Please use this identifier to cite or link to this item: https://doi.org/10.1145/3397271.3401137
Title: Disentangled Graph Collaborative Filtering
Authors: WANG XIANG 
Hongye Jin
An Zhang
Tong Xu
CHUA TAT SENG 
HE XIANGNAN 
Keywords: Collaborative Filtering
Graph Neural Networks
Disentangled Representation Learning
Explainable Recommendation
Issue Date: 25-Jul-2020
Publisher: SIGIR 2020
Citation: WANG XIANG, Hongye Jin, An Zhang, Tong Xu, CHUA TAT SENG, HE XIANGNAN (2020-07-25). Disentangled Graph Collaborative Filtering. SIGIR 2020. ScholarBank@NUS Repository. https://doi.org/10.1145/3397271.3401137
Rights: Attribution 4.0 International
Abstract: Learning informative representations of users and items from the interaction data is of crucial importance to collaborative filtering(CF). Present embedding functions exploit user-item relationships to enrich the representations, evolving from a single user-item instance to the holistic interaction graph. Nevertheless, they largely model the relationships in a uniform manner, while neglecting the diversity of user intents on adopting the items, which could be to pass time, for interest, or shopping for others like families. Such uniform approach to model user interests easily results in suboptimal representations, failing to model diverse relationship sand disentangle user intents in representations.In this work, we pay special attention on user-item relationships at the finer granularity of user intents. We hence devise a newmodel, Disentangled Graph Collaborative Filtering(DGCF), to disentangle these factors and yield disentangled representations. Specifically, by modeling a distribution over intents for each user-item interaction, we iteratively refine the intent-aware interaction graphs and representations. Meanwhile, we encourage the independence of different intents. This leads to disentangled representations, effectively distilling information pertinent to each intent. We conduct extensive experiments on three benchmark datasets, and DGCF achieves significant improvements over several state-of-the-art models like NGCF [40], DisenGCN [25], and MacridVAE [26]. Further analyses offer insights into the advantages of DGCF on the disentanglement of user intents and the interpretability of representations. Our codes are available at https://github.com/xiangwang1223/disentangled_graph_collaborative_filtering.
Source Title: SIGIR 2020
URI: https://scholarbank.nus.edu.sg/handle/10635/183427
DOI: 10.1145/3397271.3401137
Rights: Attribution 4.0 International
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Disentangled Graph Collaborative Filtering.pdf986.39 kBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

4
checked on Jun 7, 2021

Page view(s)

100
checked on Jun 10, 2021

Download(s)

2
checked on Jun 10, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons