{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T05:57:19Z","timestamp":1740895039636,"version":"3.38.0"},"reference-count":45,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T00:00:00Z","timestamp":1659916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Information Science"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:p> Machine learning approaches have become a crucial tool in graph analysis. Despite the accurate results of the existing approaches, most of them are not scalable enough to be used in real-world problems. Networks provide two different kinds of information, nodes contents and nodes relations (network structure). Training deep graph neural networks (GNN) over large-scale graphs is challenging due to the limitation of the message passing framework. Graph Convolutional Networks (GCN) work on all node neighbours at once. Furthermore, it is usual to transform node features with a deep neural network before the GC operation. Therefore, the deep transform operation may apply up to hundreds of times for each target node which is heavy computation and hard to batch. This paper presents an abstract framework with two embedding components, the first component embeds node relations, and the second one embeds node contents. The model makes predictions by aggregating these embeddings through a combination component. The presented approach limits the deep transform only to the target node and uses random walk-based embedding instead of the GC operator to reduce the cost. The main goal of the proposed approach is to provide a light framework for the task. To this aim, node relations are embedded based on node neighbourhood structure by a biased variant of the DeepWalk model, called GuidedWalk, and an autoencoder embeds node contents. The experimental results on three well-known datasets show the superiority of the proposed model compared to the state-of-the-art GraphSAGE and TADW models with less computational complexity. On the Citeseer, Cora, and PubMed datasets, the model has achieved 3.23%, 0.88%, and 7.63% improvement in Macro-F1 and 3.25%, 0.7%, and 6.34% improvement in Micro-F1, respectively. Although GNNs are state-of-the-art models, considering node content is their main advantage. This paper shows that even a simple integration of node content to available random walk-based methods improves their performance up to GCNs without increasing the complexity. <\/jats:p>","DOI":"10.1177\/01655515221111002","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T11:59:50Z","timestamp":1659959990000},"page":"977-990","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Node classifications with DjCaNE: Disjoint content and network embedding"],"prefix":"10.1177","volume":"50","author":[{"given":"Mohsen","family":"Fazaeli","sequence":"first","affiliation":[{"name":"Computer Engineering Department, Amirkabir University of Technology (Tehran Polytechnic), Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-1342","authenticated-orcid":false,"given":"Saeedeh","family":"Momtazi","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, Amirkabir University of Technology (Tehran Polytechnic), Iran"}]}],"member":"179","published-online":{"date-parts":[[2022,8,8]]},"reference":[{"key":"bibr1-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924184"},{"volume-title":"Graph representation learning. Synthesis lectures on artificial intelligence and machine learning series","year":"2020","author":"Hamilton W","key":"bibr2-01655515221111002"},{"key":"bibr3-01655515221111002","first-page":"2224","volume-title":"Advances in neural information processing Systems (NIPS)","author":"Duvenaud DK","year":"2015"},{"first-page":"968","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining","author":"Wang H","key":"bibr4-01655515221111002"},{"key":"bibr5-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1177\/0165551520912676"},{"key":"bibr6-01655515221111002","first-page":"1024","volume-title":"Advances in neural information processing systems (NIPS)","author":"Hamilton W","year":"2017"},{"key":"bibr7-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1177\/0165551519871826"},{"key":"bibr8-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1177\/0165551520962775"},{"first-page":"2267","volume-title":"Proceedings of the association for the advancement of artificial intelligence (AAAI\u201915)","author":"Lai S","key":"bibr9-01655515221111002"},{"first-page":"254","volume-title":"Proceedings of the 3rd high performance computing and cluster technologies conference","author":"Gong C","key":"bibr10-01655515221111002"},{"key":"bibr11-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.10.006"},{"key":"bibr12-01655515221111002","first-page":"649","volume-title":"Advances in neural information processing systems (NIPS)","author":"Zhang X","year":"2015"},{"first-page":"855","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining","author":"Grover A","key":"bibr13-01655515221111002"},{"first-page":"133","volume-title":"European network intelligence conference","author":"Kajdanowicz T","key":"bibr14-01655515221111002"},{"key":"bibr15-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.07.006"},{"first-page":"2111","volume-title":"Proceedings of the 24th international conference on artificial intelligence (IJCAI\u201915)","author":"Yang C","key":"bibr16-01655515221111002"},{"key":"bibr17-01655515221111002","first-page":"7370","volume-title":"Proceedings of the association for the advancement of artificial intelligence (AAAI)","volume":"33","author":"Yao L"},{"key":"bibr18-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"bibr19-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.03.022"},{"key":"bibr20-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"first-page":"701","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining","author":"Perozzi B","key":"bibr21-01655515221111002"},{"key":"bibr22-01655515221111002","unstructured":"Mikolov T, Chen K, Corrado GS, et al. Efficient estimation of word representations in vector space. CoRR, abs\/1301.3781, 2013, https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"bibr23-01655515221111002","first-page":"3111","volume-title":"Advances in neural information processing systems (NIPS)","author":"Mikolov T","year":"2013"},{"key":"bibr24-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"first-page":"385","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining","author":"Ribeiro LF","key":"bibr25-01655515221111002"},{"first-page":"135","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining","author":"Dong Y","key":"bibr26-01655515221111002"},{"volume-title":"ICLR","author":"Pimentel T","key":"bibr27-01655515221111002"},{"first-page":"891","volume-title":"Proceedings of the ACM international on conference on information and knowledge management (CIKM)","author":"Cao S","key":"bibr28-01655515221111002"},{"key":"bibr29-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2606098"},{"first-page":"459","volume-title":"Proceedings of the eleventh ACM international conference on web search and data mining","author":"Qiu J","key":"bibr30-01655515221111002"},{"first-page":"1165","volume-title":"Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining (KDD \u201915)","author":"Tang J","key":"bibr31-01655515221111002"},{"volume-title":"International Conference on Learning Representations (ICLR)","author":"Kipf TN","key":"bibr32-01655515221111002"},{"volume-title":"International conference on learning representations","author":"Veli\u010dkovi\u0107 P","key":"bibr33-01655515221111002"},{"volume-title":"International conference on learning representations","author":"Xu K","key":"bibr34-01655515221111002"},{"key":"bibr35-01655515221111002","unstructured":"Fey M, Lenssen JE. Fast graph representation learning with PyTorch Geometric. In: ICLR workshop on representation learning on graphs and manifolds, 2019, https:\/\/rlgm.github.io\/papers\/2.pdf"},{"key":"bibr36-01655515221111002","unstructured":"Wang M, Zheng D, Ye Z, et al. Deep graph library: a graph-centric, highly-performant package for graph neural networks. arXiv preprint arXiv: 1909.01315, 2019."},{"key":"bibr37-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1177\/0165551519891345"},{"first-page":"9","volume-title":"2018 IEEE\/WIC\/ACM international conference on web intelligence (WI)","author":"Lai K-H","key":"bibr38-01655515221111002"},{"key":"bibr39-01655515221111002","unstructured":"Bandyopadhyay S, Kara H, Biswas A, et al. Sac2vec: information network representation with structure and content. arXiv, abs\/1804.10363, 2018, https:\/\/arxiv.org\/abs\/1804.10363"},{"key":"bibr40-01655515221111002","unstructured":"Levy O, Goldberg Y. Neural word embedding as implicit matrix factorization. In: Advances in neural information processing systems 27 2014, https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/feab05aa91085b7a8012516bc3533958-Paper.pdf"},{"key":"bibr41-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/12\/10\/103018"},{"key":"bibr42-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1086\/676597"},{"key":"bibr43-01655515221111002","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"volume":"8","volume-title":"10th international workshop on mining and learning with graphs","author":"Namata G","key":"bibr44-01655515221111002"},{"first-page":"40","volume-title":"Proceedings of the 33rd international conference on machine learning, vol. 48 of proceedings of machine learning research","author":"Yang Z","key":"bibr45-01655515221111002"}],"container-title":["Journal of Information Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515221111002","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01655515221111002","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515221111002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T21:04:36Z","timestamp":1740863076000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01655515221111002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,8]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1177\/01655515221111002"],"URL":"https:\/\/doi.org\/10.1177\/01655515221111002","relation":{},"ISSN":["0165-5515","1741-6485"],"issn-type":[{"type":"print","value":"0165-5515"},{"type":"electronic","value":"1741-6485"}],"subject":[],"published":{"date-parts":[[2022,8,8]]}}}