{"id":"https://openalex.org/W7163124516","doi":"https://doi.org/10.48550/arxiv.2606.01660","title":"Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs","display_name":"Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163124516","doi":"https://doi.org/10.48550/arxiv.2606.01660"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.01660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.01660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029785504","display_name":"Zichao Yue","orcid":"https://orcid.org/0009-0003-8585-5947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Zichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137711847","display_name":"Zhiru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhiru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6211000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6211000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/news-aggregator","display_name":"News aggregator","score":0.6955999732017517},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5710999965667725},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5353999733924866},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44679999351501465},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/chebyshev-filter","display_name":"Chebyshev filter","score":0.38760000467300415},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.37310001254081726}],"concepts":[{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.6955999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40560001134872437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C21424316","wikidata":"https://www.wikidata.org/wiki/Q718621","display_name":"Chebyshev filter","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.01660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.01660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-propagation":[0],"graph":[1],"neural":[2],"networks":[3],"(PPGNNs)":[4],"push":[5],"all":[6,179],"graph-dependent":[7],"computation":[8],"into":[9],"a":[10,47,61,65,116,136,141,157,199],"preprocessing":[11],"step":[12],"and":[13,81,125,154,164,175],"train":[14],"only":[15],"on":[16,44,172,178],"the":[17,129,184],"resulting":[18],"dense":[19],"hop":[20,36],"features,":[21],"which":[22,140],"makes":[23],"them":[24],"highly":[25],"scalable.":[26],"A":[27],"puzzle":[28],"in":[29,73,87,119,139],"this":[30,58],"regime":[31,118],"is":[32,149],"that":[33,96,108],"more":[34],"complex":[35],"aggregators":[37],"do":[38],"not":[39],"reliably":[40],"outperform":[41],"simpler":[42],"ones:":[43],"many":[45],"benchmarks,":[46,166,182],"plain":[48],"MLP-based":[49,91],"aggregator":[50,89],"matches":[51],"or":[52],"beats":[53],"hop-attention":[54],"variants.":[55],"We":[56,133],"revisit":[57],"behavior":[59],"from":[60],"graph-filter":[62],"perspective.":[63],"Over":[64],"precomputed":[66],"diffusion":[67],"basis,":[68],"existing":[69],"PPGNNs":[70],"differ":[71],"mainly":[72],"how":[74],"filter":[75,147,196],"coefficients":[76],"are":[77,97,109],"shared":[78,99,111],"across":[79,100,112],"nodes":[80,153],"feature":[82],"channels,":[83],"rather":[84],"than":[85],"simply":[86],"raw":[88],"capacity.":[90],"architectures":[92,104],"learn":[93,105],"channel-dependent":[94],"filters":[95],"largely":[98,110],"nodes,":[101],"while":[102],"hop-attention-based":[103],"node-dependent":[106],"mixtures":[107],"channels.":[113],"This":[114],"reveals":[115],"missing":[117],"standard":[120],"PPGNN":[121,138,170],"designs:":[122],"joint":[123,194],"node-":[124],"channel-adaptive":[126],"filtering":[127],"under":[128],"pre-propagation":[130],"computational":[131],"contract.":[132],"propose":[134],"FilterMoE,":[135],"mixture-of-experts":[137],"small":[142],"bank":[143],"of":[144],"learnable":[145],"Chebyshev":[146],"experts":[148],"routed":[150],"jointly":[151],"over":[152],"channels":[155],"by":[156,188],"3D":[158],"gating":[159],"tensor.":[160],"Across":[161],"eleven":[162],"homophilic":[163],"heterophilic":[165],"FilterMoE":[167],"outperforms":[168],"strong":[169],"baselines":[171],"nine":[173],"datasets":[174],"ranks":[176],"first":[177],"three":[180],"large-scale":[181],"improving":[183],"average":[185],"test":[186],"score":[187],"1.53":[189],"points.":[190],"These":[191],"results":[192],"establish":[193],"node-channel":[195],"routing":[197],"as":[198],"robust":[200],"alternative":[201],"to":[202],"dataset-specific":[203],"hop-aggregator":[204],"selection.":[205]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-03T00:00:00"}