19,686 Hits in 6.0 sec

Learning Based Proximity Matrix Factorization for Node Embedding [article]

Xingyi Zhang, Kun Xie, Sibo Wang, Zengfeng Huang
2021 arXiv   pre-print
Node embedding learns a low-dimensional representation for each node in the graph.  ...  Existing approaches first define a proximity matrix and then learn the embeddings that fit the proximity by matrix factorization.  ...  Matrix Factorization for Node Embedding Finally, given learned probabilities, computing learned proximities for each node-pair is still expensive for large graphs, and existing efficient algorithms for  ... 
arXiv:2106.05476v3 fatcat:m5zyczkolrd5dfwcw2ulmutvme

Binarized attributed network embedding

Hong Yang, Shirui Pan, Peng Zhang, Ling Chen, Defu Lian, Chengqi Zhang
2018 2018 IEEE International Conference on Data Mining (ICDM)  
Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint.  ...  To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation.  ...  Then, based on the new proximity matrix, we formulate a Weisfiler-Lehman matrix factorization learning function under the binary representation constraint.  ... 
doi:10.1109/icdm.2018.8626170 dblp:conf/icdm/YangP00LZ18 fatcat:m3f5vb4iqrbunc33bczk3wxl5u

Enhancing Network Embedding with Auxiliary Information: An Explicit Matrix Factorization Perspective [article]

Junliang Guo, Linli Xu, Xunpeng Huang, Enhong Chen
2018 arXiv   pre-print
For structure, we validate that the matrix we construct preserves high-order proximities of the network.  ...  As a consequence, network embedding can be learned in a unified framework integrating network structure and node content as well as label information simultaneously.  ...  matrix of structural proximities for a network based on a random walk sampling procedure.  ... 
arXiv:1711.04094v2 fatcat:3rowahnat5gxxoq3c7no4jadae

Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings [article]

Benedek Rozemberczki, Rik Sarkar
2021 arXiv   pre-print
Proximity preserving and structural role-based node embeddings have become a prime workhorse of applied graph mining.  ...  Our analysis of the social network and node classification experiments illustrate that Twitch Gamers is suitable for assessing the predictive performance of novel proximity preserving and structural role-based  ...  ACKNOWLEDGEMENTS Benedek Rozemberczki was supported by the Centre for Doctoral Training in Data Science, funded by EPSRC (grant EP/L016427/1).  ... 
arXiv:2101.03091v2 fatcat:chizif4aynakrmaet3fpjt2mn4

Local Structure and High-Order Feature Preserved Network Embedding Based on Non-negative Matrix Factorization

Qin Tian, Lin Pan, Xuan Guo, Xiaoming Li, Wei Yu, Faming Li
2020 IEEE Access  
The methods based on matrix factorization by decomposing the adjacency matrix to learn node embedding could only capture the local structure of the network.  ...  learned from random walk algorithm and local structure proximity for node representations.  ... 
doi:10.1109/access.2020.3045532 fatcat:mdhslji6xzguhdnsamntcqshrq

Low-Bit Quantization for Attributed Network Representation Learning

Hong Yang, Shirui Pan, Ling Chen, Chuan Zhou, Peng Zhang
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
Specifically, we formulate a new representation learning function based on matrix factorization that can jointly learn the low-bit node representations and the layer aggregation weights under the low-bit  ...  To this end, we present a new Low-Bit Quantization for Attributed Network Representation Learning model (LQANR for short) that can learn compact node representations with low bitwidth values while preserving  ...  The achievement in low-rank matrix and tensor factorization based compression motivates to learn low-bit quantization for attributed network embedding based on matrix factorization.  ... 
doi:10.24963/ijcai.2019/562 dblp:conf/ijcai/YangP0Z019 fatcat:q4jwh3xq2fbd7fm2h7jnq3kcyi

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
In this survey, we conduct a literature review of recent developments and trends in applying graph embedding methods for biomedical data.  ...  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  ...  Generally, there are two types of matrix factorization to compute the node embedding, i.e., node proximity matrix and graph Laplacian eigenmaps.  ... 
arXiv:2101.06569v2 fatcat:vqfosu4o6neklfffpvpmmdor2q

Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding [article]

Jingya Zhou, Ling Liu, Wenqi Wei, Jianxi Fan
2021 arXiv   pre-print
Most of them focus on learning node embeddings for homogeneous networks, but they differ in the specific encoding schemes and specific types of node semantics captured and used for learning node embedding  ...  This survey paper reviews the design principles and the different node embedding techniques for network representation learning over homogeneous networks.  ...  Different embedding models can be leveraged to learn hidden features for node embedding, such as matrix factorization, probabilistic model, graph neural networks.  ... 
arXiv:2110.07582v1 fatcat:gbjn3evwwzf4xkeobrsfo6hope

Network Embedding Using Deep Robust Nonnegative Matrix Factorization

Chaobo He, Hai Liu, Yong Tang, Xiang Fei, Hanchao Li, Qiong Zhang
2020 IEEE Access  
Due to the virtues of better interpretability and flexibility, matrix factorization based methods for network embedding have received increasing attentions.  ...  Meanwhile, DRNMF employs the combination of high-order proximity matrices of the network as the original feature matrix for the factorization.  ...  NETWORK EMBEDDING BASED ON MATRIX FACTORIZATION Owing that our goal is to boost the performance of matrix factorization for network embedding, here we are only concerned about matrix factorization based  ... 
doi:10.1109/access.2020.2992269 fatcat:7pks5mspsrhotnpya54ve6nmjq

Associative Learning for Network Embedding [article]

Yuchen Liang, Dmitry Krotov, Mohammed J. Zaki
2022 arXiv   pre-print
The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.  ...  Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly.  ...  For node proximity matrix factorization, the goal is to minimize the loss of approximating the proximity matrix directly.  ... 
arXiv:2208.14376v1 fatcat:bph5ttfapzbwvdpwllyyuha24u

Spectral Network Embedding: A Fast and Scalable Method via Sparsity [article]

Jie Zhang and Yan Wang and Jie Tang and Ming Ding
2018 arXiv   pre-print
In Progle, we first construct a sparse proximity matrix and train the network embedding efficiently via sparse matrix decomposition.  ...  Network embedding aims to learn low-dimensional representations of nodes in a network, while the network structure and inherent properties are preserved.  ...  It is a matrix factorization spectral method, approximating high-order proximity based on factorizing the Katz matrix. Evaluation Methods.  ... 
arXiv:1806.02623v2 fatcat:gppkwgrerfeczlpgob2yj4gnga

Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding [article]

Jing Zhu, Xingyu Lu, Mark Heimann, Danai Koutra
2021 arXiv   pre-print
We present PhUSION, a proximity-based unified framework for computing structural and positional node embeddings, which leverages well-established methods for calculating node proximity scores.  ...  In a comprehensive empirical study with over 10 datasets, 4 tasks, and 35 methods, we systematically reveal successful design choices for node and graph-level machine learning with embeddings.  ...  For example, many proximity-preserving embedding methods were shown to implicitly factorize different proximity-based node similarity matrices; this insight inspired the NetMF method based on explicit  ... 
arXiv:2102.13582v1 fatcat:ds6sd22x6zbnrgz77op4n2wa3a

Graph embedding techniques, applications, and performance: A survey

Palash Goyal, Emilio Ferrara
2018 Knowledge-Based Systems  
We then present three categories of approaches based on factorization methods, random walks, and deep learning, with examples of representative algorithms in each category and analysis of their performance  ...  Recently, methods which use the representation of graph nodes in vector space have gained traction from the research community.  ...  Factorization based Methods Factorization based algorithms represent the connections between nodes in the form of a matrix and factorize this matrix to obtain the embedding.  ... 
doi:10.1016/j.knosys.2018.03.022 fatcat:wpud5byxxndllmhqdnhkljvcga

Multi-Scale attributed node embedding

Benedek Rozemberczki, Carl Allen, Rik Sarkar, xx Thilo Gross
2021 Journal of Complex Networks  
We prove theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings.  ...  We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to  ...  An embedding technique which contextualizes the nodes based on the proximity to other nodes cannot be inductive. • Non-linear: A node-node proximity score in the target matrix is not a linear function  ... 
doi:10.1093/comnet/cnab014 fatcat:gaseh5xrmvhwtcqsw6soq5mrb4

N odeS ig: Random Walk Diffusion meets Hashing for Scalable Graph Embeddings [article]

Abdulkadir Çelikkanat and Apostolos N. Papadopoulos and Fragkiskos D. Malliaros
2020 arXiv   pre-print
Learning node representations is a crucial task with a plethora of interdisciplinary applications.  ...  In particular, we propose N odeS ig, a scalable embedding model that computes binary node representations.  ...  . • HOPE [18] is a matrix factorization-based method aiming to capture high-order proximity among nodes.  ... 
arXiv:2010.00261v1 fatcat:rtaz7z33g5gjdmsvlasvvmbgwi
« Previous Showing results 1 — 15 out of 19,686 results