Filters








557,257 Hits in 3.6 sec

Higher-order Network Representation Learning

Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh
2018 Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18  
The experimental results demonstrate the effectiveness of learning higher-order network representations.  ...  This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs.  ...  Given Y, we learn a global higherorder network embedding by solving the following: arg min Z,H∈ C D Y ∥ Φ⟨ZH⟩ (9) where Z is a N × D matrix of node embeddings.  ... 
doi:10.1145/3184558.3186900 dblp:conf/www/RossiAK18 fatcat:zav4qhlmv5debjvovpbofkpbom

Higher-Order Function Networks for Learning Composable 3D Object Representations [article]

Eric Mitchell, Selim Engin, Volkan Isler, Daniel D Lee
2020 arXiv   pre-print
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network.  ...  Further experiments on feature mixing through the composition of learned functions show that the encoding captures a meaningful subspace of objects.  ...  The parameters of this function are estimated by a 'higher order' encoder network, thus motivating the name for our method: Higher-Order Function networks (HOF).  ... 
arXiv:1907.10388v2 fatcat:3mxbe7tqmrfa3i5nigq4dsmvem

Multi-View Network Representation Learning Algorithm Research

Zhonglin Ye, Haixing Zhao, Ke Zhang, Yu Zhu
2019 Algorithms  
Network representation learning is a key research field in network data mining.  ...  In contrast to existing approaches, MVNR explicitly encodes higher order information using k-step networks.  ...  The MVNR algorithm proposed is a higher order network representation learning algorithm.  ... 
doi:10.3390/a12030062 fatcat:7vc7kajfzvagzbjpln5wh6tgqu

Consciousness and metarepresentation: A computational sketch

Axel Cleeremans, Bert Timmermans, Antoine Pasquali
2007 Neural Networks  
This implements a limited form of metarepresentation, to the extent that the second-order network's internal representations become re-representations of the first-order network's internal states.  ...  Consciousness, in this light, thus involves knowledge of the geography of one own's internal representations -a geography that is itself learned over time as a result of an agent's attributing value to  ...  and the higher-order network.  ... 
doi:10.1016/j.neunet.2007.09.011 pmid:17904799 fatcat:qjibfdwewnbardrzssi5hpds3i

Higher-order Boltzmann machines

Terrence J. Sejnowski
1986 AIP Conference Proceedings  
T h e rate of learning for internal representations in a higher-order Boltzmann machine should be much faster t h a n for a second-order Boltzmann machine based on pairwise interactions.  ...  In a third-order Boltzmann machine, triples of units interact through symmetric conjunctive interactions. The Boltzmann learning algorithm is generalized t o higher-order interactions.  ...  T h e rate of learning for internal representations in a higher-order Boltzmann machine should be much faster t h a n for a second-order Boltzmann machine based on pairwise interactions.  ... 
doi:10.1063/1.36246 fatcat:dpfiseswozeyplef7oejoklkgu

Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks

Kishan Kc, Rui Li, Feng Cui, Anne Haake
2021 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
In this paper, we present a higher-order graph convolutional network (HOGCN) to aggregate information from the higher-order neighborhood for biomedical interaction prediction.  ...  Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction.  ...  Thus, we adopt a higher-order graph convolution (HOGC) layer from MixHop [13] to learn such feature differences and encode the higher-order network properties of biomedical networks.  ... 
doi:10.1109/tcbb.2021.3059415 pmid:33587705 pmcid:PMC8518029 fatcat:txg5omrtdnadvjk6bjk4ey2wqm

An Optimized Network Representation Learning Algorithm Using Multi-Relational Data

Ye, Zhao, Zhang, Zhu, Wang
2019 Mathematics  
Importantly, we adopted a kind of higher order transformation strategy to optimize the learnt network representation vectors.  ...  The purpose of network representation learning is to learn the structural relationships between network vertices.  ...  [13] propose a unified framework of higher order proximity approximation, NEU, which can approximate a higher order proximity matrix for learning better network representations.  ... 
doi:10.3390/math7050460 fatcat:qgipkrrtezhf3bjbagjdazhyma

OFFER: A Motif Dimensional Framework for Network Representation Learning

Shuo Yu, Feng Xia, Jin Xu, Zhikui Chen, Ivan Lee
2020 Proceedings of the 29th ACM International Conference on Information & Knowledge Management  
In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined.  ...  The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results.  ...  INTRODUCTION Network representation learning has been widely applied. The general idea of network representation learning is to convert nodes into vectors.  ... 
doi:10.1145/3340531.3417446 dblp:conf/cikm/Yu0XCL20 fatcat:zbfmgyiqube7hemrnilikpntr4

OFFER: A Motif Dimensional Framework for Network Representation Learning [article]

Shuo Yu, Feng Xia, Jin Xu, Zhikui Chen, Ivan Lee
2020 arXiv   pre-print
In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined.  ...  The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results.  ...  INTRODUCTION Network representation learning has been widely applied. The general idea of network representation learning is to convert nodes into vectors.  ... 
arXiv:2008.12010v1 fatcat:qgswpwk4mbfybeifaszejil2su

HSNR: A Network Representation Learning Algorithm Using Hierarchical Structure Embedding

Zhonglin Ye, Haixing Zhao, Yu Zhu, Yuzhi Xiao
2020 Chinese journal of electronics  
In this work, we propose a novel network representation learning algorithm by introducing group features of vertices of different orders to learn more discriminative network representations, named as network  ...  In order to introduce hierarchical features into the network representation learning model, HSNR algorithm then introduces the idea of multi-relational modeling from knowledge representation, and converts  ...  essentially embed higher order features of the network into the network representation learning algorithm.  ... 
doi:10.1049/cje.2020.10.001 fatcat:zjjuevofbvaf7nikstq7x2xa6y

Semisupervised Community Preserving Network Embedding with Pairwise Constraints

Dong Liu, Yan Ru, Qinpeng Li, Shibin Wang, Jianwei Niu, Xianggui Guo
2020 Complexity  
Network embedding aims to learn the low-dimensional representations of nodes in networks.  ...  Experimental results on eight real network datasets show that, comparing with the representative network embedding methods, the node representations learned after incorporating the pairwise constraints  ...  Constructing a k-order proximity matrix preserves higher-order node similarity and improves network embedding performance.  ... 
doi:10.1155/2020/7953758 fatcat:sw3fe6iqv5hkbm4axp3ndfekua

Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis [article]

Guixiang Ma, Nesreen K. Ahmed, Ted Willke, Dipanjan Sengupta, Michael W. Cole, Nicholas B. Turk-Browne, Philip S. Yu
2019 arXiv   pre-print
Our proposed framework performs higher-order convolutions by incorporating higher-order proximity in graph convolutional networks to characterize and learn the community structure in brain connectivity  ...  The proposed framework learns the brain network representations via a supervised metric-based approach with siamese neural networks using two graph convolutional networks as the twin networks.  ...  That motivates us to design the higher-order GCNs that operate on higher-order proximity representations of graphs.  ... 
arXiv:1811.02662v5 fatcat:aovkttg67ffm5gtprk57tlqdpq

Motif-Aware Adversarial Graph Representation Learning

Ming Zhao, Yinglong Zhang, Xuewen Xia, Xing Xu
2022 IEEE Access  
INDEX TERMS Graph representation learning, higher order structure, motif connectivity, generative adversarial networks.  ...  higher order structure and the original lower order structure.  ...  As a result, the learned graph representation preserves the Motif higher order structure and the original lower order structure. IV.  ... 
doi:10.1109/access.2022.3144233 fatcat:lsbfu7ov2rakhhqwlpad6lvmw4

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

Manoj Reddy Dareddy, Mahashweta Das, Hao Yang
2019 arXiv   pre-print
We propose a novel efficient algorithm, motif2vec that learns node representations or embeddings for heterogeneous networks.  ...  Research efforts dedicated to representation learning, especially representation learning using deep learning, has shown us ways to automatically learn relevant features from vast amounts of potentially  ...  Rossi et al. introduced the problem of higher-order network representation learning using motifs for homogeneous networks [20] . But the method cannot be extended to handle heterogeneous networks.  ... 
arXiv:1908.08227v1 fatcat:v2rz4tieyzh4pkr6wajqdfunfq

Graph Neural Network for Higher-Order Dependency Networks

Di Jin, Yingli Gong, Zhiqiang Wang, Zhizhi Yu, Dongxiao He, Yuxiao Huang, Wenjun Wang
2022 Proceedings of the ACM Web Conference 2022  
We formulize the network with higher-order dependency as an augmented conventional first-order network, and then feed it into GNNs to derive network embeddings.  ...  To address this problem, we propose for the first time new GNN approaches for higher-order networks in this paper.  ...  PRELIMINARIES We first introduce the concept of conventional networks and graph representation learning tasks, and then explain in details what are higher-order dependencies and higher-order networks.  ... 
doi:10.1145/3485447.3512161 fatcat:mwssd2ensfef3f6uc3zcxu5ota
« Previous Showing results 1 — 15 out of 557,257 results