Filters








71,985 Hits in 4.8 sec

Multi-modal Network Representation Learning

Chuxu Zhang, Meng Jiang, Xiangliang Zhang, Yanfang Ye, Nitesh V. Chawla
2020 Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining  
In this tutorial, we systematically review the area of multi-modal network representation learning, including a series of recent methods and applications.  ...  Therefore, automating the feature discovery through representation learning in multi-modal networks has become essential for many applications.  ...  Unsupervised Methods and Applications (50 mins) 4.1 Heterogeneous network embedding 4.2 Heterogeneous graph neural network 4.3 Temporal/dynamic/evolutionary graph neural network 4.4 Graph neural network  ... 
doi:10.1145/3394486.3406475 fatcat:vbnikhs53ndczblj2nepa5nq2y

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  
Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning.  ...  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.  ...  Applications Since heterogeneous networks can abstract and model realworld complex systems, representation learning on heterogeneous networks have numerous applications, such as similarity search, knowledge  ... 
doi:10.24963/ijcai.2020/677 dblp:conf/ijcai/DongHWS020 fatcat:srd5r66dovefrpa5drxmrek25e

End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning [article]

Yao Xiao, Guixiang Ma, Nesreen K. Ahmed, Mihai Capota, Theodore Willke, Shahin Nazarian, Paul Bogdan
2022 arXiv   pre-print
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is  ...  The proposed framework extracts multi-fractal topological features from code graphs, utilizes graph autoencoders to learn how to partition the graph into computational kernels, and exploits graph neural  ...  Graph Representation Learning for Code Representation.  ... 
arXiv:2204.11981v1 fatcat:jfmas6hxareuhpf4tq4ed7dxli

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.  ...  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  ...  Heterogeneous Contextual Relation Learning for User Representation In this section, we review the recent advances for user modeling and personalization with the modeling heterogeneous relational context  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Metapaths guided Neighbors aggregated Network for?Heterogeneous Graph Reasoning [article]

Bang Lin, Xiuchong Wang, Yu Dong, Chengfu Huo, Weijun Ren, Chuanyu Xu
2021 arXiv   pre-print
Heterogeneous graph embedding is to learn the structure and semantic information from the graph, and then embed it into the low-dimensional node representation.  ...  We conduct extensive experiments for the proposed MHN on three real-world heterogeneous graph datasets, including node classification, link prediction and online A/B test on Alibaba mobile application.  ...  Given a heterogeneous graph = {V, }, heterogeneous graph embedding is the task to learn the -dimensional node representations ∈ R , ∀ ∈ V, which can capture the structural and semantic information of the  ... 
arXiv:2103.06474v1 fatcat:rt7lwzapebccrg3ta4zrztwc4u

MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding

Junhui Chen, Feihu Huang, Jian Peng
2021 Applied Sciences  
Furthermore, we discussed the application of MSGCN with respect to a transductive learning task and inductive learning task, respectively.  ...  Heterogeneous graph embedding has become a hot topic in network embedding in recent years and has been widely used in lots of practical scenarios.  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app11219832 fatcat:jllatfdxlzdvjd5sqeejuy6twe

motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks [article]

Manoj Reddy Dareddy, Mahashweta Das, Hao Yang
2019 arXiv   pre-print
Recent years have witnessed a surge of interest in machine learning on graphs and networks with applications ranging from vehicular network design to IoT traffic management to social network recommendations  ...  We propose a novel efficient algorithm, motif2vec that learns node representations or embeddings for heterogeneous networks.  ...  Each method is designed for a specific heterogeneous network mining application. In our work, we learn node representations that are effective for both classification and prediction.  ... 
arXiv:1908.08227v1 fatcat:v2rz4tieyzh4pkr6wajqdfunfq

A Literature Review of Recent Graph Embedding Techniques for Biomedical Data [article]

Yankai Chen and Yaozu Wu and Shicheng Ma and Irwin King
2021 arXiv   pre-print
research and industrial application for human healthcare.  ...  Many graph-based learning methods have been proposed to analyze such type of data, giving a deeper insight into the topology and knowledge behind the biomedical data, which greatly benefit to both academic  ...  In addition, the biomedical graphs are usually sparse, incomplete, and heterogeneous, making graph embedding more complicated than other application domains.  ... 
arXiv:2101.06569v2 fatcat:vqfosu4o6neklfffpvpmmdor2q

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
2021 IEEE Transactions on Knowledge and Data Engineering  
in graph representation learning.  ...  With the ubiquitous graph-structured data in various applications, models that can learn compact but expressive vector representations of nodes have become highly desirable.  ...  We propose WIDEN, which is an innovative graph neural network variant that supports inductive and efficient representation learning on heterogeneous graphs.  ... 
doi:10.1109/tkde.2021.3100529 fatcat:azur4cdwafg3zhk27tnssqysza

Towards Robust Representations of Spatial Networks Using Graph Neural Networks

Chidubem Iddianozie, Gavin McArdle
2021 Applied Sciences  
Specifically, we consider homogeneous and heterogeneous representations of spatial networks.  ...  We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks.  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app11156918 fatcat:gh6hbdl3xbfx3eoyl6bwwryeuq

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [article]

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
2021 arXiv   pre-print
in graph representation learning.  ...  With the ubiquitous graph-structured data in various applications, models that can learn compact but expressive vector representations of nodes have become highly desirable.  ...  We propose WIDEN, which is an innovative graph neural network variant that supports inductive and efficient representation learning on heterogeneous graphs.  ... 
arXiv:2104.01711v2 fatcat:uozthcnesjbszdf2ciauvvgrai

Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction

Youru Li, Zhenfeng Zhu, Deqiang Kong, Meixiang Xu, Yao Zhao
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To address this issue, we proposed a novel model named STG2Vec to learn the representation from heterogeneous spatial-temporal graph.  ...  Additionally, together with other multi-source information such as geographical position, historical transition patterns and weather, e.g., the representation learned by STG2Vec can be fed into the LSTMs  ...  Ackowledgments This work was jointly sponsored by the National Key Research and Development of China (No.2016YFB0800404) and the National Natural Science Foundation of China (No.61572068, No.61532005)  ... 
doi:10.1609/aaai.v33i01.33011004 fatcat:4xo7b35m75hmxny7tob7vbbici

Semantic Mediation Model to Promote Improved Data Sharing Using Representation Learning in Heterogeneous Healthcare Service Environments

Ali, Chong
2019 Applied Sciences  
The alignment of diverse data models has been supported with the deep representation learning method.  ...  This is mainly because of the reason that data is collected, processed, and managed using heterogeneous protocols, different data formats, and diverse technologies, respectively.  ...  S.A. and I.C. defined the research theme and designed the proposed model. S.A. implemented the prototype and wrote the article. S.A. and I.C. discussed and evaluated the prototype outcomes.  ... 
doi:10.3390/app9194175 fatcat:g5w5xw3j65f27kewcmqix6vffu

Deep Learning with Knowledge Graphs

Jure Leskovec
2022 Zenodo  
Machine learning, especially deep representation learning, on graphs is an emerging field with a wide array of applications from protein folding and fraud detection, to drug discovery and recommender systems  ...  I will also discuss industrial applications, software frameworks, benchmarks, and challenges with scaling-up graph learning systems.  ...  (1): Recommender Engines § Challenges: § Massive size: 3 billion nodes, 20 billion edges § Heterogeneous data: Rich image and text features Learn node embeddings 𝑧 !  ... 
doi:10.5281/zenodo.6538200 fatcat:7a2m4pjczjdcbomhkoe3yqgnay

A Tutorial on Network Embeddings [article]

Haochen Chen, Bryan Perozzi, Rami Al-Rfou, Steven Skiena
2018 arXiv   pre-print
These representations can be used as features for a wide range of tasks on graphs such as classification, clustering, link prediction, and visualization.  ...  Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.  ...  [27] propose a neural network model for learning user representations in a heterogeneous social network.  ... 
arXiv:1808.02590v1 fatcat:ramuqdavczfabb4o7r42kice7q
« Previous Showing results 1 — 15 out of 71,985 results