{"id":"https://openalex.org/W7163188284","doi":"https://doi.org/10.48550/arxiv.2606.00559","title":"Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction","display_name":"Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163188284","doi":"https://doi.org/10.48550/arxiv.2606.00559"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00559","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":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.2606.00559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129658745","display_name":"Jiafu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiafu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137686673","display_name":"Chao Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137703517","display_name":"Chenyang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137625920","display_name":"Zhengfeng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhengfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123342475","display_name":"Kecheng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Kecheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137655665","display_name":"Chenhao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137627189","display_name":"Yi Wang","orcid":"https://orcid.org/0009-0001-5647-7110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747627","display_name":"Yiwei Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Yiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668074","display_name":"Wanqin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wanqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5098550523","display_name":"Irene Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Irene","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/T10036","display_name":"Advanced Neural Network Applications","score":0.14959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.14959999918937683,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.094200000166893,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08290000259876251,"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/encoder","display_name":"Encoder","score":0.8047999739646912},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6650999784469604},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.570900022983551},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48660001158714294},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4684000015258789},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42640000581741333}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8047999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.570900022983551},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00559","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00559","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":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":{"Neural":[0],"algorithmic":[1,63,85,133,145,258],"reasoning":[2,259],"has":[3,96,110],"emerged":[4],"as":[5,35],"a":[6,36,149,208],"popular":[7],"research":[8],"direction.":[9],"It":[10],"aims":[11,153],"to":[12,16,55,139,154,170,232,246],"train":[13],"neural":[14,144,190],"networks":[15],"mimic":[17],"the":[18,27,44,61,76,82,88,100,102,105,122,156,168,175,186,203,225,230,244,252],"step-by-step":[19],"behavior":[20],"of":[21,29,38,80,104,124,188,224,254],"classical":[22],"rule-based":[23],"algorithms.":[24],"More":[25],"specifically,":[26],"execution":[28,49],"such":[30,126],"algorithms":[31],"can":[32],"be":[33],"abstracted":[34],"sequence":[37],"states,":[39,81],"where":[40,75],"each":[41],"state":[42,57,158],"represents":[43],"intermediate":[45],"outcome":[46],"after":[47],"an":[48,72,221],"step.":[50],"The":[51],"training":[52,184],"objective":[53],"is":[54],"generate":[56],"sequences":[58],"that":[59,152,179,198,228,240],"replicate":[60],"underlying":[62],"process.":[64],"A":[65],"common":[66],"framework":[67],"for":[68,131,143],"this":[69,181],"task":[70,166,182,227],"adopts":[71],"encoder-processor-decoder":[73],"architecture,":[74],"encoder":[77,106,141,169,231,245],"learns":[78],"representations":[79,127,142],"processor":[83],"simulates":[84],"steps,":[86],"and":[87,219],"decoder":[89],"reconstructs":[90],"output":[91],"states.":[92],"While":[93],"prior":[94],"work":[95],"focused":[97],"on":[98,117,192,257],"improving":[99],"processor,":[101],"role":[103],"in":[107],"representation":[108],"learning":[109,218],"received":[111],"little":[112],"attention.":[113],"Most":[114],"methods":[115],"rely":[116],"simple":[118],"MLP":[119],"encoders,":[120],"raising":[121],"question":[123],"whether":[125],"are":[128],"sufficiently":[129],"informative":[130],"supporting":[132],"reasoning.":[134,146],"This":[135,163],"paper":[136],"investigates":[137],"how":[138],"improve":[140],"We":[147,177],"propose":[148],"reconstruction":[150,165],"module":[151],"recover":[155],"input":[157],"from":[159,216],"its":[160],"encoded":[161],"representation.":[162],"auxiliary":[164,226],"encourages":[167,229],"retain":[171],"critical":[172],"information":[173],"about":[174],"input.":[176],"demonstrate":[178],"incorporating":[180],"during":[183],"improves":[185],"performance":[187,253],"existing":[189,255],"architectures":[191],"standard":[193],"benchmarks.":[194],"Furthermore,":[195],"we":[196,213],"observe":[197],"current":[199],"encoders":[200],"often":[201],"underutilize":[202],"correlations":[204],"among":[205],"features":[206],"within":[207],"state.":[209],"To":[210],"address":[211],"this,":[212],"draw":[214],"inspiration":[215],"self-supervised":[217],"design":[220],"enhanced":[222],"variant":[223],"capture":[233],"intra-state":[234],"feature":[235],"dependencies.":[236],"Experimental":[237],"results":[238],"show":[239],"our":[241],"method":[242],"enables":[243],"learn":[247],"richer":[248],"representations,":[249],"thereby":[250],"enhancing":[251],"processors":[256],"tasks.":[260]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}