{"id":"https://openalex.org/W7137952481","doi":"https://doi.org/10.48550/arxiv.2603.14946","title":"Spiking Layer-Adaptive Magnitude-based Pruning","display_name":"Spiking Layer-Adaptive Magnitude-based Pruning","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137952481","doi":"https://doi.org/10.48550/arxiv.2603.14946"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14946","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":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.2603.14946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012218055","display_name":"Junqiao Wang","orcid":"https://orcid.org/0009-0005-4298-5885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Junqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050869096","display_name":"Zhehang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zhehang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080351177","display_name":"Yuqi Ouyang","orcid":"https://orcid.org/0000-0002-1611-1114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Yuqi","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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9182000160217285,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.048900000751018524,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.864799976348877},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5056999921798706},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4717999994754791},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3921999931335449},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37439998984336853},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.3619999885559082}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.864799976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762999892234802},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745999872684479},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3619999885559082},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14946","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":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.2603.14946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14946","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.9107186198234558,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spiking":[0,50],"Neural":[1],"Networks":[2],"(SNNs)":[3],"provide":[4],"energy-efficient":[5],"computation":[6],"but":[7],"their":[8],"deployment":[9],"is":[10,105],"constrained":[11],"by":[12,67],"dense":[13],"connectivity":[14,136],"and":[15,38,75,114,126,137,146],"high":[16],"spiking":[17,138],"operation":[18,139],"costs.":[19],"Existing":[20],"magnitude-based":[21],"pruning":[22,57,63,97,116],"strategies,":[23],"when":[24],"naively":[25],"applied":[26],"to":[27,30,43,64,94],"SNNs,":[28],"fail":[29],"account":[31],"for":[32,119],"temporal":[33,65,83,108],"accumulation,":[34],"non-uniform":[35],"timestep":[36],"contributions,":[37],"membrane":[39],"stability,":[40],"often":[41],"leading":[42],"severe":[44],"performance":[45],"degradation.":[46],"This":[47],"paper":[48],"proposes":[49],"Layer-Adaptive":[51],"Magnitude-based":[52],"Pruning":[53],"(SLAMP),":[54],"a":[55,82],"theory-guided":[56],"framework":[58],"that":[59,92,132],"generalizes":[60],"layer-adaptive":[61,96],"magnitude":[62,115],"SNNs":[66],"explicitly":[68],"controlling":[69],"worst-case":[70],"output":[71],"distortion":[72],"across":[73],"layers":[74],"timesteps.":[76],"SLAMP":[77,133],"formulates":[78],"sparsity":[79,112],"allocation":[80],"as":[81],"distortion-constrained":[84],"optimization":[85],"problem,":[86],"yielding":[87],"time-aware":[88],"layer":[89],"importance":[90],"scores":[91],"reduce":[93],"conventional":[95],"in":[98],"single-timestep":[99],"limit.":[100],"An":[101],"efficient":[102,145],"two-stage":[103],"procedure":[104],"derived,":[106],"combining":[107],"score":[109],"estimation,":[110],"global":[111],"allocation,":[113],"with":[117],"retraining":[118],"stability":[120],"recovery.":[121],"Experiments":[122],"on":[123],"CIFAR10,":[124],"CIFAR100,":[125],"the":[127],"event-based":[128],"CIFAR10-DVS":[129],"datasets":[130],"demonstrate":[131],"achieves":[134],"substantial":[135],"reductions":[140],"while":[141],"preserving":[142],"accuracy,":[143],"enabling":[144],"deployable":[147],"SNN":[148],"inference.":[149]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}