Internet Archive Scholar
Filters
























15,251 Hits in 7.3 sec

Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport [article]

Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso, Alain Rakotomamonjy
<span title="2021-04-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (774.1 kB)
https://web.archive.org/web/20201231042219/https://arxiv.org/pdf/2002.08314v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2002.08314v4.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-12-25">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v4">arXiv:2002.08314v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/665352znjjdi3kelrtiksntxai">fatcat:665352znjjdi3kelrtiksntxai</a> </span>

Other Versions

<span title="2020-10-16">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v3">arXiv:2002.08314v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/35eu2m73xrcd7kxk2cu55wdagi">fatcat:35eu2m73xrcd7kxk2cu55wdagi</a> </span>
<span title="2020-06-09">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v2">arXiv:2002.08314v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qszyq5zjwjdkrklehif6nftt7a">fatcat:qszyq5zjwjdkrklehif6nftt7a</a> </span>
<span title="2020-02-19">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v1">arXiv:2002.08314v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n2typw5nprhdpfv2s7au7pneta">fatcat:n2typw5nprhdpfv2s7au7pneta</a> </span>
and compute an optimal transport (OT) on the embedded distributions.  ...  Under some conditions, SERW is a distance that considers an OT distance of the (low-distorted) embedded distributions using a common metric.  ...  We consider two metric measure spaces (mm-space for short) (Gromov et al., 1999) is a compact metric space and µ is a probability measure with full support, i.e. µ(X) = 1 and supp[µ] = X.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v5">arXiv:2002.08314v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4j3y2en4mrb33dfmwzarnxgoe4">fatcat:4j3y2en4mrb33dfmwzarnxgoe4</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201231042219/https://arxiv.org/pdf/2002.08314v4.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/35/e1/35e1430521fe91acba754e15300a8a418048106a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.08314v5" 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>
Citation

Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso, Alain Rakotomamonjy. "Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport." arXiv (2021)

Gromov-Wasserstein Alignment of Word Embedding Spaces [article]

David Alvarez-Melis, Tommi S. Jaakkola
<span title="2018-08-31">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.3 MB)
https://web.archive.org/web/20200826115644/https://arxiv.org/pdf/1809.00013v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1809.00013v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper, we cast the correspondence problem directly as an optimal transport (OT) problem, building on the idea that word embeddings arise from metric recovery algorithms.  ...  Indeed, we exploit the Gromov-Wasserstein distance that measures how similarities between pairs of words relate across languages.  ...  The work was partially supported by MIT-IBM grant "Adversarial learning of multimodal and structured data", and Graduate Fellowships from Hewlett Packard and CONACYT.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.00013v1">arXiv:1809.00013v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4njieo6spjhc5ouft6rgxy3pfe">fatcat:4njieo6spjhc5ouft6rgxy3pfe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826115644/https://arxiv.org/pdf/1809.00013v1.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/34/d0/34d09f5b9107f6b14c7798ef2ea1f588121e29d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.00013v1" 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>
Citation

David Alvarez-Melis, Tommi S. Jaakkola. "Gromov-Wasserstein Alignment of Word Embedding Spaces." arXiv (2018)

Gromov-Wasserstein Alignment of Word Embedding Spaces

David Alvarez-Melis, Tommi Jaakkola
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.3 MB)
https://web.archive.org/web/20191203194924/https://www.aclweb.org/anthology/D18-1214.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://www.aclweb.org/anthology/D18-1214.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper, we cast the correspondence problem directly as an optimal transport (OT) problem, building on the idea that word embeddings arise from metric recovery algorithms.  ...  Indeed, we exploit the Gromov-Wasserstein distance that measures how similarities between pairs of words relate across languages.  ...  The work was partially supported by MIT-IBM grant "Adversarial learning of multimodal and structured data", and Graduate Fellowships from Hewlett Packard and CONACYT.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d18-1214">doi:10.18653/v1/d18-1214</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/Alvarez-MelisJ18.html">dblp:conf/emnlp/Alvarez-MelisJ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e2qsf2fwafaupg437ruygdtd54">fatcat:e2qsf2fwafaupg437ruygdtd54</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191203194924/https://www.aclweb.org/anthology/D18-1214.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/37/77/3777dae81535d0d922aa51ec6831451cc1ebd0cc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d18-1214"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

David Alvarez-Melis, Tommi Jaakkola. "Gromov-Wasserstein Alignment of Word Embedding Spaces." Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018) 1881-1890

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces [article]

David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola
<span title="2020-05-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20200512013338/https://arxiv.org/pdf/1911.02536v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1911.02536v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2019-11-06">2019</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.02536v1">arXiv:1911.02536v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/trppa2ogwnbmdo6lsfmov5k4ry">fatcat:trppa2ogwnbmdo6lsfmov5k4ry</a> </span>
We then propose a novel approach based on optimal transport over hyperbolic spaces, and show that it outperforms standard embedding alignment techniques in various experiments on cross-lingual WordNet  ...  alignment and ontology matching tasks.  ...  Acknowledgements The work was partially supported by the MIT-IBM project on adversarial learning of multi-modal and structured data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.02536v2">arXiv:1911.02536v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c5tqf2b4gfdylatnavtum7fx7q">fatcat:c5tqf2b4gfdylatnavtum7fx7q</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200512013338/https://arxiv.org/pdf/1911.02536v2.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/a8/a4/a8a4630ff1a2ebc3d2e8294281f731992299de00.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.02536v2" 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>
Citation

David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola. "Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces." arXiv (2020)

Few-Shot Action Recognition with Compromised Metric via Optimal Transport [article]

Su Lu, Han-Jia Ye, De-Chuan Zhan
<span title="2021-04-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.6 MB)
https://web.archive.org/web/20210414070026/https://arxiv.org/pdf/2104.03737v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2104.03737v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper, we propose Compromised Metric via Optimal Transport (CMOT) to combine the advantages of these two solutions.  ...  In detail, given two videos, we sample segments from them and cast the calculation of their distance as an optimal transport problem between two segment sequences.  ...  Optimal Transport The theory of optimal transport defines a geometry to compare measures supported on metric probability spaces [2] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.03737v1">arXiv:2104.03737v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7g7fmzbktnhxpe3x2gj2crnuom">fatcat:7g7fmzbktnhxpe3x2gj2crnuom</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414070026/https://arxiv.org/pdf/2104.03737v1.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/95/ee/95ee63fca1cacdbe8d14349baddc41cade26dc7b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.03737v1" 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>
Citation

Su Lu, Han-Jia Ye, De-Chuan Zhan. "Few-Shot Action Recognition with Compromised Metric via Optimal Transport." arXiv (2021)

Gromov-Wasserstein optimal transport to align single-cell multi-omics data [article]

Pinar Demetci, Rebecca Santorella, Bjorn Sandstede, William Stafford Noble, Ritambhara Singh
<span title="2020-04-29">2020</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.5 MB)
https://web.archive.org/web/20210428102114/https://www.biorxiv.org/content/biorxiv/early/2020/11/11/2020.04.28.066787.full.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://www.biorxiv.org/content/biorxiv/early/2020/11/11/2020.04.28.066787.full.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We present Single-Cell alignment using Optimal Transport (SCOT), an unsupervised learning algorithm that uses Gromov Wasserstein-based optimal transport to align single-cell multi-omics datasets.  ...  The optimization uses k-nearest neighbor graphs, thus preserving the local geometry of the data.  ...  Acknowledgments We are grateful to Yang Lu, Jean-Philippe Vert, and Marco Cuturi for helpful discussion of Gromov-Wasserstein optimal transport.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2020.04.28.066787">doi:10.1101/2020.04.28.066787</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fsogpf6isvg5hjkbxsxrfp5sx4">fatcat:fsogpf6isvg5hjkbxsxrfp5sx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428102114/https://www.biorxiv.org/content/biorxiv/early/2020/11/11/2020.04.28.066787.full.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/5c/6e/5c6ec03786eb9ee818e51338da6f77a622f5d9a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2020.04.28.066787"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>
Citation

Pinar Demetci, Rebecca Santorella, Bjorn Sandstede, William Stafford Noble, Ritambhara Singh. "Gromov-Wasserstein optimal transport to align single-cell multi-omics data." bioRxiv (2020)

Improving Cross-lingual Entity Alignment via Optimal Transport

Shichao Pei, Lu Yu, Xiangliang Zhang
<span title="">2019</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (514.7 kB)
https://web.archive.org/web/20200506223922/https://repository.kaust.edu.sa/bitstream/handle/10754/661838/3778_OTEA.pdf;jsessionid=6F86B49F6694BEE6597FEBF624E2B95C?sequence=1

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://repository.kaust.edu.sa/bitstream/handle/10754/661838/3778_OTEA.pdf;jsessionid=6F86B49F6694BEE6597FEBF624E2B95C?sequence=1">the original URL</a>. The file type is <code>application/pdf</code>.

We propose a novel entity alignment framework (OTEA), which dually optimizes the entity-level loss and group-level loss via optimal transport theory.  ...  However, the important duality of alignment between different KGs (X to Y by M1 and Y to X by M2) is ignored.  ...  Acknowledgments The research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST), under award number FCC/1/1976-19-01, and NSFC No. 61828302  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2019/448">doi:10.24963/ijcai.2019/448</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/Pei0Z19.html">dblp:conf/ijcai/Pei0Z19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/irbcsnygnvdqhisga26sqe6nni">fatcat:irbcsnygnvdqhisga26sqe6nni</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506223922/https://repository.kaust.edu.sa/bitstream/handle/10754/661838/3778_OTEA.pdf;jsessionid=6F86B49F6694BEE6597FEBF624E2B95C?sequence=1" 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/fc/20/fc204be436e189a82122e9f61eb0ec1ecc6dff35.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2019/448"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Shichao Pei, Lu Yu, Xiangliang Zhang. "Improving Cross-lingual Entity Alignment via Optimal Transport." Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (2019) 3231-3237

GOT: An Optimal Transport framework for Graph comparison [article]

Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia, Pascal Frossard
<span title="2019-12-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20200930173530/https://arxiv.org/pdf/1906.02085v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1906.02085v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2019-06-05">2019</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.02085v1">arXiv:1906.02085v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nsospof2dnbkve4kzjoic44xoi">fatcat:nsospof2dnbkve4kzjoic44xoi</a> </span>
Our measure is then used for formulating a new graph alignment problem, whose objective is to estimate the permutation that minimizes the distance between two graphs.  ...  We present a novel framework based on optimal transport for the challenging problem of comparing graphs.  ...  We use GOT to align graphs, and eventually use a simple non-parametric 1-NN classification algorithm to classify graphs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.02085v2">arXiv:1906.02085v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dl22pfzopvdtxaeugqgggz5sdm">fatcat:dl22pfzopvdtxaeugqgggz5sdm</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930173530/https://arxiv.org/pdf/1906.02085v2.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/e7/c2/e7c20203e5c0be51397815476aa7b0a3e9b5f8c8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.02085v2" 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>
Citation

Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia, Pascal Frossard. "GOT: An Optimal Transport framework for Graph comparison." arXiv (2019)

Evaluating Natural Language Generation via Unbalanced Optimal Transport

Yimeng Chen, Yanyan Lan, Ruinbin Xiong, Liang Pang, Zhiming Ma, Xueqi Cheng
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (371.8 kB)
https://web.archive.org/web/20201106212610/https://www.ijcai.org/Proceedings/2020/0512.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://www.ijcai.org/Proceedings/2020/0512.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In these measures, various intrinsic metrics are used in the computation, including generalized precision, recall, F-score and the earth mover's distance.  ...  Therefore we propose a family of new evaluation metrics, namely Lazy Earth Mover's Distances, based on the more general unbalanced optimal transport problem.  ...  Acknowledgments We thank the reviewers for their critical comments and we are grateful for funding support from NSERC and Mitacs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/512">doi:10.24963/ijcai.2020/512</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/LianJTPY20.html">dblp:conf/ijcai/LianJTPY20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5njowiz3jzbw7jfvyw2dgnmume">fatcat:5njowiz3jzbw7jfvyw2dgnmume</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201106212610/https://www.ijcai.org/Proceedings/2020/0512.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/40/d1/40d1b32a4304e0b3c74064c8982a075a5e179d24.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/512"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Yimeng Chen, Yanyan Lan, Ruinbin Xiong, Liang Pang, Zhiming Ma, Xueqi Cheng. "Evaluating Natural Language Generation via Unbalanced Optimal Transport." Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2020) 3702-3708

A Regularized Wasserstein Framework for Graph Kernels [article]

Asiri Wijesinghe, Qing Wang, Stephen Gould
<span title="2021-10-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (660.4 kB)
https://web.archive.org/web/20211012130427/https://arxiv.org/pdf/2110.02554v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2110.02554v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-10-06">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02554v1">arXiv:2110.02554v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bqwzu76v3zdonevmsi6fijd2qe">fatcat:bqwzu76v3zdonevmsi6fijd2qe</a> </span>
This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on  ...  We propose a learning framework for graph kernels, which is theoretically grounded on regularizing optimal transport.  ...  Acknowledgement: We gratefully acknowledge that the Titan Xp used for this research was donated by NVIDIA.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02554v2">arXiv:2110.02554v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kwmv2zqiijf35o2djfbzoi7c7i">fatcat:kwmv2zqiijf35o2djfbzoi7c7i</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211012130427/https://arxiv.org/pdf/2110.02554v2.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/4a/4a/4a4a29303177b3276c0c7329a4e217be4a4d6917.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02554v2" 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>
Citation

Asiri Wijesinghe, Qing Wang, Stephen Gould. "A Regularized Wasserstein Framework for Graph Kernels." arXiv (2021)

Regularized Wasserstein Means for Aligning Distributional Data

Liang Mi, Wen Zhang, Yalin Wang
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.6 MB)
https://web.archive.org/web/20201103163624/https://aaai.org/ojs/index.php/AAAI/article/download/5960/5816

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://aaai.org/ojs/index.php/AAAI/article/download/5960/5816">the original URL</a>. The file type is <code>application/pdf</code>.

Our formulation is based on the variational transportation to distribute a sparse discrete measure into the target domain.  ...  We propose to align distributional data from the perspective of Wasserstein means.  ...  Acknowledgements This work was supported in part by NIH (RF1AG051710 and R01EB025032). Liang Mi is supported in part by ASU Completion Fellowship.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.5960">doi:10.1609/aaai.v34i04.5960</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33868774">pmid:33868774</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8049602/">pmcid:PMC8049602</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uggwrx2hv5cvdnbfvjaj2ciluy">fatcat:uggwrx2hv5cvdnbfvjaj2ciluy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103163624/https://aaai.org/ojs/index.php/AAAI/article/download/5960/5816" 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/ed/ae/edae6ab02243af506235127d62a9dcd51ad42241.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.5960"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8049602" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>
Citation

Liang Mi, Wen Zhang, Yalin Wang. "Regularized Wasserstein Means for Aligning Distributional Data." PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE 34.04 (2020) 5166-5173

Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment [article]

Alex Gabourie, Mohammad Rostami, Philip Pope, Soheil Kolouri, Kyungnam Kim
<span title="2019-09-24">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.6 MB)
https://web.archive.org/web/20200922161017/https://arxiv.org/pdf/1907.02271v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1907.02271v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2019-07-04">2019</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.02271v1">arXiv:1907.02271v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wyyov6m5xfd4xdcwz5amtpzofe">fatcat:wyyov6m5xfd4xdcwz5amtpzofe</a> </span>
We use the output space of a shared cross-domain deep encoder to model the embedding space anduse the Sliced-Wasserstein Distance (SWD) to measure and minimize the distance between the embedded distributions  ...  We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target  ...  More importantly, the SWD is a good approximation for the optimal transport [2] which has gained interest in deep learning community as it is an effective distribution metric and its gradient is non-vanishing  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.02271v2">arXiv:1907.02271v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ct3ilhgenetlmtqncjylk5nxm">fatcat:2ct3ilhgenetlmtqncjylk5nxm</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200922161017/https://arxiv.org/pdf/1907.02271v2.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/c7/8e/c78e09448aa9e86c2d0f59b1a5dce56b4e185242.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.02271v2" 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>
Citation

Alex Gabourie, Mohammad Rostami, Philip Pope, Soheil Kolouri, Kyungnam Kim. "Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment." arXiv (2019)

Towards Fully 8-bit Integer Inference for the Transformer Model

Ye Lin, Yanyang Li, Tengbo Liu, Tong Xiao, Tongran Liu, Jingbo Zhu
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (153.9 kB)
https://web.archive.org/web/20201106230818/https://www.ijcai.org/Proceedings/2020/0516.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://www.ijcai.org/Proceedings/2020/0516.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

., Softmax in Transformer), and make heavy use of quantization and de-quantization.  ...  8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently.  ...  Since both BERTScore and YiSi-1 use generalized precision, recall and F-score as the intrinsic metrics, while WMD, WMDo and MoverScore all use earth mover's distance as the intrinsic metric, this section  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/516">doi:10.24963/ijcai.2020/516</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/ChenLXPMC20.html">dblp:conf/ijcai/ChenLXPMC20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/meqdgmlcg5e7vc2mcodlu5hnjy">fatcat:meqdgmlcg5e7vc2mcodlu5hnjy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201106230818/https://www.ijcai.org/Proceedings/2020/0516.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/e0/92/e092977936bca9ac9491740dced4d69de6576e96.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/516"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Ye Lin, Yanyang Li, Tengbo Liu, Tong Xiao, Tongran Liu, Jingbo Zhu. "Towards Fully 8-bit Integer Inference for the Transformer Model." Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2020) 3730-3736

Unsupervised integration of single-cell multi-omics datasets with disparities in cell-type representation [article]

Pinar Demetci, Rebecca Santorella, Bjorn Sandstede, Ritambhara Singh
<span title="2021-11-11">2021</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.3 MB)
https://web.archive.org/web/20220205050850/https://www.biorxiv.org/content/biorxiv/early/2021/11/11/2021.11.09.467903.full.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://www.biorxiv.org/content/biorxiv/early/2021/11/11/2021.11.09.467903.full.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Here, we improve our previous work Single Cell alignment using Optimal Transport (SCOT) by using unbalanced optimal transport to handle disproportionate cell-type representation and differing sample sizes  ...  across single-cell measurements.  ...  We thank Ievgen Redko, Ph.D. for useful discussions of optimal transport theory. Funding. Ritambhara Singh's contribution to the work is supported by NIH award 1R35HG011939-01.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2021.11.09.467903">doi:10.1101/2021.11.09.467903</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qopxeckxinh7nmx7dbb2xatwja">fatcat:qopxeckxinh7nmx7dbb2xatwja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220205050850/https://www.biorxiv.org/content/biorxiv/early/2021/11/11/2021.11.09.467903.full.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/3a/9e/3a9e9264f19ac9a3817562cadd09abdd38c854aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2021.11.09.467903"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>
Citation

Pinar Demetci, Rebecca Santorella, Bjorn Sandstede, Ritambhara Singh. "Unsupervised integration of single-cell multi-omics datasets with disparities in cell-type representation." bioRxiv (2021)

Correcting nuisance variation using Wasserstein distance

Gil Tabak, Minjie Fan, Samuel Yang, Stephan Hoyer, Geoffrey Davis
<span title="2020-02-28">2020</span> <i title="PeerJ"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/eyfkjqp7sva5bbnwatk5zazi7q" style="color: black;">PeerJ</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (18.3 MB)
https://web.archive.org/web/20200306065611/https://peerj.com/articles/8594.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://peerj.com/articles/8594.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To achieve this, we minimize a loss function based on distances between marginal distributions (such as the Wasserstein distance) of embeddings across domains for each replicated treatment.  ...  We find that for our transformed embeddings (i) the underlying geometric structure is not only preserved but the embeddings also carry improved biological signal; and (ii) less domain-specific information  ...  for useful discussions and suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7717/peerj.8594">doi:10.7717/peerj.8594</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32161688">pmid:32161688</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7050548/">pmcid:PMC7050548</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4225iniv4bex3ihklab5hu6u7y">fatcat:4225iniv4bex3ihklab5hu6u7y</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306065611/https://peerj.com/articles/8594.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/f1/37/f137966864e4ff5ecab583706bb82717c91c0bc1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7717/peerj.8594"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7050548" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>
Citation

Gil Tabak, Minjie Fan, Samuel Yang, Stephan Hoyer, Geoffrey Davis. "Correcting nuisance variation using Wasserstein distance." PeerJ (2020) e8594

&laquo; Previous Showing results 1 &mdash; 15 out of 15,251 results