Filters








5,993 Hits in 7.8 sec

Joint Learning of Hierarchical Community Structure and Node Representations: An Unsupervised Approach [article]

Ancy Sarah Tom, Nesreen K. Ahmed, George Karypis
2022 arXiv   pre-print
In this work, we present Mazi, an algorithm that jointly learns the hierarchical community structure and the node representations of the graph in an unsupervised fashion.  ...  However, these approaches do not take advantage of the learned representations to also improve the quality of the discovered communities and establish an iterative and joint optimization of representation  ...  We present Mazi 1 , an algorithm that performs a joint unsupervised learning of the hierarchical community structure of a graph and the representations of its nodes.  ... 
arXiv:2201.09086v1 fatcat:6pxata2kcjhlfa6qql5xmqqvui

An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS [article]

Chao Liu, Sambuddha Ghosal, Zhanhong Jiang, Soumik Sarkar
2016 arXiv   pre-print
nominal modes with one graphical model; (3) the case studies with simulated data and an integrated building system validate the proposed approach.  ...  The framework is based on a spatiotemporal feature extraction scheme built on the concept of symbolic dynamics for discovering and representing causal interactions among the subsystems of a CPS.  ...  Mike Wassmer (Live to Zero Inc.) for their support in the validation process using real data, and for providing access to their historic data collected as part of the building science plank research of  ... 
arXiv:1512.07876v2 fatcat:th4z4imwvzbg3guqjnl75bqrcm

Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization [article]

Sambaran Bandyopadhyay, Manasvi Aggarwal, M. Narasimha Murty
2020 arXiv   pre-print
Thus, we aim to propose an unsupervised graph neural network to generate a vector representation of an entire graph in this paper.  ...  Invent of graph neural networks has improved the state-of-the-art for both node and the entire graph representation in a vector space.  ...  We use both the link structure and the node attributes of the graphs to obtain their final representations in an unsupervised way.  ... 
arXiv:2006.04696v1 fatcat:ihbpx22jfvhx5pzhajeznyytyq

Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation

Sebastijan Dumancic, Hendrik Blockeel
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
In this work we introduce an approach for relational unsupervised representation learning.  ...  The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier.  ...  Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2017/226 dblp:conf/ijcai/DumancicB17 fatcat:jxrvvyybhjgkbit5uu52xkfoxa

Network Representation [chapter]

Zhiyuan Liu, Yankai Lin, Maosong Sun
2020 Representation Learning for Natural Language Processing  
Finally, we will introduce some common evaluation tasks of network representation learning and relevant datasets.  ...  The representations can be used as the feature of vertices and applied to many network study tasks. In this chapter, we will introduce network representation learning algorithms in the past decade.  ...  Thus, the exploration of the neural network approach on representation learning is becoming an emerging task.  ... 
doi:10.1007/978-981-15-5573-2_8 fatcat:2fljfkgpozhudbgqr7tgv45vxi

Graph Representation Learning for Road Type Classification

Zahra Gharaee, Shreyas Kowshik, Oliver Stromann, Michael Felsberg
2021 Pattern Recognition  
We compare the performance of learning representations using different types of neighborhood aggregation functions in transductive and inductive tasks and in supervised and unsupervised learning.  ...  We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks.  ...  Using recent graph representation learning approaches such as GraphSAGE [27] , GAT [21] , GaAN [41] , and GIN [42] , a node learns representation by aggregating the information of nodes sampled from  ... 
doi:10.1016/j.patcog.2021.108174 fatcat:funo4akd45f2xmf3ro6m6vl4xu

A Comparative Study for Unsupervised Network Representation Learning [article]

Megha Khosla and Vinay Setty and Avishek Anand
2019 arXiv   pre-print
There has been appreciable progress in unsupervised network representation learning (UNRL) approaches over graphs recently with flexible random-walk approaches, new optimization objectives and deep architectures  ...  In particular, we argue that most of the UNRL approaches either explicitly or implicit model and exploit context information of a node.  ...  Instead, we follow the recommendations of the authors and explore the learning rate in 0.001, 0.0001, 0.00002 [?, ?]. For GraphSAGE, in [?]  ... 
arXiv:1903.07902v4 fatcat:3w4mkk7z4zdwri2g4mr7hhhcd4

Fairness-Aware Node Representation Learning [article]

Öykü Deniz Köse, Yanning Shen
2021 arXiv   pre-print
Particularly, recent developments in contrastive learning have led to promising results in unsupervised node representation learning for a number of tasks.  ...  Node representation learning has demonstrated its effectiveness for various applications on graphs.  ...  Training a node representation learning model with such graphs may result in an intrinsic utilization of the sensitive attributes.  ... 
arXiv:2106.05391v1 fatcat:gbzvlecaeresdjn52ec3osvdwe

Network Representation Learning: A Survey [article]

Daokun Zhang, Jie Yin, Xingquan Zhu, Chengqi Zhang
2018 arXiv   pre-print
Analyzing these networks sheds light on different aspects of social life such as the structure of societies, information diffusion, and communication patterns.  ...  In this survey, we perform a comprehensive review of the current literature on network representation learning in the data mining and machine learning field.  ...  structure, and unsupervised content augmented methods that incorporate vertex attributes and network structure to learn joint vertex embeddings.  ... 
arXiv:1801.05852v3 fatcat:ploedafa4jhyxlvii5l42yw2bq

Network representation learning method embedding linear and nonlinear network structures

Hu Zhang, Jingjing Zhou, Ru Li, Yue Fan, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
2022 Semantic Web Journal  
Thus, the nodal characteristics of nonlinear and linear structures are explored in this paper, and an unsupervised representation method based on HGCN that joins learning of shallow and deep models is  ...  The former one can be used to capture the linear structure of the network using depth-first search (DFS) and width-first search (BFS), whereas Hierarchical GCN (HGCN) is an unsupervised graph embedding  ...  In order to overcome these limitations, we explore the nodal characteristics of network structures and improve the HGCN model, and a representation method based on unsupervised joint learning with shallow  ... 
doi:10.3233/sw-212968 fatcat:trmtlpbqp5dvha7mniks3yqn44

Unsupervised learning of hierarchical representations with convolutional deep belief networks

Honglak Lee, Roger Grosse, Rajesh Ranganath, Andrew Y. Ng
2011 Communications of the ACM  
Key to our approach is probabilistic max-pooling, a novel technique that shrinks the representations of higher layers in a probabilistically sound way. our experiments show that the algorithm learns useful  ...  o C To b E r 2 0 1 1 | vo L. 5 4 | N o. 1 0 | c o m m u n i c at i o n s o f t he acm 95 abstract There has been much interest in unsupervised learning of hierarchical generative models such as deep belief  ...  hierarchical probabilistic inference Once the parameters have all been learned, we compute the network's representation of an image by sampling from the joint distribution over all of the hidden layers  ... 
doi:10.1145/2001269.2001295 fatcat:7xq545joifaqxo7wxfxkm4redu

Learning Representations for Text-level Discourse Parsing

Gregor Weiss
2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop  
To train more expressive representations that capture communicative functions and semantic roles of discourse units and relations between them, we will jointly learn all discourse parsing subtasks at different  ...  By combining unsupervised training of word embeddings with our layer-wise multi-task learning of higher representations we hope to reach or even surpass performance of current state-of-the-art methods  ...  In order to automatically build a hierarchical structure of a text, first approaches (Marcu, 2000) relied mainly on discourse markers, hand-engineered rules, and heuristics.  ... 
doi:10.3115/v1/p15-3003 dblp:conf/acl/Weiss15 fatcat:lgoso2wbpvaujopgrguwzrsedi

Network representation learning: models, methods and applications

Anuraj Mohan, K. V. Pramod
2019 SN Applied Sciences  
A significant amount of research effort is made in the past few years to generate node representations from graph-structured data using representation learning methods.  ...  Generating an efficient network representation is one important challenge in applying machine learning to network data.  ...  Acknowledgements The authors would like to thank the management and staff of Department of Computer Applications, CUSAT, India and NSS College of Engineering, Palakkad, India for providing enough materials  ... 
doi:10.1007/s42452-019-1044-9 fatcat:zvlbj4qozzfw3dxoyevb6wgska

Graph Representation Learning: A Survey [article]

Fenxiao Chen, Yuncheng Wang, Bin Wang, C.-C. Jay Kuo
2019 arXiv   pre-print
Research on graph representation learning has received a lot of attention in recent years since many data in real-world applications come in form of graphs.  ...  Then, we evaluate several state-of-the-art methods against small and large datasets and compare their performance. Finally, potential applications and future directions are presented.  ...  It uses Skip-Gram and hierarchical Softmax to learn a distributed word representation.  ... 
arXiv:1909.00958v1 fatcat:6wbxy5jjx5ditbiiviwbuqyww4

Deep Representation Learning for Social Network Analysis

Qiaoyu Tan, Ninghao Liu, Xia Hu
2019 Frontiers in Big Data  
First, we introduce the basic models for learning node representations in homogeneous networks.  ...  We then introduce techniques for embedding subgraphs and also present the applications of network representation learning. Finally, we discuss some promising research directions for future work.  ...  We then provide an overview of the approaches that learn representations for subgraphs in networks, which to some extent rely on the techniques of node representation learning.  ... 
doi:10.3389/fdata.2019.00002 pmid:33693325 pmcid:PMC7931936 fatcat:w7kfbniaf5ctzp3swdttp52h3m
« Previous Showing results 1 — 15 out of 5,993 results