Filters








4,653 Hits in 4.7 sec

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks [article]

Lichao Sun, Lifang He, Zhipeng Huang, Bokai Cao, Congying Xia, Xiaokai Wei, Philip S. Yu
2018 arXiv   pre-print
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information  ...  The MEGA++ further facilitates the use of coupled tensor-matrix decomposition method to obtain a joint embedding for nodes, which simultaneously considers the hidden relations of all meta information of  ...  In this paper, we think the HIN with different views such as meta-paths and meta-graph, and fuse the different information for node embedding.  ... 
arXiv:1809.04110v1 fatcat:l6wd5ytqizamvgpsgi754yeorm

From Statistical Relational to Neuro-Symbolic Artificial Intelligence

Luc de Raedt, Sebastijan Dumančić, Robin Manhaeve, Giuseppe Marra
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to identify a number of directions for further research.  ...  Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning.  ...  It also utilizes the high-level semantic attention to differentiate and aggregate information from different meta paths. Heterogeneous Graph Transformer.  ... 
doi:10.24963/ijcai.2020/677 dblp:conf/ijcai/DongHWS020 fatcat:srd5r66dovefrpa5drxmrek25e

Heterogeneous Graph Attention Network [article]

Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Peng Cui, P. Yu, Yanfang Ye
2021 arXiv   pre-print
The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph.  ...  However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links.  ...  ACKNOWLEDGMENTS This work is supported in part by the National Natural Science Foundation of China (No. 61702296, 61772082, 61532006) , the Beijing Municipal Natural Science Foundation (4182043), and  ... 
arXiv:1903.07293v2 fatcat:wrwdajlnm5bahhh26ngd5z7pfe

A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks [article]

Rayyan Ahmad Khan, Martin Kleinsteuber
2021 arXiv   pre-print
Heterogeneous Information Network (HIN) embedding refers to the low-dimensional projections of the HIN nodes that preserve the HIN structure and semantics.  ...  In this work, we propose \ours for joint learning of cluster embeddings as well as cluster-aware HIN embedding.  ...  A Heterogeneous Information Network or HIN is defined as a graph G = {V, E, A, R, , } with the sets of nodes and edges represented by V and E respectively.  ... 
arXiv:2108.03953v1 fatcat:xde5gvcgxzejpf7rhnuljqjzcq

Attention-Guide Walk Model in Heterogeneous Information Network for Multi-Style Recommendation Explanation

Xin Wang, Ying Wang, Yunzhi Ling
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
the heterogeneous information network.  ...  Too many interactive factors between users and items can be used to interpret the recommendation in a heterogeneous information network.  ...  Acknowledgments This work was supported by a grant from the National Natural Science Foundation of China under grants (No. 61602057, No. 61872161 and No. 61976103  ... 
doi:10.1609/aaai.v34i04.6095 fatcat:mb636x2jbbhgxhxjyzxihj53w4

HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding [article]

Yu He and Yangqiu Song and Jianxin Li and Cheng Ji and Jian Peng and Hao Peng
2019 arXiv   pre-print
Then we propose a generalized scalable framework to leverage the heterogeneous personalized spacey random walk to learn embeddings for multiple types of nodes in an HIN guided by a meta-path, a meta-graph  ...  Heterogeneous information network (HIN) embedding has gained increasing interests recently.  ...  heterogeneous networks to demonstrate that the proposed methods considerably outperform both conventional homogeneous embedding and heterogeneous meta-path/meta-graph guided embedding methods in two HIN  ... 
arXiv:1909.03228v1 fatcat:uzpzogehuvhovd2tfsmcf7gutm

Network Schema Preserving Heterogeneous Information Network Embedding

Jianan Zhao, Xiao Wang, Chuan Shi, Zekuan Liu, Yanfang Ye
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Many of the existing HIN embedding methods adopt meta-path guided random walk to retain both the semantics and structural correlations between different types of nodes.  ...  As heterogeneous networks have become increasingly ubiquitous, Heterogeneous Information Network (HIN) embedding, aiming to project nodes into a low-dimensional space while preserving the heterogeneous  ...  Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/190 dblp:conf/ijcai/ZhaoWSLY20 fatcat:32hdufftejd75e2lbbnqrlizdi

Personalized Scientific Paper Recommendation based on Heterogeneous Graph Representation

Xiao Ma, Ranran Wang
2019 IEEE Access  
INDEX TERMS Recommender systems, paper recommendation, heterogeneous information networks, graph representation, meta-paths.  ...  Third, we jointly update the node embeddings in the heterogeneous graph by proposing two meta-path based proximity measures.  ...  Definition 3 ( 3 Heterogeneous Information Network Representation Learning): For a given network G(V , E), V and E represent the set of nodes and edges, respectively.  ... 
doi:10.1109/access.2019.2923293 fatcat:owaxatica5fd7paux4hgneb5ym

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 propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path and achieve more informative representations  ...  Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN.  ...  Graph Neural Networks (GNNs) More recently, graph neural networks ( Conclusion The paper proposes HetSANN to perform meta-path-free embedding based on structural information in heterogeneous graphs  ... 
arXiv:1912.10832v1 fatcat:trv7zyezzjf2dc6gr7xs4ukeoi

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 propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path and achieve more informative representations  ...  Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN.  ...  Conclusion The paper proposes HetSANN to perform meta-path-free embedding based on structural information in heterogeneous graphs.  ... 
doi:10.1609/aaai.v34i04.5833 fatcat:pztajppn4jaehn7kapyw54qnra

Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification [article]

Ting Chen, Yizhou Sun
2016 arXiv   pre-print
The guidance from author identification task for network embedding is provided both explicitly in joint training and implicitly during meta path selection.  ...  We extend the existing unsupervised network embedding to incorporate meta paths in heterogeneous networks, and select paths according to the specific task.  ...  Acknowledgement We would like to thank anonymous reviewers for helpful suggestions. This work is partially supported by NSF CAREER #1453800.  ... 
arXiv:1612.02814v2 fatcat:g5lhuqmqpnfjjjckbkaeaiojfe

Predictive and Contrastive: Dual-Auxiliary Learning for Recommendation [article]

Yinghui Tao, Min Gao, Junliang Yu, Zongwei Wang, Qingyu Xiong, Xu Wang
2022 arXiv   pre-print
user-item paths induced by meta-paths.  ...  Accordingly, the rich semantics reflected by social relationships and item categories, which lie in the recommendation data-based heterogeneous graphs, are not fully exploited.  ...  As a typical instantiation of heterogeneous graphs, meta-path [19] is widely used to capture the semantics reflected from complex information.  ... 
arXiv:2203.03982v1 fatcat:bgevmwxadnanva666ut24lzonq

Heterogeneous Similarity Graph Neural Network on Electronic Health Records [article]

Zheng Liu, Xiaohan Li, Hao Peng, Lifang He, Philip S. Yu
2021 arXiv   pre-print
On the other hand, current heterogeneous graph neural networks cannot be simply used on an EHR graph because of the existence of hub nodes in it.  ...  The preprocessing method normalizes edges and splits the EHR graph into multiple homogeneous graphs while each homogeneous graph contains partial information of the original EHR graph.  ...  It exploits meta-paths and employs a joint embedding framework to predict diagnosis for patients. We use the same graph structure on this model as HSGNN. • MAGNN [20] .  ... 
arXiv:2101.06800v1 fatcat:d3e2xvjebbc7dh7yk6hfclibau

Attentional Heterogeneous Graph Neural Network: Application to Program Reidentification [article]

Shen Wang, Zhengzhang Chen, Ding Li, Lu-An Tang, Jingchao Ni, Zhichun Li, Junghwan Rhee, Haifeng Chen, Philip S. Yu
2019 arXiv   pre-print
We formulate the program reidentification as a graph classification problem and develop an effective attentional heterogeneous graph embedding algorithm to solve it.  ...  In this paper, we propose an attentional heterogeneous graph neural network model (DeepHGNN) to verify the program's identity based on its system behaviors.  ...  a heterogeneous information network into a multi-channel graph; • We propose a heterogeneous graph neural network based approach to learn the graph embedding via propagating the contextual information  ... 
arXiv:1812.04064v2 fatcat:7vujchgqbfgenjskt66njvgsye

An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers [article]

Jie Song and Meiyu Liang and Zhe Xue and Junping Du and Kou Feifei
2022 arXiv   pre-print
Learning knowledge representation of scientific paper data is a problem to be solved, and how to learn the representation of paper nodes in scientific paper heterogeneous network is the core to solve this  ...  Based on the heterogeneous graph representation, this paper performs link prediction on the entire heterogeneous graph and obtains the relationship between the edges of the nodes, that is, the relationship  ...  This paper constructs a heterogeneous graph including 3025 papers (P), 5835 authors (A), and 56 topics (S). Experiment with the meta-path set {PAP, PSP}.  ... 
arXiv:2203.16751v1 fatcat:xtelw33xjbdwpmukle5m3zvrr4
« Previous Showing results 1 — 15 out of 4,653 results