non-local graphs, for sufficiently and coherently extracting non-local KG signals. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/KGIC.
format text
author ZOU, Ding
WEI, Wei
WANG, Ziyang
MAO, Xian-Ling
ZHU, Feida
FANG, Rui
CHEN, Dangyang
author_facet ZOU, Ding
WEI, Wei
WANG, Ziyang
MAO, Xian-Ling
ZHU, Feida
FANG, Rui
CHEN, Dangyang
author_sort ZOU, Ding
title Improving knowledge-aware recommendation with multi-level interactive contrastive learning
title_short Improving knowledge-aware recommendation with multi-level interactive contrastive learning
title_full Improving knowledge-aware recommendation with multi-level interactive contrastive learning
title_fullStr Improving knowledge-aware recommendation with multi-level interactive contrastive learning
title_full_unstemmed Improving knowledge-aware recommendation with multi-level interactive contrastive learning
title_sort improving knowledge-aware recommendation with multi-level interactive contrastive learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7751
https://ink.library.smu.edu.sg/context/sis_research/article/8754/viewcontent/improving.pdf
_version_ 1770576434584092672