{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T09:19:47Z","timestamp":1764494387363,"version":"build-2065373602"},"reference-count":24,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Web"],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>\n            In recent years, graph neural networks (GNNs) have become a popular tool for solving various problems over graphs. In these models, the link structure of the graph is typically exploited and nodes\u2019 embeddings are iteratively updated based on adjacent nodes. Nodes\u2019 contents are used solely in the form of feature vectors, served as nodes\u2019 first-layer embeddings. However, the filters or convolutions, applied during iterations\/layers to these initial embeddings lead to their impact diminish and contribute insignificantly to the final embeddings. To address this issue, in this article we propose augmenting nodes\u2019 embeddings by embeddings generated from their content, at higher GNN layers. More precisely, we propose models wherein a\n            <jats:italic toggle=\"yes\">structural<\/jats:italic>\n            embedding using a GNN and a\n            <jats:italic toggle=\"yes\">content<\/jats:italic>\n            embedding are computed for each node. These two are combined using a combination layer to form the embedding of a node at a given layer layer. We suggest methods such as using an auto-encoder or building a content graph to generate\n            <jats:italic toggle=\"yes\">content<\/jats:italic>\n            embeddings. In the end, by conducting experiments over several real-world datasets, we demonstrate the high accuracy and performance of our models.\n          <\/jats:p>","DOI":"10.1145\/3700790","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T05:40:21Z","timestamp":1729748421000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Content Augmented Graph Neural Networks"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5433-9642","authenticated-orcid":false,"given":"Fatemeh","family":"Gholamzadeh Nasrabadi","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic)","place":["Tehran, Iran (the Islamic Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5146-5160","authenticated-orcid":false,"given":"Amirhossein","family":"Kashani","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic)","place":["Tehran, Iran (the Islamic Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0490-436X","authenticated-orcid":false,"given":"Pegah","family":"Zahedi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic)","place":["Tehran, Iran (the Islamic Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3436-0541","authenticated-orcid":false,"given":"Mostafa","family":"Haghir Chehreghani","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic)","place":["Tehran, Iran (the Islamic Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR\u201921)","author":"Alon Uri","year":"2021","unstructured":"Uri Alon and Eran Yahav. 2021. On the bottleneck of graph neural networks and its practical implications. In Proceedings of the 9th International Conference on Learning Representations (ICLR\u201921). OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_2_3_2","DOI":"10.1007\/978-3-031-53468-3_19"},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)","author":"Bojchevski Aleksandar","year":"2018","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. In Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918). OpenReview.net."},{"key":"e_1_3_2_5_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR\u201922)","author":"Brody Shaked","year":"2022","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2022. How attentive are graph attention networks? In Proceedings of the 10th International Conference on Learning Representations (ICLR\u201922). OpenReview.net."},{"unstructured":"Rickard Br\u00fcel-Gabrielsson Mikhail Yurochkin and Justin Solomon. 2023. Rewiring with positional encodings for graph neural networks. (2023). arxiv:cs.LG\/2201.12674. Retrieved from https:\/\/arxiv.org\/abs\/2201.12674","key":"e_1_3_2_6_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_7_2","DOI":"10.1038\/s42256-022-00466-8"},{"key":"e_1_3_2_8_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR\u201922)","author":"Chien Eli","year":"2022","unstructured":"Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic, and Inderjit S. Dhillon. 2022. Node feature extraction by self-supervised multi-scale neighborhood prediction. In Proceedings of the 10th International Conference on Learning Representations (ICLR\u201922). OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_2_9_2","DOI":"10.1007\/s10994-023-06475-x"},{"doi-asserted-by":"publisher","key":"e_1_3_2_10_2","DOI":"10.1145\/2939672.2939754"},{"doi-asserted-by":"publisher","key":"e_1_3_2_11_2","DOI":"10.1126\/science.1127647"},{"doi-asserted-by":"publisher","key":"e_1_3_2_12_2","DOI":"10.1145\/3437963.3441735"},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR\u201917)","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR\u201917). OpenReview.net, 14."},{"key":"e_1_3_2_14_2","first-page":"1188","volume-title":"Proceedings of the 31th International Conference on Machine Learning (ICML\u201914) (JMLR Workshop and Conference Proceedings)","volume":"32","author":"Le Quoc V.","year":"2014","unstructured":"Quoc V. Le and Tom\u00e1s Mikolov. 2014. Distributed representations of sentences and documents. In Proceedings of the 31th International Conference on Machine Learning (ICML\u201914) (JMLR Workshop and Conference Proceedings), Vol. 32. JMLR.org, 1188\u20131196."},{"key":"e_1_3_2_15_2","first-page":"20887","article-title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","volume":"34","author":"Lim Derek","year":"2021","unstructured":"Derek Lim, Felix Hohne, Xiuyu Li, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, and Ser Nam Lim. 2021. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Adv. Neural Inf. Process. Syst. 34 (2021), 20887\u201320902.","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Yassin Mohamadi and Mostafa Haghir Chehreghani. 2024. Strong transitivity relations and graph neural networks. arXiv:2401.01384. Retrieved from https:\/\/arxiv.org\/abs\/2401.01384","key":"e_1_3_2_16_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_17_2","DOI":"10.1145\/2623330.2623732"},{"doi-asserted-by":"publisher","key":"e_1_3_2_18_2","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.676"},{"doi-asserted-by":"publisher","key":"e_1_3_2_19_2","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"doi-asserted-by":"publisher","key":"e_1_3_2_20_2","DOI":"10.1145\/3565472.3592965"},{"key":"e_1_3_2_21_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations, (ICLR\u201918)","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations, (ICLR\u201918). OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_2_22_2","DOI":"10.14778\/3421424.3421430"},{"key":"e_1_3_2_23_2","first-page":"40","volume-title":"Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916) (JMLR Workshop and Conference Proceedings)","volume":"48","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William W. Cohen, and Ruslan Salakhutdinov. 2016. Revisiting semi-supervised learning with graph embeddings. In Proceedings of the 33nd International Conference on Machine Learning (ICML\u201916) (JMLR Workshop and Conference Proceedings), Maria-Florina Balcan and Kilian Q. Weinberger (Eds.), Vol. 48. JMLR.org, 40\u201348."},{"key":"e_1_3_2_24_2","first-page":"17009","article-title":"Design space for graph neural networks","volume":"33","author":"You Jiaxuan","year":"2020","unstructured":"Jiaxuan You, Zhitao Ying, and Jure Leskovec. 2020. Design space for graph neural networks. Adv. Neural Inf. Process. Syst. 33 (2020), 17009\u201317021.","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"publisher","key":"e_1_3_2_25_2","DOI":"10.1007\/s11227-024-06336-x"}],"container-title":["ACM Transactions on the Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3700790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T12:27:06Z","timestamp":1760531226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3700790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3700790"],"URL":"https:\/\/doi.org\/10.1145\/3700790","relation":{},"ISSN":["1559-1131","1559-114X"],"issn-type":[{"type":"print","value":"1559-1131"},{"type":"electronic","value":"1559-114X"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"assertion":[{"value":"2024-01-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}