{"id":"https://openalex.org/W7129055715","doi":"https://doi.org/10.48550/arxiv.2602.13140","title":"FlashSchNet: Fast and Accurate Coarse-Grained Neural Network Molecular Dynamics","display_name":"FlashSchNet: Fast and Accurate Coarse-Grained Neural Network Molecular Dynamics","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129055715","doi":"https://doi.org/10.48550/arxiv.2602.13140"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.13140","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126147223","display_name":"Pingzhi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Pingzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102920218","display_name":"Hongxuan Li","orcid":"https://orcid.org/0000-0003-4760-2909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123180448","display_name":"Zirui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zirui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046672665","display_name":"Xingcheng Lin","orcid":"https://orcid.org/0000-0002-9378-6174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xingcheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126124186","display_name":"Tianlong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianlong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5126147223"],"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":0.6007000207901001,"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":0.6007000207901001,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08190000057220459,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.04670000076293945,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5088000297546387},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4916999936103821},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45399999618530273},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.40369999408721924},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3864000141620636},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3813999891281128},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.3776000142097473},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3776000142097473},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3734000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49399998784065247},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.13140","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.13140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13140","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.13140","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Graph":[0],"neural":[1],"network":[2],"(GNN)":[3],"potentials":[4],"such":[5],"as":[6],"SchNet":[7,170],"improve":[8,175],"the":[9,164],"accuracy":[10,179,226],"and":[11,33,53,60,68,90,102,120,148,155,227],"transferability":[12],"of":[13,145,214],"molecular":[14],"dynamics":[15],"(MD)":[16],"simulation":[17,193],"by":[18,142],"learning":[19],"many-body":[20],"interactions,":[21],"but":[22],"remain":[23],"slower":[24],"than":[25,208],"classical":[26,218],"force":[27,219],"fields":[28,220],"due":[29],"to":[30,122,173],"fragmented":[31],"kernels":[32],"memory-bound":[34],"pipelines":[35],"that":[36,41,162],"underutilize":[37],"GPUs.":[38],"We":[39,63],"show":[40],"a":[42,94,143,182],"missing":[43],"principle":[44],"is":[45],"making":[46],"GNN-MD":[47,72],"IO-aware,":[48],"carefully":[49],"accounting":[50],"for":[51],"reads":[52],"writes":[54,141],"between":[55],"GPU":[56],"high-bandwidth":[57],"memory":[58],"(HBM)":[59],"on-chip":[61],"SRAM.":[62],"present":[64],"FlashSchNet,":[65],"an":[66],"efficient":[67],"accurate":[69],"IO-aware":[70],"SchNet-style":[71],"framework":[73],"built":[74],"on":[75,199],"four":[76],"techniques:":[77],"(1)":[78],"flash":[79,110,130],"radial":[80],"basis,":[81],"which":[82,113,132],"fuses":[83,114],"pairwise":[84],"distance":[85,100],"computation,":[86],"Gaussian":[87],"basis":[88,107],"expansion,":[89],"cosine":[91],"envelope":[92],"into":[93],"single":[95,183],"tiled":[96],"pass,":[97],"computing":[98],"each":[99],"once":[101],"reusing":[103],"it":[104],"across":[105],"all":[106],"functions;":[108],"(2)":[109],"message":[111],"passing,":[112],"cutoff,":[115],"neighbor":[116],"gather,":[117],"filter":[118],"multiplication,":[119],"reduction":[121,213],"avoid":[123],"materializing":[124],"edge":[125],"tensors":[126],"in":[127,152,169],"HBM;":[128],"(3)":[129],"aggregation,":[131],"reformulates":[133],"scatter-add":[134],"via":[135],"CSR":[136],"segment":[137],"reduce,":[138],"reducing":[139],"atomic":[140],"factor":[144],"feature":[146],"dimension":[147],"enabling":[149],"contention-free":[150],"accumulation":[151],"both":[153],"forward":[154],"backward":[156],"passes;":[157],"(4)":[158],"channel-wise":[159],"16-bit":[160],"quantization":[161],"exploits":[163],"low":[165],"per-channel":[166],"dynamic":[167],"range":[168],"MLP":[171],"weights":[172],"further":[174],"throughput":[176,194],"with":[177,211],"negligible":[178],"loss.":[180],"On":[181],"NVIDIA":[184],"RTX":[185],"PRO":[186],"6000,":[187],"FlashSchNet":[188],"achieves":[189],"1000":[190],"ns/day":[191],"aggregate":[192],"over":[195],"64":[196],"parallel":[197],"replicas":[198],"coarse-grained":[200],"(CG)":[201],"protein":[202],"containing":[203],"269":[204],"beads":[205],"(6.5x":[206],"faster":[207],"CGSchNet":[209],"baseline":[210],"80%":[212],"peak":[215],"memory),":[216],"surpassing":[217],"(e.g.":[221],"MARTINI)":[222],"while":[223],"retaining":[224],"SchNet-level":[225],"transferability.":[228]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-17T00:00:00"}