Internet Archive Scholar
Filters
























60 Hits in 4.7 sec

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks [article]

Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe
<span title="2021-11-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (373.7 kB)
https://web.archive.org/web/20200321031026/https://arxiv.org/pdf/1810.02244v3.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/1810.02244v3.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="2020-02-14">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v3">arXiv:1810.02244v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qjncvxpfufaedcpeki3lgoe2n4">fatcat:qjncvxpfufaedcpeki3lgoe2n4</a> </span>

Other Versions

<span title="2021-11-23">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v4">arXiv:1810.02244v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bw6nssiuvvb5pkmrki5k7dy36q">fatcat:bw6nssiuvvb5pkmrki5k7dy36q</a> </span>
<span title="2018-11-16">2018</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v2">arXiv:1810.02244v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pfoyfmt3erdlzixn3cjp7omvji">fatcat:pfoyfmt3erdlzixn3cjp7omvji</a> </span>
<span title="2018-10-04">2018</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v1">arXiv:1810.02244v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uwzqot4erve6lnu7gh5rbon2ni">fatcat:uwzqot4erve6lnu7gh5rbon2ni</a> </span>
These higher-order structures play an essential role in the characterization of social networks and molecule graphs.  ...  In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion.  ...  Analysis, projects A6 and B2.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v5">arXiv:1810.02244v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jod7duiubfa7nc5bgiwhpukhpm">fatcat:jod7duiubfa7nc5bgiwhpukhpm</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321031026/https://arxiv.org/pdf/1810.02244v3.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02244v5" 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

Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe. "Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks." arXiv (2021)

Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks

Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe
<span title="2019-07-17">2019</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 (342.0 kB)
https://web.archive.org/web/20200306093248/https://aaai.org/ojs/index.php/AAAI/article/download/4384/4262

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/4384/4262">the original URL</a>. The file type is <code>application/pdf</code>.

These higher-order structures play an essential role in the characterization of social networks and molecule graphs.  ...  In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion.  ...  Analysis, projects A6 and B2.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33014602">doi:10.1609/aaai.v33i01.33014602</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3ml3ojoi4rekddw2dy4mgvgxjq">fatcat:3ml3ojoi4rekddw2dy4mgvgxjq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306093248/https://aaai.org/ojs/index.php/AAAI/article/download/4384/4262" 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/2b/32/2b3283a526b73701f897d78cd399f663593a5294.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33014602"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe. "Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks." PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (2019) 4602-4609

Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings [article]

Or Feldman, Amit Boyarski, Shai Feldman, Dani Kogan, Avi Mendelson, Chaim Baskin
<span title="2022-03-02">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (949.8 kB)
https://web.archive.org/web/20220519143814/https://arxiv.org/pdf/2201.13410v2.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://arxiv.org/pdf/2201.13410v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2022-01-31">2022</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.13410v1">arXiv:2201.13410v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vin47qwpznae3c5dvhefeon5wu">fatcat:vin47qwpznae3c5dvhefeon5wu</a> </span>
This drawback hinders the applicability of Message Passing Graph Neural Networks (MPGNNs), whose expressive power is upper bounded by the WL test.  ...  Two popular alternatives that offer a good trade-off between expressive power and computational efficiency are combinatorial (i.e., obtained via the Weisfeiler-Leman (WL) test) and spectral invariants.  ...  Acknowledgements This research was partially supported by the Technion Hiroshi Fujiwara Cyber Security Research Center and the Israel National Cyber Directorate.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.13410v2">arXiv:2201.13410v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nqvzk544szd4zhpdtikavrkj3a">fatcat:nqvzk544szd4zhpdtikavrkj3a</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220519143814/https://arxiv.org/pdf/2201.13410v2.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/21/1a/211af952734e053c01cae09f8f0aaca3b1564bf1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.13410v2" 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

Or Feldman, Amit Boyarski, Shai Feldman, Dani Kogan, Avi Mendelson, Chaim Baskin. "Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings." arXiv (2022)

Weisfeiler and Leman go Machine Learning: The Story so far [article]

Christopher Morris, Yaron Lipman, Haggai Maron, Bastian Rieck, Nils M. Kriege, Martin Grohe, Matthias Fey, Karsten Borgwardt
<span title="2021-12-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.0 MB)
https://web.archive.org/web/20211228181152/https://arxiv.org/pdf/2112.09992v1.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/2112.09992v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for machine learning with  ...  graphs and relational data.  ...  Kriege is funded by the Vienna Science and Technology Fund (WWTF) through project VRG19-009.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.09992v1">arXiv:2112.09992v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r5ahhxsvhrbotfi6grerkzxuui">fatcat:r5ahhxsvhrbotfi6grerkzxuui</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211228181152/https://arxiv.org/pdf/2112.09992v1.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/88/9a/889a7041ca9df0fa3eb6b59cac52114d662eba22.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.09992v1" 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

Christopher Morris, Yaron Lipman, Haggai Maron, Bastian Rieck, Nils M. Kriege, Martin Grohe, Matthias Fey, Karsten Borgwardt. "Weisfeiler and Leman go Machine Learning: The Story so far." arXiv (2021)

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results [article]

Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka
<span title="2021-10-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (498.1 kB)
https://web.archive.org/web/20211014233102/https://arxiv.org/pdf/2012.03174v2.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/2012.03174v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2020-12-06">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.03174v1">arXiv:2012.03174v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ksxmatdqqverjnnxyohczjbhkm">fatcat:ksxmatdqqverjnnxyohczjbhkm</a> </span>
While message passing Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power.  ...  In response, several higher-order GNNs have been proposed that substantially increase the expressive power, albeit at a large computational cost.  ...  Higher-order networks use an encoding of k-tuples and then apply message passing [10] , or equivariant tensor operations [18] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.03174v2">arXiv:2012.03174v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hdko7yf7g5af3krmyoj72ovfxm">fatcat:hdko7yf7g5af3krmyoj72ovfxm</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211014233102/https://arxiv.org/pdf/2012.03174v2.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/0b/4b/0b4b499e970532bbfa61cf2d8ebbd06a697807ae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.03174v2" 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

Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka. "Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results." arXiv (2021)

The Logic of Graph Neural Networks [article]

Martin Grohe
<span title="2022-01-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (361.0 kB)
https://web.archive.org/web/20220112002408/https://arxiv.org/pdf/2104.14624v2.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://arxiv.org/pdf/2104.14624v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-04-29">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.14624v1">arXiv:2104.14624v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zuisk6lez5hxjefkgrpadhtaoi">fatcat:zuisk6lez5hxjefkgrpadhtaoi</a> </span>
Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs.  ...  It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms and by finite variable counting logics.  ...  WEISFEILER AND LEMAN GO NEURAL In this section, we shall prove that GNNs have exactly the same expressiveness as colour refinement when it comes to distinguishing graphs or their vertices.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.14624v2">arXiv:2104.14624v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pkq6yfm53bfwxjznoxeegchzwi">fatcat:pkq6yfm53bfwxjznoxeegchzwi</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112002408/https://arxiv.org/pdf/2104.14624v2.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/dc/08/dc08220b483bcbe72f09d342cf20bfc739ed540a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.14624v2" 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

Martin Grohe. "The Logic of Graph Neural Networks." arXiv (2022)

Local Permutation Equivariance For Graph Neural Networks [article]

Joshua Mitton, Roderick Murray-Smith
<span title="2022-02-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (483.0 kB)
https://web.archive.org/web/20220209083638/https://arxiv.org/pdf/2111.11840v2.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://arxiv.org/pdf/2111.11840v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-11-23">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.11840v1">arXiv:2111.11840v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ieqwpuyjfbedroni24jvb5tbqu">fatcat:ieqwpuyjfbedroni24jvb5tbqu</a> </span>
In this work we develop a new method, named Sub-graph Permutation Equivariant Networks (SPEN), which provides a framework for building graph neural networks that operate on sub-graphs, while using permutation  ...  Message passing neural networks have been shown to be limited in their expressive power and recent approaches to over come this either lack scalability or require structural information to be encoded into  ...  Roderick Murray-Smith is grateful for EPSRC support through grants EP/R018634/1 and EP/T00097X/1.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.11840v2">arXiv:2111.11840v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6xaou6m2kvdi7mp62o4uxrryia">fatcat:6xaou6m2kvdi7mp62o4uxrryia</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220209083638/https://arxiv.org/pdf/2111.11840v2.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/2111.11840v2" 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

Joshua Mitton, Roderick Murray-Smith. "Local Permutation Equivariance For Graph Neural Networks." arXiv (2022)

The Impact of Global Structural Information in Graph Neural Networks Applications [article]

Davide Buffelli, Fabio Vandin
<span title="2021-12-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (567.1 kB)
https://web.archive.org/web/20211217040716/https://arxiv.org/pdf/2006.03814v2.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/2006.03814v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2020-06-06">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.03814v1">arXiv:2006.03814v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yokzsftprfgk7n32weswudmyou">fatcat:yokzsftprfgk7n32weswudmyou</a> </span>
Graph Neural Networks (GNNs) rely on the graph structure to define an aggregation strategy where each node updates its representation by combining information from its neighbours.  ...  Therefore, practical GNN models employ few layers and only leverage the graph structure in terms of limited, small neighbourhoods around each node.  ...  Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks. AAAI, 2019. 10. Page, L.; Brin, S.; Motwani, R.; Winograd, T. The PageRank citation ranking: Bringing order to the Web.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.03814v2">arXiv:2006.03814v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xxm7fqiwtvbrjjxl5yoxctvs5q">fatcat:xxm7fqiwtvbrjjxl5yoxctvs5q</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211217040716/https://arxiv.org/pdf/2006.03814v2.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/25/7a/257a2e6730674c19be98780f4c58f8f7371baf4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.03814v2" 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

Davide Buffelli, Fabio Vandin. "The Impact of Global Structural Information in Graph Neural Networks Applications." arXiv (2021)

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting [article]

Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein
<span title="2021-07-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.8 MB)
https://web.archive.org/web/20210709075049/https://arxiv.org/pdf/2006.09252v3.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/2006.09252v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-01-05">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09252v2">arXiv:2006.09252v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bwqkaawst5e7pd5mhjicvcpqna">fatcat:bwqkaawst5e7pd5mhjicvcpqna</a> </span>
<span title="2020-06-16">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09252v1">arXiv:2006.09252v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6dio6bixejfrbh4uwcedjjdgne">fatcat:6dio6bixejfrbh4uwcedjjdgne</a> </span>
It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Leman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and  ...  While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying  ...  Acknowledgements This research was partially supported by the ERC Consolidator Grant No. 724228 -LEMAN (GB and MB).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09252v3">arXiv:2006.09252v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2a3zatznsvdkjkan4fm2zqtute">fatcat:2a3zatznsvdkjkan4fm2zqtute</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210709075049/https://arxiv.org/pdf/2006.09252v3.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/65/95/659597b1699ba5b73da9a8628bf7e4ad9bebd242.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09252v3" 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

Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein. "Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting." arXiv (2021)

k-hop Graph Neural Networks [article]

Giannis Nikolentzos, George Dasoulas, Michalis Vazirgiannis
<span title="2020-08-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (600.1 kB)
https://web.archive.org/web/20201011225021/https://arxiv.org/pdf/1907.06051v2.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/1907.06051v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2019-07-13">2019</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.06051v1">arXiv:1907.06051v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/45s35gxf5jhbxens6bnzha6yoa">fatcat:45s35gxf5jhbxens6bnzha6yoa</a> </span>
Graph neural networks (GNNs) have emerged recently as a powerful architecture for learning node and graph representations.  ...  Standard GNNs have the same expressive power as the Weisfeiler-Leman test of graph isomorphism in terms of distinguishing non-isomorphic graphs.  ...  k-hop Graph Neural Networks In this section, we propose a generalization of GNNs, so-called k-hop Graph Neural Networks (k-hop GNNs).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.06051v2">arXiv:1907.06051v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7aj3dn5wljdghf72eja6whpnga">fatcat:7aj3dn5wljdghf72eja6whpnga</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201011225021/https://arxiv.org/pdf/1907.06051v2.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/40/14/4014419a430722dfb9e2c899355131ef6af5aaad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.06051v2" 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

Giannis Nikolentzos, George Dasoulas, Michalis Vazirgiannis. "k-hop Graph Neural Networks." arXiv (2020)

The Surprising Power of Graph Neural Networks with Random Node Initialization [article]

Ralph Abboud, İsmail İlkan Ceylan, Martin Grohe, Thomas Lukasiewicz
<span title="2021-06-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (445.5 kB)
https://web.archive.org/web/20210614104941/https://arxiv.org/pdf/2010.01179v2.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/2010.01179v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2020-10-02">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01179v1">arXiv:2010.01179v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fk2zhpwycvh5nkassrwca7o7lm">fatcat:fk2zhpwycvh5nkassrwca7o7lm</a> </span>
Graph neural networks (GNNs) are effective models for representation learning on relational data.  ...  However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman graph isomorphism heuristic.  ...  Acknowledgments This work was supported by the Alan Turing Institute under the UK EPSRC grant EP/N510129/1, by the AXA Research Fund, and by the EPSRC grants EP/R013667/1 and EP/M025268/1.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01179v2">arXiv:2010.01179v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qpi7idrhdbbc5ialjwllvgxwbi">fatcat:qpi7idrhdbbc5ialjwllvgxwbi</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210614104941/https://arxiv.org/pdf/2010.01179v2.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/aa/1c/aa1cda29362b9d670d602c7fc6964499d2a364bd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01179v2" 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

Ralph Abboud, İsmail İlkan Ceylan, Martin Grohe, Thomas Lukasiewicz. "The Surprising Power of Graph Neural Networks with Random Node Initialization." arXiv (2021)

On Graph Neural Networks versus Graph-Augmented MLPs [article]

Lei Chen, Zhengdao Chen, Joan Bruna
<span title="2020-12-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (743.2 kB)
https://web.archive.org/web/20201205201545/https://arxiv.org/pdf/2010.15116v2.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/2010.15116v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2020-10-28">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.15116v1">arXiv:2010.15116v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ccycf6tapnb2xi7fdudk2cuu7e">fatcat:ccycf6tapnb2xi7fdudk2cuu7e</a> </span>
From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which  ...  first augments node features with certain multi-hop operators on the graph and then applies an MLP in a node-wise fashion.  ...  Bronstein and Shunwang Gong for helpful conversations. This work is partially supported by the Alfred P.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.15116v2">arXiv:2010.15116v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zdiirbcuevhrvkei6kpakuaro4">fatcat:zdiirbcuevhrvkei6kpakuaro4</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201205201545/https://arxiv.org/pdf/2010.15116v2.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/31/2d/312d516a09d6cfed72b6c9f650f043898d73f9d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.15116v2" 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

Lei Chen, Zhengdao Chen, Joan Bruna. "On Graph Neural Networks versus Graph-Augmented MLPs." arXiv (2020)

RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs [article]

Anahita Iravanizad, Edgar Ivan Sanchez Medina, Martin Stoll
<span title="2021-10-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (415.9 kB)
https://web.archive.org/web/20211007161359/https://arxiv.org/pdf/2109.07555v3.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/2109.07555v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-09-26">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07555v2">arXiv:2109.07555v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ddt5fkmscnfovfnwi3wiblvh7m">fatcat:ddt5fkmscnfovfnwi3wiblvh7m</a> </span>
<span title="2021-09-15">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07555v1">arXiv:2109.07555v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wu2m46vsfzfirkgp6gj2jiwwxa">fatcat:wu2m46vsfzfirkgp6gj2jiwwxa</a> </span>
In recent years, graph neural networks (GNNs) have gained increasing popularity and have shown very promising results for data that are represented by graphs.  ...  Namely, (regular) walks of length 1 and 2, and a fractional walk of length γ∈ (0,1), in order to capture the different local and global dynamics on the graphs.  ...  They defined a local and global neighborhood for their introduced higher dimensional graph, which is based on higher order Weisfeiler-Leman graph isomorphisms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07555v3">arXiv:2109.07555v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xnx5yerrcnbe5kuxw5gzbzf6sq">fatcat:xnx5yerrcnbe5kuxw5gzbzf6sq</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007161359/https://arxiv.org/pdf/2109.07555v3.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/ff/4a/ff4ab2b1addc6f81e9d5fd93a8177b16dd238526.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07555v3" 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

Anahita Iravanizad, Edgar Ivan Sanchez Medina, Martin Stoll. "RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs." arXiv (2021)

Efficient Colon Cancer Grading with Graph Neural Networks [article]

Franziska Lippoldt
<span title="2020-10-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (512.1 kB)
https://web.archive.org/web/20201009140614/https://arxiv.org/pdf/2010.01091v1.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/2010.01091v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

The graph neural network itself consists of three convolutional blocks and linear layers, which is a rather simple design compared to other networks for this application.  ...  Further, the graph size in terms of nodes becomes stable with respect to the model's prediction and accuracy for sufficiently large models.  ...  References Ruqayya Awan, Korsuk Sirinukunwattana, David Epstein, Samuel Jefferyes, Uvais Qidwai, Zia Aftab, Imaad Mujeeb, David Snead, and Nasir Rajpoot.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01091v1">arXiv:2010.01091v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hq72sxdh7ravpmzby7777cqvbq">fatcat:hq72sxdh7ravpmzby7777cqvbq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201009140614/https://arxiv.org/pdf/2010.01091v1.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/2010.01091v1" 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

Franziska Lippoldt. "Efficient Colon Cancer Grading with Graph Neural Networks." arXiv (2020)

Graph Neural Networks: Taxonomy, Advances and Trends [article]

Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, Jumin Zhao
<span title="2022-01-21">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20201218041422/https://arxiv.org/pdf/2012.08752v1.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/2012.08752v1.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="2020-12-16">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08752v1">arXiv:2012.08752v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z3egbzaeeffy5p7j3hcghyqs6y">fatcat:z3egbzaeeffy5p7j3hcghyqs6y</a> </span>

Other Versions

<span title="2021-01-18">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08752v2">arXiv:2012.08752v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bowq2ca45nd4nh47yh3josavje">fatcat:bowq2ca45nd4nh47yh3josavje</a> </span>
<span title="2022-02-25">2022</span> <span class="release-stage">accepted</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08752v4">arXiv:2012.08752v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/up4ick25wfdcrhvt5tghuyy5nq">fatcat:up4ick25wfdcrhvt5tghuyy5nq</a> </span>
In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the facing challenges.  ...  First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 400 relevant literatures to show the panorama of the graph neural networks.  ...  Specifically, they take higher-order graph structures at multiple scales into consideration by leveraging the k-Weisfeiler-Leman (k-WL) graph isomorphism test so that the message passing is performed directly  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08752v3">arXiv:2012.08752v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xj2kambrabfj3g5ldenfyixzu4">fatcat:xj2kambrabfj3g5ldenfyixzu4</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201218041422/https://arxiv.org/pdf/2012.08752v1.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/35/57/35575c637ded972de5f857280c9f64eb69553fbf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08752v3" 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

Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, Jumin Zhao. "Graph Neural Networks: Taxonomy, Advances and Trends." arXiv (2022)

&laquo; Previous Showing results 1 &mdash; 15 out of 60 results