Filters








31,723 Hits in 4.7 sec

Theoretically Expressive and Edge-aware Graph Learning [article]

Federico Errica, Davide Bacciu, Alessio Micheli
<span title="2020-01-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and  ...  deal with arbitrary edge values.  ...  Conclusions We have proposed a new architecture for GNNs that combines the inductive bias of the theoretically expressive Graph Isomorphism Network and the recurrent mechanism of the Gated Graph Neural  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.09005v1">arXiv:2001.09005v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4rc4rjkyjbb4heshczkkfbcr6i">fatcat:4rc4rjkyjbb4heshczkkfbcr6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321080048/https://arxiv.org/pdf/2001.09005v1.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/2001.09005v1" 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 Candidate Generation for Scalable Edge-discovery Tasks on Data Graphs [article]

Mayank Kejriwal
<span title="2017-07-01">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Despite the promise of these schemes, a formalism or learning framework has not been developed for them when input data instances are generic, attributed graphs possessing both node and edge heterogeneity  ...  This paper presents a graph-theoretic formalism for DNF schemes, and investigates their learnability in an optimization framework.  ...  Miranker, and the fruitful discussions that ultimately led to the writing of the paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00686v2">arXiv:1605.00686v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/26hztmjlejc3ri73rgu5y7aopy">fatcat:26hztmjlejc3ri73rgu5y7aopy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907075401/https://arxiv.org/pdf/1605.00686v2.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/d5/5a/d55af28558a26ae7caaee54cf7a581a110534c0a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00686v2" 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>

Automorphic Equivalence-aware Graph Neural Network [article]

Fengli Xu, Quanming Yao, Pan Hui, Yong Li
<span title="2021-11-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, we theoretically prove that GRAPE is expressive in terms of generating distinct representations for nodes with different Ego-AE features, which fills in a fundamental gap of existing GNN variants  ...  Finally, we empirically validate our model on eight real-world graph data, including social network, e-commerce co-purchase network, and citation network, and show that it consistently outperforms existing  ...  Theoretical Analysis Here, we aim to answer two questions: 1) how does the expressiveness of AE-aware aggregator relate to previous works; and 2) is our designed AE-aware aggregator expressive enough to  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.04218v2">arXiv:2011.04218v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/55xw635nufchbfhnrl6tov5ove">fatcat:55xw635nufchbfhnrl6tov5ove</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211114131340/https://arxiv.org/pdf/2011.04218v2.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/b5/8a/b58a9d674201af9de74c1d65580f4d742c60d52a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.04218v2" 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>

Hop-Hop Relation-aware Graph Neural Networks [article]

Li Zhang, Yan Ge, Haiping Lu
<span title="2020-12-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In neighborhood aggregation, our model simultaneously allows for hop-aware projection and aggregation.  ...  In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs.  ...  Proposed Algorithm After the theoretical studies, we carefully design our model and propose a new GNN: Hop-Hop Relation-aware Graph Neural Network (HHR-GNN).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.11147v1">arXiv:2012.11147v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bgqrc6umtfgbjmguufngdvbma4">fatcat:bgqrc6umtfgbjmguufngdvbma4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201225062203/https://arxiv.org/pdf/2012.11147v1.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/64/9d/649d7d8dda174bcc49b0c17edaa724dae3c9ba8e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.11147v1" 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>

Fairness-Aware Node Representation Learning [article]

Öykü Deniz Köse, Yanning Shen
<span title="2021-06-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, this study addresses fairness issues in graph contrastive learning with fairness-aware graph augmentation designs, through adaptive feature masking and edge deletion.  ...  Despite the success of graph contrastive learning and consequent growing interest, fairness is largely under-explored in the field.  ...  Fairness-aware learning on graphs. While fairness-aware ML is gaining more and more attention, it is rather under-explored on graphs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.05391v1">arXiv:2106.05391v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gbzvlecaeresdjn52ec3osvdwe">fatcat:gbzvlecaeresdjn52ec3osvdwe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210728165346/https://arxiv.org/pdf/2106.05391v1.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/9d/ba/9dba5a90206ea7c29cbe27923018f070bf8a0016.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.05391v1" 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>

Graph Neural Networks for Graphs with Heterophily: A Survey [article]

Xin Zheng, Yixin Liu, Shirui Pan, Miao Zhang, Di Jin, Philip S. Yu
<span title="2022-02-14">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In the end, we point out the potential directions to advance and stimulate future research and applications on heterophilic graphs.  ...  Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriads of graph analytic tasks and applications.  ...  Therefore, the edge-aware weights of neighbors should be assigned according to the spatial graph topology and node labels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07082v1">arXiv:2202.07082v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/26d5mpnfzbb7fmloytdbj67yxa">fatcat:26d5mpnfzbb7fmloytdbj67yxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220217114752/https://arxiv.org/pdf/2202.07082v1.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/02/a3/02a3452a5f7fe42ba32bbf30af28b7845b2d6857.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07082v1" 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>

InfoGCL: Information-Aware Graph Contrastive Learning [article]

Dongkuan Xu, Wei Cheng, Dongsheng Luo, Haifeng Chen, Xiang Zhang
<span title="2021-10-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we aim to fill this gap by studying how graph information is transformed and transferred during the contrastive learning process and proposing an information-aware graph contrastive learning  ...  We empirically validate our theoretical analysis on both node and graph classification benchmark datasets, and demonstrate that our algorithm significantly outperforms the state-of-the-arts.  ...  Conclusion and Limitations We propose InfoGCL, an information-aware graph contrastive learning framework for graph contrastive learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.15438v1">arXiv:2110.15438v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u3g3sphvjrd4dlqt2kebas3oaa">fatcat:u3g3sphvjrd4dlqt2kebas3oaa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211105002935/https://arxiv.org/pdf/2110.15438v1.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/22/9c/229cf7592e45193ff6d3fed5ef13dae511f7a0d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.15438v1" 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>

Structure-Aware Transformer for Graph Representation Learning [article]

Dexiong Chen and Leslie O'Bray and Karsten Borgwardt
<span title="2022-02-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose several methods for automatically generating the subgraph representation and show theoretically that the resulting representations are at least as expressive as the subgraph representations.  ...  To address this issue, we propose the Structure-Aware Transformer, a class of simple and flexible graph transformers built upon a new self-attention mechanism.  ...  Bastian Rieck and Dr. Carlos Oliver for their insightful feedback on the manuscript, which greatly improved it.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.03036v1">arXiv:2202.03036v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rgpzhfv4gzfwvodeeeawfzrzaq">fatcat:rgpzhfv4gzfwvodeeeawfzrzaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220210082230/https://arxiv.org/pdf/2202.03036v1.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/63/f7/63f79d6b1faec166b5ecb0963fb9ad70a320e775.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.03036v1" 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>

Identity-aware Graph Neural Networks [article]

Jiaxuan You, Jonathan Gomes-Selman, Rex Ying, Jure Leskovec
<span title="2021-02-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test.  ...  However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and  ...  Comparisons with Expressive Graph Networks We provide additional experimental comparisons against other expressive graph networks in both edge and graphlevel tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.10320v2">arXiv:2101.10320v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w63r6maomnc6zj4om5hnoeo4t4">fatcat:w63r6maomnc6zj4om5hnoeo4t4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210218231749/https://arxiv.org/pdf/2101.10320v2.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/82/45/824527744e627bb1f77252a1fdd7309832ab2f2d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.10320v2" 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>

CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning [article]

Yanqiao Zhu and Yichen Xu and Feng Yu and Shu Wu and Liang Wang
<span title="2020-09-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features.  ...  In this paper, we present a novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques.  ...  [22] theoretically unify random walks and matrix factorization techniques into a framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.01674v1">arXiv:2009.01674v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3wihohgjzrbmpba3jgnoevedii">fatcat:3wihohgjzrbmpba3jgnoevedii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200918125352/https://arxiv.org/pdf/2009.01674v1.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/2009.01674v1" 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>

Similarity-Aware Spectral Sparsification by Edge Filtering [article]

Zhuo Feng
<span title="2018-04-07">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Motivated by recent graph signal processing techniques, this paper proposes a similarity-aware spectral graph sparsification framework that leverages efficient spectral off-tree edge embedding and filtering  ...  frequently studied in many machine learning and data mining applications.  ...  ) of the original graph's Laplacian, which immediately leads to a series of theoretically nearlylinear-time numerical and graph algorithms for solving sparse matrices, graph-based semi-supervised learning  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.05135v3">arXiv:1711.05135v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cxtdqiq5ljexlgpxdkskg5df2a">fatcat:cxtdqiq5ljexlgpxdkskg5df2a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200924124235/https://arxiv.org/pdf/1711.05135v3.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/86/a0/86a0675d7369d7853de8ceb7aecb86d65fb1e596.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.05135v3" 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>

Graph-based Neural Acceleration for Nonnegative Matrix Factorization [article]

Jens Sjölund, Maria Bånkestad
<span title="2022-02-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We first consider low-rank factorization more broadly and propose a graph representation of the problem suited for graph neural networks.  ...  We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known in certain fields, e.g  ...  To place node and edge features on equal footing, we, therefore, extend the relation-aware self-attention mechanism of Shaw et al. (2018) to arbitrary directed, weighted, graphs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.00264v1">arXiv:2202.00264v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l3q6i2sxlzcwrgifb4pwbksozi">fatcat:l3q6i2sxlzcwrgifb4pwbksozi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220203091755/https://arxiv.org/pdf/2202.00264v1.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/2b/34/2b34ee1b7f4cf5e7dac38d8e66849a02d96fade3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.00264v1" 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>

Feature Interaction-aware Graph Neural Networks [article]

Kaize Ding, Yichuan Li, Jundong Li, Chenghao Liu, Huan Liu
<span title="2020-01-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose Feature Interaction-aware Graph Neural Networks (FI-GNNs), a plug-and-play GNN framework for learning node representations encoded with informative feature interactions.  ...  However, most real-world graphs often come with high-dimensional and sparse node features, rendering the learned node representations from existing GNN architectures less expressive.  ...  Towards advancing graph neural networks to learn more expressive node representations, we propose a novel framework: feature interaction-aware graph neural networks (FI-GNNs) in this study.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.07110v2">arXiv:1908.07110v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fk76u5vxorfljom5s3ivwhk6ku">fatcat:fk76u5vxorfljom5s3ivwhk6ku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321024827/https://arxiv.org/pdf/1908.07110v2.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/1908.07110v2" 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>

Fuzzy Cognitive Maps for Identifying Fault Activation Patterns in Automation Systems [chapter]

Salman Mohagheghi
<span title="2015-09-02">2015</span> <i title="InTech"> Fuzzy Logic - Tool for Getting Accurate Solutions </i> &nbsp;
graph-theoretic rules.  ...  Many unsupervised learning schemes are based on the Hebb's learning law, where the change in the synaptic weight w ij linking vertices j and i is expressed as a function of signal flows before and after  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/59611">doi:10.5772/59611</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vrvauar2hnfsfdf7z77ytl5sqi">fatcat:vrvauar2hnfsfdf7z77ytl5sqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501194128/https://cdn.intechopen.com/pdfs/47891.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/81/b5/81b5f71486403c478a82bea8908ac3a4ddf35e17.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/59611"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Permutation-equivariant and Proximity-aware Graph Neural Networks with Stochastic Message Passing [article]

Ziwei Zhang, Chenhao Niu, Peng Cui, Jian Pei, Bo Zhang, Wenwu Zhu
<span title="2022-02-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Graph neural networks (GNNs) are emerging machine learning models on graphs. Permutation-equivariance and proximity-awareness are two important properties highly desirable for GNNs.  ...  Then, we propose Stochastic Message Passing (SMP) model, a general and simple GNN to maintain both proximity-awareness and permutation-equivariance.  ...  Indeed, if we use a sufficiently expressive GNN in learningẼ instead of linear propagations, we can prove a more general version of Theorem 2 as follows.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02562v2">arXiv:2009.02562v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bhj7trzub5acllbppimpjvhn3i">fatcat:bhj7trzub5acllbppimpjvhn3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200918050856/https://arxiv.org/pdf/2009.02562v1.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/2009.02562v2" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 31,723 results