{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:21:58Z","timestamp":1780352518608,"version":"3.54.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NCSR - Demokritos Library"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In this work we investigate an observation made by Kipf and Welling (5th International Conference on Learning Representations, 2017), who suggested that untrained Graph Convolutional Networks (GCNs) can generate meaningful node embeddings. In particular, we investigate the effect of training only a single layer of a GCN or a GAT (Graph Attention Network), while keeping the rest of the layers frozen. We propose a basis on which the effect of the untrained layers and their contribution to the generation of embeddings can be predicted. Moreover, we show that network width influences the dissimilarity of node embeddings produced after the initial node features pass through the untrained part of the model. Additionally, we establish a connection between partially trained GCNs and oversmoothing, showing that they are capable of reducing it. We verify our theoretical results experimentally and show the benefits of using deep networks that resist oversmoothing, in a \u201ccold start\u201d scenario, where there is a lack of feature information for unlabeled nodes.<\/jats:p>","DOI":"10.1007\/s10994-025-06865-3","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:18:15Z","timestamp":1755883095000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Partially trained graph convolutional networks resist oversmoothing"],"prefix":"10.1007","volume":"114","author":[{"given":"Dimitrios","family":"Kelesis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris","family":"Fotakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Paliouras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"issue":"3","key":"6865_CR1","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1214\/aop\/1176989118","volume":"21","author":"ZD Bai","year":"1993","unstructured":"Bai, Z. D., & Yin, Y. Q. (1993). Limit of the smallest eigenvalue of a large dimensional sample covariance matrix. The Annals of Probability, 21(3), 1275\u20131294. https:\/\/doi.org\/10.1214\/aop\/1176989118","journal-title":"The Annals of Probability"},{"key":"6865_CR2","doi-asserted-by":"publisher","unstructured":"Bo, D., Wang, X., Shi, C., et\u00a0al. (2021). Beyond low-frequency information in graph convolutional networks. In Thirty-fifth AAAI conference on artificial intelligence, AAAI 2021, thirty-third conference on innovative applications of artificial intelligence, IAAI 2021, The eleventh symposium on educational advances in artificial intelligence, EAAI 2021, virtual event, February 2\u20139, 2021. AAAI Press, pp 3950\u20133957, https:\/\/doi.org\/10.1609\/AAAI.V35I5.16514.","DOI":"10.1609\/AAAI.V35I5.16514"},{"key":"6865_CR3","unstructured":"Cai, C. & Wang, Y. (2020). A note on over-smoothing for graph neural networks. CoRR abs\/2006.13318. arxiv:https:\/\/arxiv.org\/abs\/2006.13318"},{"key":"6865_CR4","unstructured":"Chen, M., Wei, Z., Huang, Z., et\u00a0al. (2020). Simple and deep graph convolutional networks. In Proceedings of the 37th international conference on machine learning, ICML 2020, 13\u201318 July 2020, virtual event, proceedings of machine learning research, vol 119. PMLR, pp. 1725\u20131735, http:\/\/proceedings.mlr.press\/v119\/chen20v.html."},{"key":"6865_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114711","volume":"174","author":"TH Do","year":"2021","unstructured":"Do, T. H., Nguyen, D. M., Bekoulis, G., et al. (2021). Graph convolutional neural networks with node transition probability-based message passing and dropnode regularization. Expert Systems with Applications, 174, Article 114711. https:\/\/doi.org\/10.1016\/j.eswa.2021.114711","journal-title":"Expert Systems with Applications"},{"key":"6865_CR6","unstructured":"Du, S. S., Hou, K., Salakhutdinov, R., et\u00a0al. (2019). Graph neural tangent kernel: Fusing graph neural networks with graph kernels. In H. M. Wallach, H. Larochelle, A. Beygelzimer, et\u00a0al (Eds.) Advances in neural information processing systems 32: Annual conference on neural information processing systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, pp. 5724\u20135734, https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/663fd3c5144fd10bd5ca6611a9a5b92d-Abstract.html."},{"key":"6865_CR7","unstructured":"Glorot, X. & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Y. W. Teh, D. M. Titterington (Eds.) Proceedings of the thirteenth international conference on artificial intelligence and statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 13\u201315, 2010, JMLR Proceedings, vol\u00a09. JMLR.org, pp. 249\u2013256, http:\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"6865_CR8","unstructured":"Hamilton, W. L., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In I. Guyon, U. von Luxburg, S. Bengio, et\u00a0al (Eds.) Advances in neural information processing systems 30: Annual conference on neural information processing systems 2017, December 4\u20139, 2017, Long Beach, CA, USA, pp. 1024\u20131034, https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/5dd9db5e033da9c6fb5ba83c7a7ebea9-Abstract.html."},{"key":"6865_CR9","unstructured":"Hu, W., Fey, M., Zitnik, M., et\u00a0al. (2020). Open graph benchmark: Datasets for machine learning on graphs. In H. Larochelle, M. Ranzato, R. Hadsell, et\u00a0al (Eds.) Advances in neural information processing systems 33: Annual conference on neural information processing systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual, https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/fb60d411a5c5b72b2e7d3527cfc84fd0-Abstract.html."},{"key":"6865_CR10","doi-asserted-by":"publisher","unstructured":"Ju, M., Hou, S., Fan, Y., et\u00a0al. (2022). Adaptive kernel graph neural network. In Thirty-sixth AAAI conference on artificial intelligence, AAAI 2022, thirty-fourth conference on innovative applications of artificial intelligence, IAAI 2022, the twelveth symposium on educational advances in artificial intelligence, EAAI 2022 Virtual Event, February 22\u2013March 1, 2022. AAAI Press, pp 7051\u20137058, https:\/\/doi.org\/10.1609\/AAAI.V36I6.20664.","DOI":"10.1609\/AAAI.V36I6.20664"},{"key":"6865_CR11","doi-asserted-by":"publisher","unstructured":"Kelesis, D., Vogiatzis, D., Katsimpras, G., et\u00a0al. (2023). Reducing oversmoothing in graph neural networks by changing the activation function. In K. Gal, A. Now\u00e9, G. J. Nalepa , et\u00a0al (Eds.) ECAI 2023\u201426th European conference on artificial intelligence, September 30\u2013October 4, 2023, Krak\u00f3w, Poland\u2014Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), Frontiers in Artificial Intelligence and Applications, vol 372. IOS Press, pp. 1231\u20131238. https:\/\/doi.org\/10.3233\/FAIA230400.","DOI":"10.3233\/FAIA230400"},{"key":"6865_CR12","unstructured":"Kipf, T. N. & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In 5th International conference on learning representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, conference track proceedings. OpenReview.net, https:\/\/openreview.net\/forum?id=SJU4ayYgl."},{"key":"6865_CR13","unstructured":"Klicpera, J., Bojchevski, A. & G\u00fcnnemann, S. (2018). Personalized embedding propagation: Combining neural networks on graphs with personalized pagerank. CoRR abs\/1810.05997. Arxiv:http:\/\/arxiv.org\/abs\/1810.05997,"},{"key":"6865_CR14","unstructured":"Klicpera, J., Gro\u00df, J. & G\u00fcnnemann, S. (2020). Directional message passing for molecular graphs. In 8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net, https:\/\/openreview.net\/forum?id=B1eWbxStPH."},{"key":"6865_CR15","unstructured":"Li, Q., Han, Z., & Wu, X. (2018). Deeper insights into graph convolutional networks for semi-supervised learning. In S. A. McIlraith, K. Q. Weinberger (Eds.) Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018. AAAI Press, pp. 3538\u20133545. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16098."},{"key":"6865_CR16","doi-asserted-by":"publisher","unstructured":"Liben-Nowell, D. & Kleinberg, J. M. (2003). The link prediction problem for social networks. In Proceedings of the 2003 ACM CIKM international conference on information and knowledge management, New Orleans, Louisiana, USA, November 2\u20138, 2003. ACM, pp. 556\u2013559, https:\/\/doi.org\/10.1145\/956863.956972.","DOI":"10.1145\/956863.956972"},{"key":"6865_CR17","unstructured":"Luan, S., Zhao, M., Chang, X., et\u00a0al. (2019). Break the ceiling: Stronger multi-scale deep graph convolutional networks. In H. M. Wallach, H. Larochelle, A. Beygelzimer, et\u00a0al (Eds.) Advances in neural information processing systems 32: Annual conference on neural information processing systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, pp. 10943\u201310953, https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/ccdf3864e2fa9089f9eca4fc7a48ea0a-Abstract.html."},{"key":"6865_CR18","unstructured":"Oono, K. & Suzuki, T. (2020). Graph neural networks exponentially lose expressive power for node classification. In 8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net, https:\/\/openreview.net\/forum?id=S1ldO2EFPr."},{"key":"6865_CR19","unstructured":"Rong, Y., Huang, W., Xu, T., et\u00a0al. (2020). Dropedge: Towards deep graph convolutional networks on node classification. In 8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net, https:\/\/openreview.net\/forum?id=Hkx1qkrKPr."},{"key":"6865_CR20","unstructured":"Shchur, O., Mumme, M., Bojchevski, A., et\u00a0al. (2018). Pitfalls of graph neural network evaluation. CoRR abs\/1811.05868. arxiv:https:\/\/arxiv.org\/abs\/1811.05868."},{"key":"6865_CR21","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., et\u00a0al. (2018). Graph attention networks. In 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings. OpenReview.net, https:\/\/openreview.net\/forum?id=rJXMpikCZ."},{"key":"6865_CR22","unstructured":"Wu, F., Jr. A. H. S., Zhang, T., et\u00a0al. (2019). Simplifying graph convolutional networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA, Proceedings of machine learning research, vol.\u00a097. PMLR, pp. 6861\u20136871, http:\/\/proceedings.mlr.press\/v97\/wu19e.html."},{"key":"6865_CR23","unstructured":"Xu, K., Li, C., Tian, Y., et\u00a0al. (2018). Representation learning on graphs with jumping knowledge networks. In J. G. Dy, A. Krause (Eds.) Proceedings of the 35th international conference on machine learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315, 2018, Proceedings of machine learning research, vol.\u00a080. PMLR, pp. 5449\u20135458, http:\/\/proceedings.mlr.press\/v80\/xu18c.html."},{"key":"6865_CR24","doi-asserted-by":"crossref","unstructured":"Zachary, W. W. (1977). An information flow model for conflict and fission in small groups. Journal of an Thropological Research, pp. 452\u2013473. http:\/\/www.jstor.org\/stable\/3629752.","DOI":"10.1086\/jar.33.4.3629752"},{"key":"6865_CR25","unstructured":"Zhang, M. & Chen, Y. (2018). Link prediction based on graph neural networks. In S. Bengio, H. M. Wallach , H. Larochelle, et\u00a0al (Eds.) Advances in neural information processing systems 31: Annual conference on neural information processing systems 2018, NeurIPS 2018, December 3\u20138, 2018, Montr\u00e9al, Canada, pp. 5171\u20135181. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/53f0d7c537d99b3824f0f99d62ea2428-Abstract.html."},{"key":"6865_CR26","unstructured":"Zhang, M., Cui, Z., Neumann, M., et\u00a0al. (2018). An end-to-end deep learning architecture for graph classification. In S. A. McIlraith, K. Q. Weinberger (Eds.) Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018. AAAI Press, pp. 4438\u20134445, https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17146."},{"key":"6865_CR27","unstructured":"Zhao, L. & Akoglu, L. (2020). Pairnorm: Tackling oversmoothing in gnns. In 8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net, https:\/\/openreview.net\/forum?id=rkecl1rtwB."},{"key":"6865_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, C., Li, Q., Li, C., et\u00a0al. (2023). A comprehensive survey on pretrained foundation models: A history from BERT to chatgpt. CoRR abs\/2302.09419. https:\/\/doi.org\/10.48550\/ARXIV.2302.09419.","DOI":"10.48550\/ARXIV.2302.09419"},{"key":"6865_CR29","unstructured":"Zhou, K., Huang, X., Zha, D., et\u00a0al. (2021). Dirichlet energy constrained learning for deep graph neural networks. CoRR abs\/2107.02392. arxiv:https:\/\/arxiv.org\/abs\/2107.02392."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06865-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06865-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06865-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T20:56:17Z","timestamp":1759870577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06865-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":29,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6865"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06865-3","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"26 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"211"}}