Multi-behavior Recommendation with Graph Convolutional Networks

Jin, Bowen; Gao, Chen; He, Xiangnan; Jin, Depeng; Li, Yong

doi:10.1145/3397271.3401072

Cited by 270 publications

(125 citation statements)

References 24 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…Graph convolutional neural networks (GCNNs) are a generalization of convolutional neural networks (CNNs) to graph-based relational data that is not natively structured in Euclidean space [30]. Due to the expressive power of graphs, GCNNs have been applied across a wide variety of domains, including traffic flow prediction [31], recommender systems [32], and social networks [33]. The prevalence of graph-based datasets in biology has made these models a popular choice for tasks like modeling protein-protein interactions [34], stem cell differentiation [35], and chemical reactivity for drug discovery [36].…”

Section: Methodsmentioning

confidence: 99%

“…Graph convolutional networks (GCNs) are a generalization of convolutional neural networks (CNN s) to graph-based relational data that is not natively structured in Euclidean space [Liu and Zhou, 2020]. Due to the expressive power of graphs, GCNs have been applied across a wide variety of domains, including recommender systems [Jin et al, 2020] and social networks [Qiu et al, 2018].…”

Section: Graph Convolutional Network (Gcns)mentioning

confidence: 99%

“…• PRDX2 encodes an enzyme that reduces hydrogen peroxide and alkyl hydroperoxides [ Entrez Gene, 1988]. It protects against oxidative stress [Jin et al, 2020] as well as stabilizes hemoglobin, making it a therapeutic target for the treatment of hemolytic anemia. Table S3: Neighbor coordinates for exemplar genes.…”

Section: S2 Analysis Of Exemplar Genesmentioning

confidence: 99%

See 2 more Smart Citations

Integrating long-range regulatory interactions to predict gene expression using graph convolutional networks

Bigness

Patel

et al. 2020

Preprint

View full text Add to dashboard Cite

Long-range spatial interactions among genomic regions are critical for regulating gene expression and their disruption has been associated with a host of diseases. However, when modeling the effects of regulatory factors on gene expression, most deep learning models either neglect long-range interactions or fail to capture the inherent 3D structure of the underlying biological system. This prevents the field from obtaining a more comprehensive understanding of gene regulation and from fully leveraging the structural information present in the data sets. Here, we propose a graph convolutional neural network (GCNN) framework to integrate measurements probing spatial genomic organization and measurements of local regulatory factors, specifically histone modifications, to predict gene expression. This formulation enables the model to incorporate crucial information about long-range interactions via a natural encoding of spatial interaction relationships into a graph representation. Furthermore, we show that our model is interpretable in terms of the observed biological regulatory factors, highlighting both the histone modifications and the interacting genomic regions that contribute to a gene’s predicted expression. We apply our GCNN model to datasets for GM12878 (lymphoblastoid) and K562 (myelogenous leukemia) cell lines and demonstrate its state-of-the-art prediction performance. We also obtain importance scores corresponding to the histone mark features and interacting regions for some exemplar genes and validate them with evidence from the literature. Our model presents a novel setup for predicting gene expression by integrating multimodal datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Graph Convolutional Network (Gcns)mentioning

confidence: 99%

See 1 more Smart Citation

Integrating long-range regulatory interactions to predict gene expression using graph convolutional networks

Bigness

Patel

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…There are many irregular data in the form of graphs in real life, such as social networks, knowledge graphs, and so on. The graph convolutional network (GCN) has become a key research direction because of its great advantages in extracting the characteristics of irregular graph data [29], [30], [55], [70], [140], [141].…”

Section: B Model-based Cf Algorithmsmentioning

confidence: 99%

An Overview of Recommendation Techniques and Their Applications in Healthcare

Yue

Wang

Zhang

et al. 2021

IEEE/CAA J. Autom. Sinica

View full text Add to dashboard Cite

With the increasing amount of information on the internet, recommendation system (RS) has been utilized in a variety of fields as an efficient tool to overcome information overload. In recent years, the application of RS for health has become a growing research topic due to its tremendous advantages in providing appropriate recommendations and helping people make the right decisions relating to their health. This paper aims at presenting a comprehensive review of typical recommendation techniques and their applications in the field of healthcare. More concretely, an overview is provided on three famous recommendation techniques, namely, content-based, CF-based, and hybrid methods. Next, we provide a snapshot of five application scenarios about health RS, which are dietary recommendation, lifestyle recommendation, training recommendation, decision-making for patients and physicians, and disease-related prediction. Finally, some key challenges are given with clear justifications to this new and booming field.

show abstract

“…Graph neural network (GNN) is an effective neural architecture for mining graph-structured data, since it can capture the high-order content and topological information on graphs 8 . It has been widely used in personalization scenarios such as product recommendation [9][10][11] and content personalization 12 to model the complicated interactions among users and items. The success of existing GNN-based personalization systems depends on centralized graph data for model learning, which is usually constructed by the data collected from a large number of users 13 .…”

mentioning

confidence: 99%

A Federated Graph Neural Network Framework for Privacy-Preserving Personalization

Huang

Lyu

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rely on centralized GNN learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, we present a federated GNN framework named FedGNN for both effective and privacy-preserving personalization. Through a privacy-preserving model update method, we can collaboratively train GNN models based on decentralized graphs inferred from local data. To further exploit graph information beyond local interactions, we introduce a privacy-preserving graph expansion protocol to incorporate high-order information under privacy protection. Experimental results on six datasets for personalization in different scenarios show that FedGNN achieves 4.0%~9.6% lower errors than the state-of-the-art federated personalization methods under good privacy protection. FedGNN provides a novel direction to mining decentralized graph data in a privacy-preserving manner for responsible and intelligent personalization.

show abstract

Multi-behavior Recommendation with Graph Convolutional Networks

Cited by 270 publications

References 24 publications

Integrating long-range regulatory interactions to predict gene expression using graph convolutional networks

Integrating long-range regulatory interactions to predict gene expression using graph convolutional networks

An Overview of Recommendation Techniques and Their Applications in Healthcare

A Federated Graph Neural Network Framework for Privacy-Preserving Personalization

Contact Info

Product

Resources

About