Filters








35,123 Hits in 8.7 sec

Heterogeneous Graph Representation Learning with Relation Awareness [article]

Le Yu, Leilei Sun, Bowen Du, Chuanren Liu, Weifeng Lv, Hui Xiong
2021 arXiv   pre-print
To this end, in this paper, we propose a novel Relation-aware Heterogeneous Graph Neural Network, namely R-HGNN, to learn node representations on heterogeneous graphs at a fine-grained level by considering  ...  Moreover, a semantic fusing module is presented to aggregate relation-aware node representations into a compact representation with the learned relation representations.  ...  CONCLUSION This paper studied the problem of heterogeneous graph learning and proposed to learn node representations considering relation-aware characteristics.  ... 
arXiv:2105.11122v1 fatcat:qs6wnnwksveqdim3nvgmk4fe4m

Heterogeneity-aware Twitter Bot Detection with Relational Graph Transformers [article]

Shangbin Feng, Zhaoxuan Tan, Rui Li, Minnan Luo
2021 arXiv   pre-print
We then propose relational graph transformers to model heterogeneous influence between users and learn node representations.  ...  Specifically, we construct a heterogeneous information network with users as nodes and diversified relations as edges.  ...  We then learn node representations under each relation with our proposed relational graph transformers.  ... 
arXiv:2109.02927v3 fatcat:oq5si6mw6jh3xgyts7u7ftap3u

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
In this survey, we review the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items.  ...  The objective of this task is to map heterogeneous relational data into latent representation space, such that the structural and relational properties from both user and item domain can be well preserved  ...  Along with this line, learning informative multi-modal representations of users and items with the incorporation of multi-modal content data into heterogeneous relational learning paradigms, become an  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Hop-Hop Relation-aware Graph Neural Networks [article]

Li Zhang, Yan Ge, Haiping Lu
2020 arXiv   pre-print
In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs.  ...  Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs.  ...  We propose Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), a new class of GNNs, to unify GNN-based homogeneous and heterogeneous graph representation learning. 2.  ... 
arXiv:2012.11147v1 fatcat:bgqrc6umtfgbjmguufngdvbma4

Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning [article]

Ziyue Qiao, Pengyang Wang, Yanjie Fu, Yi Du, Pengfei Wang, Yuanchun Zhou
2020 arXiv   pre-print
Therefore, to overcome the limitations of the literature, we propose T-GNN, a tree structure-aware graph neural network model for graph representation learning.  ...  While Graph Neural Network (GNN) has shown superiority in learning node representations of homogeneous graphs, leveraging GNN on heterogeneous graphs remains a challenging problem.  ...  Therefore, to overcome the limitations of the literature, we propose a Tree structure-aware Graph Neural Network(T-GNN) for heterogeneous graph representation learning.  ... 
arXiv:2008.10003v2 fatcat:rnmuindpgng2vfo47lr5i6lory

DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction [article]

Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu
2020 arXiv   pre-print
Then, we encode the temporal information into the heterogeneous graph to learn the users' dynamic preferences.  ...  In this paper, we propose a novel dynamic heterogeneous graph convolutional network (DyHGCN) to jointly learn the structural characteristics of the social graph and dynamic diffusion graph.  ...  Firstly, we design a heterogeneous graph algorithm to learn the representation of the social network and diffusion relations.  ... 
arXiv:2006.05169v1 fatcat:442shdfz7jb2fgmnp3mezscpoy

Fraud Detection in Online Product Review Systems via Heterogeneous Graph Transformer

Songkai Tang, Luhua Jin, Fan Cheng
2021 IEEE Access  
FAHGT adopts a type-aware feature mapping mechanism to handle heterogeneous graph data, then implementing various relation scoring methods to alleviate inconsistency and discover camouflage.  ...  Alternatively, we propose a new model named Fraud Aware Heterogeneous Graph Transformer(FAHGT), to address camouflages and inconsistency problems in a unified manner.  ...  Given a sampled heterogeneous sub-graph with t as the target node, s 1 and s 2 as the source nodes, the FAHGT model takes its edges e 1 = (s 1 , t) and e 2 = (s 2 , t) as input to learn the representation  ... 
doi:10.1109/access.2021.3084924 fatcat:wzzwnmdptnfm5hvarripls7heu

Multi-Behavior Sequential Recommendation with Temporal Graph Transformer

Lianghao Xia, Chao Huang, Yong Xu, Jian Pei
2022 IEEE Transactions on Knowledge and Data Engineering  
In this work, we tackle the dynamic user-item relation learning with the awareness of multi-behavior interactive patterns.  ...  Learning from informative representations of users and items based on their multi-typed interaction data, is of great importance to accurately characterize the time-evolving user preference.  ...  It is a state-of-the-art heterogeneous graph learning model which integrates the transformer with the graph-based message passing scheme.  ... 
doi:10.1109/tkde.2022.3175094 fatcat:iqreqptfvbeeffmit4isv7xsuu

CKGAT: Collaborative Knowledge-Aware Graph Attention Network for Top-N Recommendation

Zhuoming Xu, Hanlin Liu, Jian Li, Qianqian Zhang, Yan Tang
2022 Applied Sciences  
learn high-order entity representations, thereby generating refined ripple set embeddings.  ...  Based on the heterogeneous propagation strategy, CKGAT uses the knowledge-aware graph attention network to extract the topological proximity structures of entities in the multi-hop ripple sets and then  ...  learn user representations, item representations, entity representations, and relation representations.  ... 
doi:10.3390/app12031669 fatcat:wi4xwnajr5ekth3fbtafw2p5b4

Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning [article]

Yanqiao Zhu, Yichen Xu, Hejie Cui, Carl Yang, Qiang Liu, Shu Wu
2021 arXiv   pre-print
Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data.  ...  Considering the complex graph structure and the smoothing nature of GNNs, we propose a structure-aware hard negative mining scheme that measures hardness by structural characteristics for HGs.  ...  We term the resulting CL framework for HGs as HeterOgeneous gRAph Contrastive learning with structure-aware hard nEgative mining, HORACE for brevity ( Figure 2 ).  ... 
arXiv:2108.13886v1 fatcat:sqsy56q3incsxj5bi36ixxg74q

An Attention-Based Graph Neural Network for Heterogeneous Structural Learning

Huiting Hong, Hantao Guo, Yucheng Lin, Xiaoqing Yang, Zang Li, Jieping Ye
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations.  ...  spaces, and multi-task learning with full use of information.  ...  Related Work Heterogeneous Graph Representation Learning The existing works of HIN embedding tend to utilize the meta-path to adapt the heterogeneous graph for the application of the homogeneous graph  ... 
doi:10.1609/aaai.v34i04.5833 fatcat:pztajppn4jaehn7kapyw54qnra

An Attention-based Graph Neural Network for Heterogeneous Structural Learning [article]

Huiting Hong, Hantao Guo, Yucheng Lin, Xiaoqing Yang, Zang Li, Jieping Ye
2019 arXiv   pre-print
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations.  ...  spaces, and multi-task learning with full use of information.  ...  Related Work Heterogeneous Graph Representation Learning The existing works of HIN embedding tend to utilize the meta-path to adapt the heterogeneous graph for the application of the homogeneous graph  ... 
arXiv:1912.10832v1 fatcat:trv7zyezzjf2dc6gr7xs4ukeoi

DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction [article]

Yule Wang, Qiang Luo, Yue Ding, Dong Wang, Hongbo Deng
2021 arXiv   pre-print
To be specific, we first consider various dependency types between item nodes and perform dependency-aware heterogeneous attention for denoising and obtaining accurate sequence item representations.  ...  Secondly, for multiple interests extraction, multi-head attention is conducted on top of the graph embedding.  ...  havior sequence, we perform multi-dependency-aware heterogeneous attention and self-supervised interest learning.  ... 
arXiv:2109.12512v1 fatcat:vznmni5xfzhsnjkfnxh5kfyhsa

A Semantic Aware Meta-path Model for Heterogeneous Network Representation Learning

Yiping Yang, Zhongwang Fu, Adnan Iftekhar, Xiaohui Cui
2020 IEEE Access  
Heterogeneous Network Representation Learning.  ...  A GNN based method for heterogeneous graphs. It learns node representations from each meta-path.  ... 
doi:10.1109/access.2020.3043269 fatcat:s3uispdobvecnoejiz4tu23j5q

Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network

Meng Cao, Jinliang Yuan, Ming Xu, Hualei Yu, Chongjun Wang
2021 IEEE Access  
Specifically, we first design a relational self-attention graph neural network model to aggregate heterogeneous information and automatically extract semantic similarity without using meta-paths.  ...  In this paper, we propose a local structural aware heterogeneous information network embedding model named LSA-HNE.  ...  The two key components, i.e., (1) the relational self-attention graph neural network (RSANN), and (2) the local structural aware embedding learning method, are introduced as follows. C.  ... 
doi:10.1109/access.2021.3090055 fatcat:6ynffvfhgvgcndcpd3374jrwyu
« Previous Showing results 1 — 15 out of 35,123 results