Filters








109,652 Hits in 3.2 sec

Distance Metric Learning for Graph Structured Data [article]

Tomoki Yoshida, Ichiro Takeuchi, Masayuki Karasuyama
<span title="2020-02-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Graphs are versatile tools for representing structured data. Therefore, a variety of machine learning methods have been studied for graph data analysis.  ...  Hence, we propose a supervised distance metric learning method for the graph classification problem.  ...  Conclusions We proposed an interpretable metric learning method for graph data, named interpretable graph metric learning (IGML).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.00727v1">arXiv:2002.00727v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5wvlulx42nb6vfsj5stisrtamm">fatcat:5wvlulx42nb6vfsj5stisrtamm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321081550/https://arxiv.org/pdf/2002.00727v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.00727v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning an Integrated Distance Metric for Comparing Structure of Complex Networks [article]

Sadegh Aliakbary, Sadegh Motallebi, Jafar Habibi, Ali Movaghar
<span title="2013-07-13">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we employ distance metric learning algorithms in order to construct an integrated distance metric for comparing structural properties of complex networks.  ...  Graph comparison plays a major role in many network applications. We often need a similarity metric for comparing networks according to their structural properties.  ...  Acknowledgements The authors wish to thank Hossein Rahmani, Mehdi Jalili, Mahdieh Soleymani and Masoud Asadpour for helpful discussions and comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1307.3626v1">arXiv:1307.3626v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a4koykbi2jcnrg2uyrbu6vprou">fatcat:a4koykbi2jcnrg2uyrbu6vprou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829224009/https://arxiv.org/ftp/arxiv/papers/1307/1307.3626.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/10/97/109793bcd37fe5330a47917d0505fd1c3b9c199d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1307.3626v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Adaptive Graph Convolutional Neural Networks [article]

Ruoyu Li, Sheng Wang, Feiyun Zhu, Junzhou Huang
<span title="2018-01-10">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To efficiently learn the graph, a distance metric learning is proposed.  ...  The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training.  ...  As far as we know, the AGCN is the first graph CNN that accepts data of arbitrary graph structure and size.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.03226v1">arXiv:1801.03226v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2l46c3eqdbde5j7es6ngicn56e">fatcat:2l46c3eqdbde5j7es6ngicn56e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915111301/https://arxiv.org/pdf/1801.03226v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c0/cd/c0cda2d7be0c269dd23ccf5513b7fd26765c9595.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.03226v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Semi-supervised Learning of a Markovian Metric [chapter]

Avleen S. Bijral, Manuel E. Lladser, Gregory Grudic
<span title="2008-04-24">2008</span> <i title="Society for Industrial and Applied Mathematics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/viwc2ys5x5a47ogpdlftfzj5fm" style="color: black;">Proceedings of the 2008 SIAM International Conference on Data Mining</a> </i> &nbsp;
In this paper we present a Markov random walk based semi-supervised method for metric learning.  ...  Since existing metrics like Euclidean do not necessarily reflect the true structure (clusters or manifolds) in the data, it becomes imperative that an appropriate metric be somehow learned from training  ...  The problem we pose is, for a connected graph with adjacency matrix H that imposes a certain structure on the given data, to learn suitable Markovian transition probabilities on the edges based on the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611972788.42">doi:10.1137/1.9781611972788.42</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sdm/BijralLG08.html">dblp:conf/sdm/BijralLG08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cdy37jab6zfbpfmhlq6emarxd4">fatcat:cdy37jab6zfbpfmhlq6emarxd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20121018161214/http://siam.org/proceedings/datamining/2008/dm08_42_%20Bijral.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d3/d4/d3d40bc09a280a3edacb6aa5de7afbb77f4a59aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611972788.42"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs [article]

Hongwei Jin, Xun Chen
<span title="2022-02-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, structured data are widely distributed for different data mining and machine learning applications.  ...  Learning the similarity between structured data, especially the graphs, is one of the essential problems.  ...  Gromov-Wasserstein Discrepancy Graph neural networks rely on training on structured data for various graph-related tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.00808v1">arXiv:2202.00808v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ezkqbboyjre6hgrqgvkn55htyy">fatcat:ezkqbboyjre6hgrqgvkn55htyy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220204082038/https://arxiv.org/pdf/2202.00808v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6f/ca/6fca0510dd3902082a48f4aa92bf8f0c1401a8e8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.00808v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Relational Constraints for Metric Learning on Relational Data [article]

Jiajun Pan, Hoel Le Capitaine, Philippe Leray
<span title="2018-07-02">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Most of metric learning approaches are dedicated to be applied on data described by feature vectors, with some notable exceptions such as times series, trees or graphs.  ...  The proposed approach can take benefit from both the topological structure of the data and supervised labels.  ...  Such a distance is perfectly adapted for flat or iid data, but obviously fails to take into account complex and/or (semi-)structured, non-iid data without considering the structured information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00558v1">arXiv:1807.00558v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7twsoyt7gbhxpgoifziby7u7cm">fatcat:7twsoyt7gbhxpgoifziby7u7cm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914032834/https://arxiv.org/pdf/1807.00558v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e8/0f/e80f477200177f0058bebcc4bd170555f402f4e5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00558v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Metric learning with spectral graph convolutions on brain connectivity networks

Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert
<span title="">2018</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sa477uo7lveh7hchpikpixop5u" style="color: black;">NeuroImage</a> </i> &nbsp;
We propose to learn a graph similarity metric using a siamese graph convolutional neural network (s-GCN) in a supervised setting.  ...  Graph representations are often used to model structured data at an individual or population level and have numerous applications in pattern recognition problems.  ...  This indicates how challenging the problem of metric learning is for brain graphs, given that for certain acquisition sites the estimated distances for the matching graphs have a higher mean than the distances  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neuroimage.2017.12.052">doi:10.1016/j.neuroimage.2017.12.052</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29278772">pmid:29278772</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ihthm266gbclpcm3eqq3tu2zmm">fatcat:ihthm266gbclpcm3eqq3tu2zmm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190427100442/http://spiral.imperial.ac.uk/bitstream/10044/1/55600/2/ktena2017metric.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/08/6d/086db487bcad482a7790f589774ab4f31cca1279.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neuroimage.2017.12.052"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Learning Graph While Training: An Evolving Graph Convolutional Neural Network [article]

Ruoyu Li, Junzhou Huang
<span title="2017-08-10">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Under some circumstances, e.g. chemical molecular data, clustering or coarsening for simplifying the graphs is hard to be justified chemically.  ...  In this paper, we propose a more general and flexible graph convolution network (EGCN) fed by batch of arbitrarily shaped data together with their evolving graph Laplacians trained in supervised fashion  ...  O(f 2 k−1 ) is for the weights W k d in distance metric.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.04675v1">arXiv:1708.04675v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/afe2uopf6rhtvbrv57aiv2s7wy">fatcat:afe2uopf6rhtvbrv57aiv2s7wy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200725192339/https://arxiv.org/pdf/1708.04675v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/2f/ec2f95f7cdbfd81651b57217507f553131bdb688.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.04675v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Distance metric learning for complex networks: Towards size-independent comparison of network structures

Sadegh Aliakbary, Sadegh Motallebi, Sina Rashidian, Jafar Habibi, Ali Movaghar
<span title="">2015</span> <i title="AIP Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jh7idzebgzcuffjreetqux4374" style="color: black;">Chaos</a> </i> &nbsp;
The definition of an appropriate network distance metric is the base of many data-analysis and data-mining tasks including classification and clustering.  ...  Our proposed methodology includes a novel feature selection and feature weighting method for learning a network distance metric based on a genetic algorithm.  ...  ACKNOWLEDGEMENTS The authors wish to thank Hossein Rahmani, Mehdi Jalili, Mahdieh Soleymani and Masoud Asadpour for their constructive comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1063/1.4908605">doi:10.1063/1.4908605</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/25725647">pmid:25725647</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gcbyxjifvrfznermka4iqhhc64">fatcat:gcbyxjifvrfznermka4iqhhc64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808191425/http://sina.sharif.ac.ir/~movaghar/Chaos-Aliakbary-2015.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9f/f8/9ff87ba607f083da6c253998669a12f4a0003646.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1063/1.4908605"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Finding MNEMON: Reviving Memories of Node Embeddings [article]

Yun Shen and Yufei Han and Zhikun Zhang and Min Chen and Ting Yu and Michael Backes and Yang Zhang and Gianluca Stringhini
<span title="2022-04-29">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we fill this gap and propose a novel model-agnostic graph recovery attack that exploits the implicit graph structural information preserved in the embeddings of graph nodes.  ...  Little attention has been paid to understand the privacy risks of integrating the output from graph embedding models (e.g., node embeddings) with complex downstream machine learning pipelines.  ...  Acknowledgments We wish to thank the anonymous reviewers for their feedback and our shepherd Gergely Acs for his help in improving our paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.06963v2">arXiv:2204.06963v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wrz73p5g5rcq5ko7ab2ytabpky">fatcat:wrz73p5g5rcq5ko7ab2ytabpky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220503110827/https://arxiv.org/pdf/2204.06963v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d8/14/d8145f177e499fe494f6c83b39b082231e3602d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.06963v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multiple Metric Learning for Structured Data [article]

Nicolo Colombo
<span title="2020-02-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We address the problem of merging graph and feature-space information while learning a metric from structured data.  ...  The idea is that the input matrices can be pre-computed dissimilarity measures obtained from any kind of available data (e.g. node attributes or edge structure).  ...  Goal of this work is to present a new and general method for learning statistical models from graph-structured data sets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.05747v1">arXiv:2002.05747v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xlwofvcbyjdcvbzyxttaqdfmwa">fatcat:xlwofvcbyjdcvbzyxttaqdfmwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322221603/https://arxiv.org/pdf/2002.05747v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.05747v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks [article]

Jiaxiang Tang, Wei Hu, Xiang Gao, Zongming Guo
<span title="2019-09-11">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We deploy the Mahalanobis distance metric and further decompose the metric matrix into a low-dimensional matrix, which converts graph learning to the optimization of a low-dimensional matrix for efficient  ...  In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer.  ...  In particular, we optimize an underlying graph kernel from data features via distance metric learning that characterizes pairwise similarities of data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04931v1">arXiv:1909.04931v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uni3l77wwred7oeohyvhfandzi">fatcat:uni3l77wwred7oeohyvhfandzi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825190134/https://arxiv.org/pdf/1909.04931v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6f/8b/6f8b327b9c950daecf1ed36d03ca7708a9aa06bf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04931v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks [chapter]

Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert
<span title="">2017</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this work, we propose a novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory  ...  Experimental results on the ABIDE dataset show that our method can learn a graph similarity metric tailored for a clinical application, improving the performance of a simple k-nn classifier by 11.9% compared  ...  To the best of our knowledge, this is the first application of graph convolutional networks for distance metric learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-66182-7_54">doi:10.1007/978-3-319-66182-7_54</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ydvxdnwacjf5vdoa4dbnfavp7e">fatcat:ydvxdnwacjf5vdoa4dbnfavp7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190304120652/http://pdfs.semanticscholar.org/dbbe/f7c54b88ed4814954062d0922fbf0cc34b28.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/be/dbbef7c54b88ed4814954062d0922fbf0cc34b28.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-66182-7_54"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Representing Hierarchical Structure by Using Cone Embedding [article]

Daisuke Takehara, Kei Kobayashi
<span title="2022-05-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
geometrically and intuitively natural to interpret, and 2) we can extract the hierarchical structure from a graph embedding output of other methods by learning additional one-dimensional parameters.  ...  In particular, Poincar\'e embedding has been proposed to capture the hierarchical structure of graphs, and its effectiveness has been reported.  ...  In recent years, machine learning for graph-structured data has attracted significant attention.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.08014v2">arXiv:2102.08014v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ee2s7hhcfcqbaqi7qm22wcg5u">fatcat:6ee2s7hhcfcqbaqi7qm22wcg5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220512041047/https://arxiv.org/pdf/2102.08014v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/3f/e23fda3df0a550d093b65f7025012e92e726bbba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.08014v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Manifold Modeling with Learned Distance in Random Projection Space for Face Recognition

Grigorios Tsagkatakis, Andreas Savakis
<span title="">2010</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jsl2pgelqja2piczru3a6nqkg4" style="color: black;">2010 20th International Conference on Pattern Recognition</a> </i> &nbsp;
To address this impediment of manifold learning, we investigated the combination of manifold learning and distance metric learning for the generation of a representation that is both discriminative and  ...  Distance metric learning is then applied to increase the separation between classes and improve the accuracy of nearest neighbor classification.  ...  Distance Metric Learning Typically, the distance between input data is measured using the Euclidian distance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2010.165">doi:10.1109/icpr.2010.165</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icpr/TsagkatakisS10.html">dblp:conf/icpr/TsagkatakisS10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zlixruu6ijbl7bmd2lzqi2ijzu">fatcat:zlixruu6ijbl7bmd2lzqi2ijzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170705102314/http://www.cis.rit.edu/microgrants/2010/Tsagkatakis_report.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1f/49/1f491e4a9466d45d3904bdb266fb48687274bf76.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2010.165"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 109,652 results