{"id":"https://openalex.org/W7163869300","doi":"https://doi.org/10.48550/arxiv.2606.06861","title":"Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks","display_name":"Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163869300","doi":"https://doi.org/10.48550/arxiv.2606.06861"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2606.06861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138121185","display_name":"Ziyuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ziyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029941961","display_name":"Uwe Jaekel","orcid":"https://orcid.org/0000-0002-4275-1430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaekel, Uwe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138186008","display_name":"Babette Dellen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dellen, Babette","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/T11948","display_name":"Machine Learning in Materials Science","score":0.18790000677108765,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.18790000677108765,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.1340000033378601,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11779999732971191,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.7598999738693237},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7468000054359436},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6162999868392944},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.6039999723434448},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5493999719619751},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43560001254081726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3962000012397766}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7598999738693237},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7468000054359436},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040999889373779},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5493999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382000207901001},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42010000348091125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C203223496","wikidata":"https://www.wikidata.org/wiki/Q4681344","display_name":"Additive model","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32330000400543213},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"nonlinear":[1],"feature":[2,73],"interactions":[3,18],"is":[4],"crucial":[5],"in":[6,127],"science":[7],"and":[8,29,63,75,81,85,107,124,130],"engineering,":[9],"yet":[10],"standard":[11],"multilayer":[12],"perceptrons":[13],"(MLPs)":[14],"often":[15],"capture":[16],"such":[17],"only":[19],"implicitly,":[20],"leading":[21],"to":[22,45,71],"entangled":[23],"representations":[24],"that":[25,37,102],"can":[26],"impair":[27],"robustness":[28,70,123],"interpretability.":[30,133],"We":[31,53],"investigate":[32],"product-unit":[33],"residual":[34,43],"networks":[35],"(PURe)":[36],"integrate":[38],"multiplicative":[39],"product":[40],"units":[41],"with":[42],"connections":[44],"explicitly":[46],"model":[47],"cross-feature":[48],"couplings":[49],"while":[50],"stabilizing":[51],"optimization.":[52],"conduct":[54],"a":[55,89],"systematic":[56],"evaluation":[57],"on":[58],"an":[59],"interaction-driven":[60],"synthetic":[61],"benchmark":[62],"two":[64],"real-world":[65],"datasets,":[66],"assessing":[67],"predictive":[68],"accuracy,":[69,94],"Gaussian":[72],"noise,":[74],"performance":[76],"under":[77,88],"limited":[78],"training":[79],"data,":[80],"we":[82],"compare":[83],"real-":[84],"complex-valued":[86],"variants":[87],"matched":[90],"parameter":[91],"budget.":[92],"Beyond":[93],"SHapley":[95],"Additive":[96],"exPlanations":[97],"(SHAP)-based":[98],"interaction":[99,110],"analyses":[100],"show":[101],"PURe":[103,116],"learns":[104],"more":[105],"concentrated":[106],"structurally":[108],"coherent":[109],"patterns":[111],"than":[112],"MLP":[113],"baselines.":[114],"Overall,":[115],"achieves":[117],"competitive":[118],"or":[119],"improved":[120],"performance,":[121],"better":[122],"sample":[125],"efficiency":[126],"low-data":[128],"regimes,":[129],"enhanced":[131],"interaction-level":[132]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-09T00:00:00"}