没有合适的资源?快使用搜索试试~ 我知道了~
首页清华最新《图神经网络推荐系统》综述论文
清华最新《图神经网络推荐系统》综述论文
需积分: 0 22 下载量 159 浏览量
更新于2023-04-28
评论
收藏 3.39MB PDF 举报
推荐系统是当今互联网上最重要的信息服务之一。近年来,图神经网络已成为推荐系统的新技术。在这个调研中,我们对基于图神经网络的推荐系统的文献进行了全面的回顾。我们首先介绍了推荐系统和图神经网络的背景和发展历史。对于推荐系统,一般来说,现有工作的分类分为四个方面: 阶段、场景、目标和应用。对于图神经网络,现有的方法包括谱模型和空间模型两大类。
资源详情
资源评论
资源推荐
Graph Neural Networks for Recommender Systems:
Challenges, Methods, and Directions
CHEN GAO*
1
, YU ZHENG*
1
, NIAN LI
1
, YINFENG LI
1
, YINGRONG QIN
1
, JINGHUA
PIAO
1
, YUHAN QUAN
1
, JIANXIN CHANG
1
, DEPENG JIN
1
, XIANGNAN HE
2
, YONG
LI*
1
,
1
Beijing National Research Center for Information Science and Technology (BNRist), Department of
Electronic Engineering, Tsinghua University and
2
School of Information Science and Technology, University
of Science and Technology of China
Recommender system is one of the most important information services on today’s Internet. Recently, graph
neural networks have become the new state-of-the-art approach of recommender systems. In this survey,
we conduct a comprehensive review of the literature in graph neural network-based recommender systems.
We rst introduce the background and the history of the development of both recommender systems and
graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing
works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist
of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph
neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural
property of data, and the enhanced supervision signal. We then systematically analyze the challenges in
graph construction, embedding propagation/aggregation, model optimization, and computation eciency.
Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph
neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions
on the open problems and promising future directions of this area. We summarize the representative papers
along with their codes repositories in https://github.com/tsinghua-b-lab/GNN-Recommender-Systems.
Additional Key Words and Phrases: Recommender Systems, Graph Neural Networks, Graph Representation
Learning; Information Retrieval
ACM Reference Format:
Chen Gao*
1
, Yu Zheng*
1
, Nian Li
1
, Yinfeng Li
1
, Yingrong Qin
1
, Jinghua Piao
1
, Yuhan Quan
1
, Jianxin Chang
1
,
Depeng Jin
1
, Xiangnan He
2
, Yong Li*
1
. 2021. Graph Neural Networks for Recommender Systems: Challenges,
Methods, and Directions. ACM Transactions on Information Systems 1, 1 (September 2021), 46 pages. https:
//doi.org/10.1145/nnnnnnn.nnnnnnn
1 INTRODUCTION
Recommender system, is a kind of ltering system of which the goal is to present personalized
information to users, which improves the user experience and promotes business prot. As one of
∗
Yong Li is the Corresponding Author. The rst two authors contributed equally to this paper.
Author’s address: Chen Gao*
1
, Yu Zheng*
1
, Nian Li
1
, Yinfeng Li
1
, Yingrong Qin
1
, Jinghua Piao
1
, Yuhan Quan
1
, Jianxin
Chang
1
, Depeng Jin
1
, Xiangnan He
2
, Yong Li*
1
,
1
Beijing National Research Center for Information Science and Technology
(BNRist), Department of Electronic Engineering, Tsinghua University,
2
School of Information Science and Technology,
University of Science and Technology of China, chgao96@gmail.com,{y-zheng19,linian21,liyf19,qyr16,pojh19,quanyh19,
changjx18}@mails.tsinghua.edu.cn,xiangnanhe@gmail.com,{jindp,liyong07}@tsinghua.edu.cn.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee
provided that copies are not made or distributed for prot or commercial advantage and that copies bear this notice and
the full citation on the rst page. Copyrights for components of this work owned by others than ACM must be honored.
Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires
prior specic permission and/or a fee. Request permissions from permissions@acm.org.
© 2021 Association for Computing Machinery.
1046-8188/2021/9-ART $15.00
https://doi.org/10.1145/nnnnnnn.nnnnnnn
ACM Transactions on Information Systems, Vol. 1, No. 1, Article . Publication date: September 2021.
arXiv:2109.12843v1 [cs.IR] 27 Sep 2021
2 Gao et al.
the typical applications of machine learning driven by the real world, it is an extremely hot topic in
both industrial and academia nowadays.
To recap the history of recommender systems, it can be generally divided into three stages,
shallow models [
74
,
125
,
126
], neural models [
26
,
48
,
56
], and GNN-based models [
55
,
153
,
188
]. The
earliest recommendation models capture the collaborative ltering (CF) eect by directly calculating
the similarity of interactions. Then model-based CF methods, such as matrix factorization (MF) [
74
]
or factorization machine[
125
], were proposed to approach recommendation as a representation
learning problem. However, these methods are faced with critical challenges such as complex user
behaviors or data input. To address it, neural network-based models [
26
,
48
,
56
] are proposed. For
example, neural collaborative ltering (NCF) was developed to extend the inner product in MF
with multi-layer perceptrons (MLP) to improve its capacity. Similarly, deep factorization machine
(DeepFM) [
48
] combined the shallow model factorization machine (FM) [
125
] with MLP. However,
these methods are still highly limited since their paradigms of prediction and training ignore the
high-order structural information in observed data. For example, the optimization goal of NCF
is to predict user-item interaction, and the training samples include observed positive user-item
interactions and unobserved negative user-item interactions. It means that during the parameter
updating for a specic user, only the items interacted by him/her are involved.
Recently, the advances of graph neural networks provide a strong fundamental and opportunity
to address the above issues in recommender systems. Specically, graph neural networks adopt
embedding propagation to aggregate neighborhood embedding iteratively. By stacking the propaga-
tion layers, each node can access high-order neighbors’ information, rather than only the rst-order
neighbors’ as the traditional methods do. With its advantages to handle the structural data and
to explore structural information, GNN-based methods have become the new state-of-the-art
approaches in recommender systems.
To well apply graph neural networks into recommender systems, there are some critical chal-
lenges required to be addressed. First, the data input of recommender system should be carefully
and properly constructed to graph, with nodes representing elements and edges representing the
relations. Second, for the specic task, the component in the graph neural network should be
adaptively designed, including how to propagate and aggregate, in which existing works have
explored various choices with dierent advantages and disadvantages. Third, the optimization of
the GNN-based model, including the optimization goal, loss function, data sampling, etc., should
be consistent with the task requirement. Last, since recommender systems have strict limitations
on the computation cost, and also due to GNNs’ embedding propagation operations introduce
a number of computations, the ecient deployment of graph neural networks in recommender
systems is another critical challenge.
In this paper, we aim to provide a systematic and comprehensive review of the research eort,
especially on how they improve recommendation with graph neural networks and address the
corresponding challenges. To fulll a clear understanding, we categorize researches of recommender
systems from four perspectives, stage, scenario, objectives, and applications. We summarize the
representative papers along with their codes repositories in https://github.com/tsinghua-b-lab/
GNN-Recommender-Systems.
It is worth mentioning that there is one existing survey [
168
] of graph neural network-based
recommender system. However, it is limited due to the following reasons. First, it does not provide
extensive taxonomy of recommender systems. Specically, it roughly divides recommender systems
into non-sequential recommendation and sequential recommendation, however, which is not so
reasonable. In fact, the sequential recommendation is only one specic recommendation scenario
with a special setting of input and output, as pointed out by this survey. Second, it does not provide
adequate explanations of the motivations and reasons that the existing works leverage graph
ACM Transactions on Information Systems, Vol. 1, No. 1, Article . Publication date: September 2021.
Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions 3
• Accuracy (precision)
• Diversity / Novelty
• Explainability / Interpretability
• Fairness
• Security and Privacy
Objective
Recommender System
• Matching (Collaborative Filtering)
• Ranking (Feature-based / CTR)
• Re-Ranking
Stage
• Social Recommendation
• Sequential Recommendation
• Session-based Recommendation
• Cross-domain Recommendation
• Multi-behavior Recommendation
• Bundle Recommendation
Application
• Product Recommendation
• POI Recommendation
• News Recommendation
• Movie Recommendation
• Video Recommendation
• Music Recommendation
Scenario
Fig. 1. An illustration of typical recommender systems (stages, scenarios, objectives, and applications)
neural networks for recommender systems. In this survey, by contrast, we provide a comprehensive
understanding of why GNN can be and should be used in recommender system, which can help
readers to understand the position and value of this new research eld. Third, it does not explain
the critical challenges of applying graph neural networks to recommendation and how to address
them, which are fully discussed in this survey. Last, since this area is increasingly popular, our
survey also introduces a lot of recently published papers not covered by [168].
The structure of this survey is organized as follows. We rst introduce the background of
recommender systems, from four kinds of perspectives (stage, scenario, objective, application), and
the background of graph neural networks, in Section 2. We then discuss the challenges of applying
graph neural networks to recommender systems from four aspects, in Section 3. Then we elaborate
on the representative methods of graph nerual network-based recommendation in Section 4 by
following the taxonomy in the above section. We discuss the most critical open problems in this
area and provide ideas of the future directions in Section 5 and conclude this survey in Section 6.
2 BACKGROUND
2.1 Recommender Systems
2.1.1 Overview . In this section, we present the background of recommender systems from four
perspectives: stages, scenarios, objectives, and applications. Specically, in industrial applications,
due to the real-world requirements on system engineering, the recommender systems are always
split into three stages, matching, ranking, and re-ranking, forming a standard pipeline. Each stage
has dierent characteristics on data input, output, model design, etc. Besides the standard stages,
there are many specic recommendation scenarios with a special denition. For example, in the
last twenty years, social recommendation has been attracting attention, dened as improving
recommender system based on social relations. Last, dierent recommender systems have dierent
objectives, of which accuracy is always the most important one as it directly determines the
system’s utility. Recently, recommender systems have been assigned other requirements such as
recommending diversied items to avoid boring user experience, making sure the system treats
all users fairly, protecting user privacy from attack, etc. As for the applications, GNN models can
ACM Transactions on Information Systems, Vol. 1, No. 1, Article . Publication date: September 2021.
4 Gao et al.
Stage Matching Ranking Re-ranking
Pipeline
Item Amount
Millions → Hundreds Hundreds → Tens Tens → Tens
Alias Candidate Generation, Retrieval Scoring, CTR prediction
Post
-
processing, Policy
Challenge Relevance, Efficiency
Accuracy, Feature Interaction
Item Relationship
item pool
Ranking
Model
Matching Source 1
Matching Source 2
Matching Source K
…
User Features
Item Features
Re-ranking
Model
Fig. 2. The typical pipeline of recommender systems.
be widely deployed in e-commerce recommendation, point-of-interest recommendation, news
recommendation, movie recommendation, music recommendation, etc.
2.1.2 Stages . The item pool, i.e. all the items available for recommender systems, is usually large
and can include millions of items. Thus, common recommender systems follow a multi-stage archi-
tecture, ltering items stage by stage from the large-scale item pool to the nal recommendations
exposed to users, tens of items. [
29
,
158
]. Generally, a modern recommender system is composed
of the following three stages.
• Matching.
This rst stage generates hundreds of candidate items from the extremely large
item pool (million-level or even billion-level), which signicantly reduces the scale. Considering
the large scale of data input in this stage, and due to the strict latency restrictions of online
serving, complicated algorithms cannot be adopted, such as very deep neural networks [
29
,
70
].
In other words, models in this stage are usually concise. That is, the core task of this stage is to
retrieve potentially relevant items with high eciency and attain coarse-grained modeling of
user interests. It is worth noting that a recommender system in the real world usually contains
multiple matching channels with multiple models, such as embedding matching, geographical
matching, popularity matching, social matching, etc.
• Ranking.
After the matching stage, multiple sources of candidate items from dierent channels
are merged into one list and then scored by a single ranking model. Specically, the ranking
model ranks these items according to the scores, and the top dozens of items are selected. Since
the amount of input items in this stage is relatively small, the system can aord much more
complicated algorithms to achieve higher recommendation accuracy [69, 89, 133]. For example,
rich features including user proles and item attributes can be taken into consideration, and
advanced techniques such as self-attention [
69
] can be utilized. Since a lot of features are involved,
the key challenge in this stage is to design appropriate models for capturing complicated feature
interactions.
• Re-ranking.
Although the obtained item list after the ranking stage is optimized with respect
to relevance, it may not meet other important requirements, such as freshness, diversity, fairness,
etc. [
120
] Therefore, a re-ranking stage is necessary, which usually removes certain items or
changes the order of the list in order to fulll additional criteria and also satisfy business needs.
The main concern in this stage is to consider multiple relationships among the top-scored items
[
5
,
217
]. For example, similar or substitutable items can lead to information redundancy when
they are displayed closely in the recommendations.
ACM Transactions on Information Systems, Vol. 1, No. 1, Article . Publication date: September 2021.
Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions 5
User-item Interaction Social Networks
Fig. 3. An illustration of social recommendation. User interactions are aected by both their own preferences
and the social factor.
Sequence
Fig. 4. An illustration of sequential recommendation. Given a user’s historical sequence, recommender
system aims to predict the next item.
Fig. 2 illustrates the typical pipeline of a recommender system, as well as the comparisons of the
three stages above.
2.1.3 Scenarios. In the following, we will elaborate on the dierent scenarios of recommender
systems, including social recommendation, sequential recommendation, session recommendation,
bundle recommendation, cross-domain recommendation, and multi-behavior recommendation.
• Social Recommendation.
In the past few years, social platforms have dramatically changed
users’ daily life. With the ability to interact with other users, individual behaviors are driven by
both personal and social factors. Specically, users’ behavior may be inuenced by what their
friends might do or think, which is known as social inuence [
28
]. For example, users in WeChat
∗
Video platform may like some videos only because of their WeChat friends’ like behaviors. At
the same time, social homophily is another popular phenomenon in many social platforms, i.e.,
people tend to build social relations with others who have similar preferences with them [
107
].
Taking social e-commerce as an example, users from a common family possibly share similar
product preferences, such as food, clothes, daily necessities, and so on. Hence, social relations are
often integrated into recommender systems to enhance the nal performance, which is called
social recommendation. Fig. 3 illustrates the data input of social recommendation, of which user
interactions are determined by both his/her own preferences and social factors (social inuence
and social homophily).
• Sequential Recommendation.
In recommender systems, users will produce a large number of
interaction behaviors over time. The sequential recommendation method extracts information
from these behavioral sequences and predicts the user’s next interaction item, as shown in
Fig. 4. To symbolize this problem, for the sequence of items
{𝑥
1
, 𝑥
2
, ..., 𝑥
𝑛
}
that the user has
∗
http://wechat.com/
ACM Transactions on Information Systems, Vol. 1, No. 1, Article . Publication date: September 2021.
剩余45页未读,继续阅读
syp_net
- 粉丝: 158
- 资源: 1196
上传资源 快速赚钱
- 我的内容管理 收起
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
会员权益专享
最新资源
- zigbee-cluster-library-specification
- JSBSim Reference Manual
- c++校园超市商品信息管理系统课程设计说明书(含源代码) (2).pdf
- 建筑供配电系统相关课件.pptx
- 企业管理规章制度及管理模式.doc
- vb打开摄像头.doc
- 云计算-可信计算中认证协议改进方案.pdf
- [详细完整版]单片机编程4.ppt
- c语言常用算法.pdf
- c++经典程序代码大全.pdf
- 单片机数字时钟资料.doc
- 11项目管理前沿1.0.pptx
- 基于ssm的“魅力”繁峙宣传网站的设计与实现论文.doc
- 智慧交通综合解决方案.pptx
- 建筑防潮设计-PowerPointPresentati.pptx
- SPC统计过程控制程序.pptx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0