Filters








15,740 Hits in 4.0 sec

Graph Regularized Transductive Classification on Heterogeneous Information Networks [chapter]

Ming Ji, Yizhou Sun, Marina Danilevsky, Jiawei Han, Jing Gao
<span title="">2010</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this paper, we consider the transductive classification problem on heterogeneous networked data which share a common topic.  ...  However, although classification on homogeneous networks has been studied for decades, classification on heterogeneous networks has not been explored until recently.  ...  Transductive classification on heterogeneous information networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-15880-3_42">doi:10.1007/978-3-642-15880-3_42</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r47krvy7tbgkvdponhgzcdh2za">fatcat:r47krvy7tbgkvdponhgzcdh2za</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171204145903/https://core.ac.uk/download/pdf/4837585.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/bb/31bbe7af0e70bebcaa9cf484dbc77bfac9262df7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-15880-3_42"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Music Classification By Transductive Learning Using Bipartite Heterogeneous Networks

Diego Furtado Silva, Rafael Geraldeli Rossi, Solange Oliveira Rezende, Gustavo Enrique De Almeida Prado Alves Batista
<span title="2014-10-27">2014</span> <i title="Zenodo"> Zenodo </i> &nbsp;
Transductive Classification Using Bipartite Heterogeneous Networks The main algorithms for transductive classification in data represented as networks are based on regularization [19] , which have to  ...  The proposed framework has three main steps: (i) codebook generation, (ii) network generation for transductive classification, and (iii) transductive classification using bipartite heterogeneous networks  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1418264">doi:10.5281/zenodo.1418264</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ic7iwvnaeva6nke6ekvhq4djfy">fatcat:ic7iwvnaeva6nke6ekvhq4djfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201225025509/https://zenodo.org/record/1418265/files/SilvaRRB14.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/c6/e0/c6e0572181fa661e3eb4000c867a03de726c0c12.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1418264"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Topological Transduction for Hybrid Few-shot Learning

Jiayi Chen, Aidong Zhang
<span title="2022-04-25">2022</span> <i title="ACM"> Proceedings of the ACM Web Conference 2022 </i> &nbsp;
To alleviate these challenges, we propose the Task-adaptive Topological Transduction Network, namely TopoNet, which trains a heterogeneous graph-based transductive meta-learner that can combine information  ...  well as its inter-and intra-class data relationships, through an edge-enhanced heterogeneous graph neural network.  ...  Transductive Learning with Edge-enhanced Heterogeneous Graph Neural Network. An hFSL classification task has been converted into a node-heterogeneous and multi-relation graph G = (V, E; T ).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3485447.3512033">doi:10.1145/3485447.3512033</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o4jes64ec5hhfhoffrxx57j5fa">fatcat:o4jes64ec5hhfhoffrxx57j5fa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220503033629/https://dl.acm.org/doi/pdf/10.1145/3485447.3512033" 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/e6/34/e634e082f64acb1f7c391bbdb4518f32faf4ed8a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3485447.3512033"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Mining heterogeneous information networks

Jaiwei Han
<span title="">2012</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fqqihtxlu5bvfaqxjyvqcob35a" style="color: black;">Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD &#39;12</a> </i> &nbsp;
., "Graph Regularized Transductive Classification on Heterogeneous Information Networks", ECMLPKDD'10. M. Ji, M.  ...  ., "Graph Regularized Transductive Classification on Heterogeneous Information Networks", ECMLPKDD'10 23 ( ) ( ) 1 ( ) ( ) 2 , , 1 1 1 , , ( ) ( ) ( ) ( ) 1 ( ,..., ) 1 1  ...   Topological features encoded in meta-paths  Surprisingly rich knowledge can be mined from such structured heterogeneous info. networks  Clustering, ranking, classification, data cleaning, trust analysis  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2339530.2339533">doi:10.1145/2339530.2339533</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/kdd/Han12.html">dblp:conf/kdd/Han12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2kycyso37fgu5f5a2tai52bhem">fatcat:2kycyso37fgu5f5a2tai52bhem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809140305/http://web.engr.illinois.edu/~hanj/slides/kdd12_jhan_slides.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/40/90/409019dc684c032d9be1a878e428ba0881d6bcf7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2339530.2339533"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Graph Regularized Meta-path Based Transductive Regression in Heterogeneous Information Network [chapter]

Mengting Wan, Yunbo Ouyang, Lance Kaplan, Jiawei Han
<span title="2015-06-30">2015</span> <i title="Society for Industrial and Applied Mathematics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/viwc2ys5x5a47ogpdlftfzj5fm" style="color: black;">Proceedings of the 2015 SIAM International Conference on Data Mining</a> </i> &nbsp;
Numerical prediction in heterogeneous information networks is a challenging but significant area because network based information for unlabeled objects is usually limited to make precise estimations.  ...  A number of real-world networks are heterogeneous information networks, which are composed of different types of nodes and links.  ...  However, classification in heterogeneous networks [1] [2] [3] [4] and regression in homogeneous networks [5, 6] have been studied.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611974010.103">doi:10.1137/1.9781611974010.103</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26705510">pmid:26705510</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4688014/">pmcid:PMC4688014</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sdm/WanOKH15.html">dblp:conf/sdm/WanOKH15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s7u6do2x4rdivivmprstaelani">fatcat:s7u6do2x4rdivivmprstaelani</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170108195443/http://cseweb.ucsd.edu:80/~m5wan/paper/sdm15_mwan.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/c5/83/c583d7cc19267433ccde8f0cad4e70da95e103ef.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611974010.103"> <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/PMC4688014" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Transductive Classification on Heterogeneous Information Networks with Edge Betweenness-based Normalization

Phiradet Bangcharoensap, Tsuyoshi Murata, Hayato Kobayashi, Nobuyuki Shimizu
<span title="">2016</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/puezkhxc3rggrgb456avsvxi34" style="color: black;">Proceedings of the Ninth ACM International Conference on Web Search and Data Mining - WSDM &#39;16</a> </i> &nbsp;
This paper proposes a novel method for transductive classification on heterogeneous information networks composed of multiple types of vertices.  ...  Since directly applying the conventional edge betweenness is inefficient on heterogeneous networks, we propose two additional refinements.  ...  CONCLUSION We proposed a novel method for transductive classification on heterogeneous information networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2835776.2835799">doi:10.1145/2835776.2835799</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wsdm/BangcharoensapM16.html">dblp:conf/wsdm/BangcharoensapM16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/acgdnfolhzfahgesg6ovvwtbuu">fatcat:acgdnfolhzfahgesg6ovvwtbuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830032205/https://s3-us-west-2.amazonaws.com/ai2-s2-public/wsdm-pdfs/p437-bangcharoensap.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/08/96/0896bbb0c56d63631b72886ddd773d0d468d2132.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2835776.2835799"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

TLINE: Scalable Transductive Network Embedding [chapter]

Xia Zhang, Weizheng Chen, Hongfei Yan
<span title="">2016</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
To evaluate the performance in node classification task, we test our methods on two real world network datasets, which are Citeseer and DBLP.  ...  TLINE is a transductive network embedding method, which optimizes the loss function of LINE to preserve both local and global network structure information, and applies SVM to maximize the margin between  ...  In real world, homogeneous networks are just a small part of various information networks, while heterogeneous networks are more common.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-48051-0_8">doi:10.1007/978-3-319-48051-0_8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/34dmmhel2fbdhbir3lgymardv4">fatcat:34dmmhel2fbdhbir3lgymardv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218131807/https://static.aminer.org/upload/pdf/1362/1769/358/581ee1e268ab39f745b47365.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/68/6c/686c12dd06d9db7af0e793ad2edda856ef29695b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-48051-0_8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Graph Representation Learning Network via Adaptive Sampling [article]

Anderson de Andrade, Chen Liu
<span title="2020-06-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data and have been widely studied for link prediction and node classification.  ...  We conduct experiments on both transductive and inductive settings.  ...  We evaluate the proposed method in node classification tasks using the Cora, Citeseer and Pubmed citation networks in a transductive setting, and on a protein to protein interaction (PPI) dataset in an  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.04637v1">arXiv:2006.04637v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zvri6b65kffxtcwhnhqfiwitre">fatcat:zvri6b65kffxtcwhnhqfiwitre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200610072128/https://arxiv.org/pdf/2006.04637v1.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/2006.04637v1" 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>

Heterformer: A Transformer Architecture for Node Representation Learning on Heterogeneous Text-Rich Networks [article]

Bowen Jin, Yu Zhang, Qi Zhu, Jiawei Han
<span title="2022-05-20">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We study node representation learning on heterogeneous text-rich networks, where nodes and edges are multi-typed and some types of nodes are associated with text information.  ...  to delicately coupling these two types of models on heterogeneous text-rich networks.  ...  quite well on unseen nodes as its performance on inductive node classification is quite close to that on transductive node classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.10282v1">arXiv:2205.10282v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q3vqdn3nubhvzlpkw45bgesima">fatcat:q3vqdn3nubhvzlpkw45bgesima</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220530042939/https://arxiv.org/pdf/2205.10282v1.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/d4/88/d48846abdac33d56f48ac5e617609a05b577e889.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.10282v1" 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>

HinDom: A Robust Malicious Domain Detection System based on Heterogeneous Information Network with Transductive Classification [article]

Xiaoqing Sun, Mingkai Tong, Jiahai Yang
<span title="2019-09-04">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Instead of relying on manually selected features, HinDom models the DNS scene as a Heterogeneous Information Network (HIN) consist of clients, domains, IP addresses and their diverse relationships.  ...  Besides, the metapath-based transductive classification method enables HinDom to detect malicious domains with only a small fraction of labeled samples.  ...  Additionally, we appreciate 360netLab, VirusTotal for permissions of their advanced APIs and we thank Information Technology Center of Tsinghua University for authorizing the use of their data in our experiments  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.01590v1">arXiv:1909.01590v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2zphegvq6bgf5ktrzqdylb3kwm">fatcat:2zphegvq6bgf5ktrzqdylb3kwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831031210/https://arxiv.org/pdf/1909.01590v1.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/05/39/053973b807d752b5961326e231dc6f7b8add957b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.01590v1" 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>

Automatic Opioid User Detection from Twitter: Transductive Ensemble Built on Different Meta-graph Based Similarities over Heterogeneous Information Network

Yujie Fan, Yiming Zhang, Yanfang Ye, Xin Li
<span title="">2018</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-Seventh International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
In HinOPU, to model the users and the posted tweets as well as their rich relationships, we introduce structured heterogeneous information network (HIN) for representation.  ...  To reduce the cost of acquiring labeled samples for supervised learning, we propose a transductive classification method to build the base classifiers based on different similarities formulated by different  ...  based similarities over heterogeneous information network (HIN), to automatically detect opioid users from Twitter.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/466">doi:10.24963/ijcai.2018/466</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/FanZYL18.html">dblp:conf/ijcai/FanZYL18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sdgwqhzgfvbldfgbl3d526crv4">fatcat:sdgwqhzgfvbldfgbl3d526crv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190222235302/http://pdfs.semanticscholar.org/45cc/775bffb0b38836a54289d618885fb61cd670.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/45/cc/45cc775bffb0b38836a54289d618885fb61cd670.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/466"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [article]

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
<span title="2021-04-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experiments on three real-world heterogeneous graphs have further validated the efficacy of WIDEN on both transductive and inductive node representation learning, as well as the superior training efficiency  ...  ., in streaming scenarios), few heterogeneous GNNs can bypass the transductive learning scheme where all nodes must be known during training.  ...  transductive node classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.01711v2">arXiv:2104.01711v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uozthcnesjbszdf2ciauvvgrai">fatcat:uozthcnesjbszdf2ciauvvgrai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414053325/https://arxiv.org/pdf/2104.01711v2.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/d1/f8/d1f81ea14c31ab4ec188b21a43989f6ca6ee067f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.01711v2" 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>

Meta-path Free Semi-supervised Learning for Heterogeneous Networks [article]

Shin-woo Park, Byung Jun Bae, Jinyoung Yeo, Seung-won Hwang
<span title="2021-01-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification.  ...  In this paper, we propose simple and effective graph neural networks for heterogeneous graph, excluding the use of meta-paths.  ...  First, we present HEterogeneity Relaxation (HER) network that replaces the use of node pair information by using only single node information to compute attention coefficients.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08924v2">arXiv:2010.08924v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7dkluz7eyrcjfj37f6roshu24y">fatcat:7dkluz7eyrcjfj37f6roshu24y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201022204638/https://arxiv.org/pdf/2010.08924v1.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/5a/d9/5ad9e62fc5da270e56dbb7f09f2c0753393a7bef.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08924v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning latent representations of nodes for classifying in heterogeneous social networks

Yann Jacob, Ludovic Denoyer, Patrick Gallinari
<span title="">2014</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/puezkhxc3rggrgb456avsvxi34" style="color: black;">Proceedings of the 7th ACM international conference on Web search and data mining - WSDM &#39;14</a> </i> &nbsp;
We address here the specific problem of nodes classification and tagging in heterogeneous social networks, where different types of nodes are considered, each type with its own label or tag set.  ...  While learning and performing inference on homogeneous networks have motivated a large amount of research, few work exists on heterogeneous networks and there are open and challenging issues for existing  ...  Classification in heterogeneous networks, representative of real world media, is much more recent with only a few attempts for now.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2556195.2556225">doi:10.1145/2556195.2556225</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wsdm/JacobDG14.html">dblp:conf/wsdm/JacobDG14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/klpzid4d5nferl35fpk5wobkxe">fatcat:klpzid4d5nferl35fpk5wobkxe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808010131/http://www-connex.lip6.fr/~gallinar/gallinari/uploads/Teaching/WSDM2014-jacob.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/03/0d/030d436cb0465fd6cec0d5140b2534a8f1b8aeca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2556195.2556225"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

BertGCN: Transductive Text Classification by Combining GCN and BERT [article]

Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu
<span title="2022-03-21">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification.  ...  Experiments show that BertGCN achieves SOTA performances on a wide range of text classification datasets. Code is available at https://github.com/ZeroRin/BertGCN.  ...  Results for different models on transductive text classification datasets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.05727v4">arXiv:2105.05727v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kcqvihtygnbw5mu3zjlvpuxwci">fatcat:kcqvihtygnbw5mu3zjlvpuxwci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220517023946/https://arxiv.org/pdf/2105.05727v4.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/d2/2b/d22b109eb5089179f8bd48ef47513533890f6bf9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.05727v4" 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 15,740 results