Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

Wang, Xiao; Liu, Nian; Han, Hu; Shi, Chuan

doi:10.48550/arxiv.2105.09111

Cited by 9 publications

(19 citation statements)

References 29 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HeCo [32]: A self-supervised heterogeneous graph neural network. The node representation of the heterogeneous network is learned from two perspectives, namely the network architecture perspective and the metapath perspective, which fully capture the information in the heterogeneous network.…”

Section: Methodsmentioning

confidence: 99%

MEAHNE: MiRNA-disease association prediction based on semantic information in heterogeneous networks

Huang

Cen

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Prior studies have suggested close associations between miRNAs and diseases. Correct prediction of potential miRNA-disease pairs by computational methods is able to greatly accelerate the experimental process in biomedical research. However, many methods cannot effectively learn the complex information in the multi-source data, and limits the performance of the prediction model. A heterogeneous network prediction model MEAHNE is proposed to make full use of the complex information in multi-source data. We first constructed a heterogeneous network using miRNA-disease associations, miRNA-gene associations, disease-gene associations, and gene-gene associations. Because the rich semantic information in the heterogeneous network contains a lot of relational information of the network. To mine the relational information in heterogeneous network, we use neural networks to extract semantic information in metapath instances. We encode the obtained semantic information into weights using the attention mechanism, and use the weights to aggregate nodes in the network. At the same time, we also aggregate the semantic information in the metapath instances into the nodes associated with the instances, which can make the node embedding have excellent ability to represent the network. MEAHNE optimizes parameters through end-to-end training. MEAHNE is compared with other state-of-the-art heterogeneous graph neural network methods. The values of area under precision-recall curve and receiver operating characteristic curve show the superiority of MEAHNE. Additionally, MEAHNE predicted 50 miRNAs for lung cancer and esophageal cancer each and verified 49 miRNAs associated with lung cancer and 44 miRNAs associated with esophageal cancer by consulting relevant databases. MEAHNE has good performance and interpretability by experimental verification.

show abstract

Section: Methodsmentioning

confidence: 99%

MEAHNE: MiRNA-disease association prediction based on semantic information in heterogeneous networks

Huang

Cen

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, in citation networks like ACM, there are three types of nodes (including author, paper, and subject), and there are two types of edges (representing author-write-paper and paper-belongsubject relations). To cluster nodes of a speciic type (e.g., papers), it is a common practice to construct various meta-paths between two papers, such as paper-author-paper (describing two papers written by the same author), and paper-subject-paper (meaning that two papers belong to the same subject) [57,70]. Therefore, heterogeneous graphs can be transformed into multi-relational graphs having homogeneous nodes (papers) and diferent types of edges (meta-paths).…”

Section: Four Types Of Graph Structuresmentioning

confidence: 99%

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Kamhoua

Zhang

et al. 2023

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

Attributed graph clustering (AGC) is an important problem in graph mining as more and more complex data in real-world have been represented in graphs with attributed nodes. While it is a common practice to leverage both attribute and structure information for improved clustering performance, most existing AGC algorithms consider only a specific type of relations, which hinders their applicability to integrate various complex relations into node attributes for AGC. In this paper, we propose GRACE, an extended graph convolution framework for AGC tasks. Our framework provides a general and interpretative solution for clustering many different types of attributed graphs, including undirected, directed, heterogeneous and hyper attributed graphs. By building suitable graph Laplacians for each of the aforementioned graph types, GRACE can seamlessly perform graph convolution on node attributes to fuse all available information for clustering. We conduct extensive experiments on 14 real-world datasets of 4 different graph types. The experimental results show that GRACE outperforms the state-of-the-art AGC methods on the different graph types in terms of clustering quality, time, and memory usage.

show abstract

“…Contrastive Learning methods [34,44,49] learn node representations by contrasting positive pairs against negative pairs. DGI [34] first adopts Infomax [23] in graph representation learning, and focuses on contrasting the local node embeddings with global graph embeddings.…”

Section: Contrastive Learningmentioning

confidence: 99%

“…Similarly, MVGRL [12] learns node-and graph-level node representations from two structural graph views including first-order neighbors and a graph diffusion, and contrasts encoded embeddings between two graph views. More recently, HeCo [44] proposes to learn node representations from network schema view and metapath view, and performs contrastive learning between them. And in traditional collaborative filtering (CF) based recommendation domain, SGL [49] conducts contrastive learning between original graph and corrupted graph on user-item interactions.…”

Section: Contrastive Learningmentioning

confidence: 99%

“…Actually, it is still non-trivial to design a proper contrastive learning framework, for that characteristics of both contrastive learning and knowledge-aware recommendation are needed to be carefully considered for balance, which requires us to address the following fundamental issues [44]: (1) How to design a proper contrastive mechanism? Due to heterogeneity, the designed model is naturally required to simultaneously handle multiple types of nodes (e.g., user, item, and entity) and relations (e.g., user-item, item-entity and etc).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

Zou,

Wei,

Mao

et al. 2022

Preprint

View full text Add to dashboard Cite

Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-aware recommendation (KGR). However, there is a natural deficiency for GNN-based KGR models, that is, the sparse supervised signal problem, which may make their actual performance drop to some extent. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring the contrastive learning in KG-aware recommendation and propose a novel multi-level cross-view contrastive learning mechanism, named MCCLK. Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views. Specifically, we consider the user-item graph as a collaborative view, the item-entity graph as a semantic view, and the user-item-entity graph as a structural view. MCCLK hence performs contrastive learning across three views on both local and global levels, mining comprehensive graph feature and structure information in a self-supervised manner. Besides, in semantic view, a 𝑘-Nearest-Neighbor (𝑘NN) item-item semantic graph construction module is proposed, to capture the important item-item semantic relation which is usually ignored by previous work. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are

show abstract

Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

Cited by 9 publications

References 29 publications

MEAHNE: MiRNA-disease association prediction based on semantic information in heterogeneous networks

MEAHNE: MiRNA-disease association prediction based on semantic information in heterogeneous networks

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

Contact Info

Product

Resources

About