{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T12:48:03Z","timestamp":1786020483252,"version":"3.56.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013209","name":"Hellenic Foundation for Research and Innovation","doi-asserted-by":"publisher","award":["10860"],"award-info":[{"award-number":["10860"]}],"id":[{"id":"10.13039\/501100013209","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NCSR - Demokritos Library"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The performance of Graph Neural Networks (GNNs) diminishes as their depth increases. That is mainly attributed to oversmoothing, which leads to similar node representations through repeated graph convolutions. To enable deep GNNs, several approaches have been proposed, among which the use of residual connections. Residual connections have proven effective in benchmark datasets, but the way in which they improve the performance of deep GNNs has not been fully studied. We show that residual connections force the model to focus on the local neighborhood of graph nodes, making the GNN equivalent to the sum of shallow GCNs. We explain theoretically why this is the case and verify the theoretical results experimentally. However, our findings raise the question of whether residual connections are helpful in cases where deep networks are necessary. We assess this experimentally, in two situations: (a) in the presence of the \u201ccold start\" problem, i.e. when there is no feature information about unlabeled nodes; and (b) in a new synthetic dataset of controllable long-interactions. These experiments highlight the drawbacks of GNNs using residual connections, while showing that simpler methods can be more effective.<\/jats:p>","DOI":"10.1007\/s10994-025-06822-0","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T16:47:15Z","timestamp":1752252435000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Analyzing the effect of residual connections to oversmoothing in graph neural networks"],"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":[[2025,7,11]]},"reference":[{"key":"6822_CR1","unstructured":"Alon, U., & Yahav, E. (2020). On the bottleneck of graph neural networks and its practical implications. CoRR abs\/2006.05205. arXiv: 2006.05205."},{"key":"6822_CR2","unstructured":"Cai, C., & Wang, Y. (2020). A note on over-smoothing for graph neural networks. CoRR abs\/2006.13318. arXiv: 2006.13318."},{"key":"6822_CR3","unstructured":"Chen, M., Wei, Z., Huang, Z., Ding, B., & Li, Y. (2020). Simple and deep graph convolutional networks. In: Proceedings of the 37th International conference on machine learning, ICML 2020, 13-18 July 2020, virtual event, proceedings of machine learning research (vol. 119, pp. 1725\u20131735). PMLR. http:\/\/proceedings.mlr.press\/v119\/chen20v.html."},{"key":"6822_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/9783527617234","volume-title":"Methods of mathematical physics","author":"R Courant","year":"1989","unstructured":"Courant, R., & Hilbert, D. (1989). Methods of mathematical physics (Vol. 1). Wiley."},{"issue":"200","key":"6822_CR5","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman, M. (1937). The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the American Statistical Association, 32(200), 675\u2013701. https:\/\/doi.org\/10.1080\/01621459.1937.10503522","journal-title":"Journal of the American Statistical Association"},{"key":"6822_CR6","doi-asserted-by":"publisher","unstructured":"Gong, L., & Cheng, Q. (2019). Exploiting edge features for graph neural networks. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019 (pp. 9211\u20139219). Computer Vision Foundation\/IEEE. https:\/\/doi.org\/10.1109\/CVPR.2019.00943, http:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Gong_Exploiting_Edge_Features_for_Graph_Neural_Networks_CVPR_2019_paper.html.","DOI":"10.1109\/CVPR.2019.00943"},{"key":"6822_CR7","unstructured":"Gu, F., Chang, H., Zhu, W., Sojoudi, S., & El Ghaoui, L. (2020). Implicit graph neural networks. 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 6-12, 2020, virtual. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/8b5c8441a8ff8e151b191c53c1842a38-Abstract.html."},{"key":"6822_CR8","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016 (pp. 770\u2013778). IEEE Computer Society. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"6822_CR9","unstructured":"Hu, W., Fey, M., Zitnik, M., Dong, Y., Ren, H., Liu, B., Catasta, M., & Leskovec, J. (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 6-12, 2020, virtual. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/fb60d411a5c5b72b2e7d3527cfc84fd0-Abstract.html"},{"key":"6822_CR10","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 24-26, 2017, conference track proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=SJU4ayYgl."},{"key":"6822_CR11","unstructured":"Klicpera, J., Bojchevski, A., & G\u00fcnnemann, S. (2019). Predict then propagate: Graph neural networks meet personalized pagerank. In: 7th international conference on learning representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=H1gL-2A9Ym."},{"key":"6822_CR12","doi-asserted-by":"crossref","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 2-7, 2018 (pp. 3538\u20133545). AAAI Press. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16098","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"6822_CR13","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 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=S1ldO2EFPr."},{"key":"6822_CR14","unstructured":"Rong, Y., Huang, W., Xu, T., & Huang J. (2020). Dropedge: Towards deep graph convolutional networks on node classification. In: 8th International conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=Hkx1qkrKPr."},{"key":"6822_CR15","doi-asserted-by":"publisher","unstructured":"Roth, A., & Liebig, T. (2022). Transforming pagerank into an infinite-depth graph neural network. CoRR abs\/2207.00684. https:\/\/doi.org\/10.48550\/arXiv.2207.00684, arXiv: 2207.00684.","DOI":"10.48550\/arXiv.2207.00684"},{"key":"6822_CR16","unstructured":"Shchur, O., Mumme, M., Bojchevski, A., & G\u00fcnnemann, S. (2018). Pitfalls of graph neural network evaluation. CoRR abs\/1811.05868. arXiv: 1811.05868."},{"key":"6822_CR17","unstructured":"Thekumparampil, K. K., Wang, C., Oh, S., & Li, L.-J. (2018). Attention-based graph neural network for semi-supervised learning. CoRR abs\/1803.03735. arXiv: 1803.03735."},{"key":"6822_CR18","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2018). Graph attention networks. In: 6th international conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, conference track proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=rJXMpikCZ."},{"key":"6822_CR19","doi-asserted-by":"publisher","unstructured":"Wang, Z., Chen, J., & Chen, H. (2021). EGAT: Edge-featured graph attention network. In: I. Farkas, P. Masulli, & S. Otte et\u00a0al. (Eds.), Artificial neural networks and machine learning - ICANN 2021 - 30th International conference on artificial neural networks, Bratislava, Slovakia, September 14-17, 2021, Proceedings, Part I, Lecture Notes in Computer Science (vol. 12891, pp. 253\u2013264). Springer. https:\/\/doi.org\/10.1007\/978-3-030-86362-3_21.","DOI":"10.1007\/978-3-030-86362-3_21"},{"key":"6822_CR20","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/BF01456804","volume":"71","author":"H Weyl","year":"1912","unstructured":"Weyl, H. (1912). Das asymptotische verteilungsgesetz der eigenwerte linearer partieller differentialgleichungen (mit einer anwendung auf die theorie der hohlraumstrahlung). Mathematische Annalen, 71, 441\u2013479.","journal-title":"Mathematische Annalen"},{"key":"6822_CR21","unstructured":"Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.-I., & Jegelka, S. (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 10-15, 2018, Proceedings of Machine Learning Research (vol.\u00a080, pp. 5449\u20135458). PMLR. http:\/\/proceedings.mlr.press\/v80\/xu18c.html."},{"key":"6822_CR22","unstructured":"Zhao, L., & Akoglu, L. (2020). Pairnorm: Tackling oversmoothing in gnns. In: 8th international conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=rkecl1rtwB."},{"key":"6822_CR23","unstructured":"Zhou, K., Huang, X., Zha, D., Chen, R., Li, L., Choi, S.-H., & Hu, X. (2021). Dirichlet energy constrained learning for deep graph neural networks. In: M. Ranzato, A. Beygelzimer, & Y. N. Dauphin et\u00a0al. (Eds.), Advances in neural information processing systems 34: Annual conference on neural information processing systems 2021, NeurIPS 2021, December 6-14, 2021, virtual (pp. 21834\u201321846). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/b6417f112bd27848533e54885b66c288-Abstract.html."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06822-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06822-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06822-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T07:53:51Z","timestamp":1757231631000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06822-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":23,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["6822"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06822-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]},"assertion":[{"value":"11 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"184"}}