{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:13:47Z","timestamp":1780766027469,"version":"3.54.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889874","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Redesigning graph filter-based GNNs to relax the homophily assumption"],"prefix":"10.1109","author":[{"given":"Samuel","family":"Rey","sequence":"first","affiliation":[{"name":"King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madeline","family":"Navarro","sequence":"additional","affiliation":[{"name":"Rice University,Dept. of Electrical and Computer Engineering,Houston,TX,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor M.","family":"Tenorio","sequence":"additional","affiliation":[{"name":"King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santiago","family":"Segarra","sequence":"additional","affiliation":[{"name":"Rice University,Dept. of Electrical and Computer Engineering,Houston,TX,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio G.","family":"Marques","sequence":"additional","affiliation":[{"name":"King Juan Carlos University,Dept. of Signal Theory and Communications,Madrid,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref4","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3369017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447223"},{"key":"ref8","article-title":"Bridging the gap between spectral and spatial domains in graph neural networks","author":"Balcilar","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00169"},{"key":"ref10","article-title":"Graph neural networks for graphs with heterophily: A survey","author":"Zheng","year":"2024"},{"key":"ref11","article-title":"Diffusion-convolutional neural networks","volume":"29","author":"Atwood","year":"2016","journal-title":"Advances in Neural Info. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482225"},{"key":"ref14","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Intl. Conf. on Machine Learning (ICML)","volume":"80","author":"Xu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF53345.2021.9723282"},{"key":"ref16","article-title":"Revisiting graph neural networks: All we have is low-pass filters","author":"NT","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054830"},{"key":"ref18","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume-title":"Intl. Conf. on Machine Learning (ICML)","volume":"162","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.09.042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9048767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3055400"},{"key":"ref22","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Intl. Conf. on Machine Learning (ICML)","volume":"97","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3349788"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3014591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3300632"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3223552"},{"key":"ref27","article-title":"Combining neural networks with personalized PageRank for classification on graphs","volume-title":"Int. Conf. Learn. Representations","author":"Gasteiger"},{"key":"ref28","first-page":"9224","article-title":"Improving graph neural networks with learnable propagation operators","volume-title":"Intl. Conf. on Machine Learning (ICML)","volume":"202","author":"Eliasof"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF60004.2024.10943014"},{"key":"ref30","article-title":"SIGN: Scalable inception graph neural networks","author":"Frasca","year":"2020"},{"key":"ref31","first-page":"14556","article-title":"Scalable graph neural networks via bidirectional propagation","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Info. Process. Syst."},{"key":"ref32","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2321121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2703660"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2018.8445934"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/267"},{"key":"ref37","first-page":"841","article-title":"N-GCN: Multi-scale graph convolution for semi-supervised node classification","volume-title":"Uncertainty in Artif. Intell. Conf","volume":"115","author":"Abu-El-Haija"},{"key":"ref38","article-title":"Analyzing the expressive power of graph neural networks in a spectral perspective","volume-title":"Int. Conf. Learn. Representations","author":"Balcilar"},{"key":"ref39","article-title":"Is homophily a necessity for graph neural networks?","volume-title":"Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"issue":"3.6","key":"ref41","first-page":"2","article-title":"Learning to extract symbolic knowledge from the World Wide Web","volume-title":"AAAI Conf. on Artif. Intell","volume":"3","author":"Craven"},{"key":"ref42","first-page":"20887","article-title":"Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods","volume-title":"Conf. Neural Inform. Process. Syst","volume":"34","author":"Lim"},{"key":"ref43","article-title":"Graph attention networks","volume-title":"Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref44","article-title":"Inductive representation learning on large graphs","volume-title":"Conf. Neural Inform. Process. Syst","volume":"30","author":"Hamilton"},{"key":"ref45","article-title":"How powerful are graph neural networks?","volume-title":"Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref46","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Conf. Neural Inform. Process. Syst","volume":"29","author":"Defferrard"},{"key":"ref47","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","volume-title":"Int. Conf. Learn. Representations","author":"Gasteiger"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889874.pdf?arnumber=10889874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:31Z","timestamp":1774416151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889874","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}