{"id":"https://openalex.org/W6940897346","doi":"https://doi.org/10.13016/dspace/mlfd-eyla","title":"Understanding and Enriching the Algorithmic Reasoning Capabilities of Deep Learning Models","display_name":"Understanding and Enriching the Algorithmic Reasoning Capabilities of Deep Learning Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6940897346","doi":"https://doi.org/10.13016/dspace/mlfd-eyla"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/30963","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/30963","pdf_url":"https://drum.lib.umd.edu/bitstreams/8a0ba12c-c438-4a37-8f29-82a4155a0a1d/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://drum.lib.umd.edu/bitstreams/8a0ba12c-c438-4a37-8f29-82a4155a0a1d/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Jingling","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Jingling","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":true,"primary_topic":{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5691999793052673,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5691999793052673,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.09080000221729279,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10825","display_name":"Plant Pathogens and Fungal Diseases","score":0.055799998342990875,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6047000288963318},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5544000267982483},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.44830000400543213},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.43790000677108765},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42320001125335693},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.38440001010894775},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.382099986076355},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.3781999945640564},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6917999982833862},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.43790000677108765},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.29840001463890076},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/30963","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/30963","pdf_url":"https://drum.lib.umd.edu/bitstreams/8a0ba12c-c438-4a37-8f29-82a4155a0a1d/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"doi:10.13016/dspace/mlfd-eyla","is_oa":true,"landing_page_url":"https://doi.org/10.13016/dspace/mlfd-eyla","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"thesis"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/30963","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/30963","pdf_url":"https://drum.lib.umd.edu/bitstreams/8a0ba12c-c438-4a37-8f29-82a4155a0a1d/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6940897346.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0,616],"to":[1,7,24,28,47,115,148,169,179,198,206,306,351,409,438,454,470,542,592,600,627],"reason":[2],"is":[3,467,476],"an":[4],"essential":[5],"step":[6],"achieving":[8],"general":[9],"intelligence.":[10],"My":[11],"research":[12],"has":[13,73],"been":[14],"focusing":[15],"on":[16,280,391,419],"empowering":[17],"deep":[18,78],"learning":[19,79,154,591],"models":[20,46,155],"with":[21,97,134,273,458,479,603,624],"the":[22,45,55,69,121,135,150,157,200,250,285,294,323,326,344,358,401,424,447,459,480,484,520,547,551,567,571,578,581,584,630],"abilities":[23],"generalize":[25,221],"efficiently,":[26],"extrapolate":[27,340,366,377],"out-of-distribution":[29],"data,":[30],"learn":[31,321,593],"under":[32,211,335,565],"noisy":[33,439,471],"labels,":[34],"and":[35,67,84,103,164,166,215,246,298,338,398,486,491,499,586],"make":[36,170,180,207],"better":[37,181,208,222,628],"sequential":[38,182,209,513,563],"decisions":[39,210],"---":[40],"all":[41],"of":[42,51,107,152,159,190,252,296,325,403,528,580,597,611],"these":[43,109,604],"require":[44],"have":[48,525],"varying":[49],"levels":[50],"reasoning":[52,56,71,118,140,160,237,269,282],"capabilities.":[53],"As":[54],"process":[57],"can":[58,112,302,375,507,588],"be":[59],"described":[60],"as":[61,240],"a":[62,89,100,128,139,188,218,253,308,312,318,378,389,431,451,465,526,609],"step-by-step":[63],"algorithmic":[64,70,91,122,136,143,255,304,407],"procedure,":[65],"understanding":[66,106],"enriching":[68],"capabilities":[72],"drawn":[74],"increasing":[75],"attention":[76],"in":[77,99,138,156,405,423,522,534,557,583],"communities.":[80],"To":[81,329,441],"bridge":[82],"algorithms":[83,98,205,613,623],"neural":[85,95,129,319,432,496],"networks,":[86],"we":[87,145,175,186,233,291,301,332,371,395,445,487,508,554,587,607,619],"propose":[88],"framework,":[90,174,290],"alignment,":[92,144],"which":[93,185,195,275,336,394],"connects":[94],"networks":[96],"novel":[101],"manner":[102],"advances":[104],"our":[105],"how":[108,126,178,300,429,506],"two":[110],"fields":[111],"work":[113,532],"together":[114],"solve":[116],"complex":[117],"tasks.":[119,283],"Intuitively,":[120],"alignment":[123,305],"framework":[124,449],"evaluates":[125],"well":[127,272,533],"network's":[130,452],"computation":[131],"structure":[132,137,220],"aligns":[133],"process.":[141],"Utilizing":[142],"are":[146,574],"able":[147],"understand":[149],"limitations":[151,295],"machine":[153,590],"context":[158],"(e.g.,":[161,412],"generalization,":[162],"extrapolation,":[163],"robustness)":[165],"know":[167],"where":[168,618],"improvements.":[171],"Beyond":[172],"this":[173,289,443],"also":[176,292],"investigate":[177],"decisions,":[183],"during":[184],"introduce":[187],"class":[189,610],"efficient":[191],"approaches,":[192],"hindsight":[193],"learning,":[194],"allows":[196],"us":[197],"leverage":[199],"knowledge":[201],"inside":[202],"existing":[203,621],"human-designed":[204,529,622],"uncertainty.":[212],"First,":[213],"why":[214],"when":[216],"does":[217,317,430],"network":[219,310,320,466,497],"than":[223,483,545],"others,":[224],"despite":[225],"having":[226],"equal":[227],"expressive":[228],"power?":[229],"In":[230],"studying":[231],"this,":[232,331],"unify":[234],"seemingly":[235],"different":[236,500],"tasks,":[238],"such":[239],"intuitive":[241],"physics,":[242],"visual":[243],"question":[244],"answering,":[245],"shortest":[247],"paths,":[248],"via":[249],"lens":[251],"powerful":[254],"paradigm,":[256],"dynamic":[257],"programming":[258],"(DP).":[259],"We":[260,462],"then":[261],"show":[262],"that":[263,346,361,373,464,531,556],"Graph":[264],"Neural":[265],"Network":[266],"(GNNs)---a":[267],"popular":[268],"model---algorithmically":[270],"align":[271],"DP,":[274],"explains":[276],"their":[277],"empirical":[278,399,492],"success":[279,402],"many":[281,558],"At":[284,550],"same":[286,552],"time,":[287,553],"using":[288],"suggest":[293,388],"GNNs":[297,339,392,404],"demonstrate":[299],"use":[303,446,589],"design":[307,509,608],"structured":[309],"given":[311,382],"particular":[313],"task.":[314],"Second,":[315],"what":[316],"outside":[322,577],"support":[324],"training":[327,384],"distribution?":[328],"answer":[330],"identify":[333],"conditions":[334],"MLPs":[337,348,363,374],"well.We":[341],"first":[342],"quantify":[343],"observation":[345],"ReLU":[347,362],"quickly":[349],"converge":[350],"linear":[352,379],"functions":[353],"along":[354],"any":[355],"direction":[356],"from":[357,594],"origin,":[359],"implying":[360],"do":[364],"not":[365,504],"most":[367],"nonlinear":[368],"functions.":[369,461],"Yet,":[370],"prove":[372],"successfully":[376],"target":[380,481],"function":[381,482],"sufficient":[383],"support.":[385],"These":[386,536],"results":[387],"hypothesis":[390],"for":[393,512],"provide":[396,488,539],"theoretical":[397,490],"evidence:":[400],"extrapolating":[406],"tasks":[408],"new":[410],"data":[411,626],"larger":[413],"graphs":[414],"or":[415,426],"edge":[416],"weights)":[417],"relies":[418],"encoding":[420],"task-specific":[421],"non-linearities":[422],"architecture":[425,434,475],"features.":[427],"Third,":[428],"network\u2019s":[433],"impact":[435],"its":[436,455,474],"robustness":[437,453],"labels?":[440],"figure":[442],"out,":[444],"proposed":[448],"connecting":[450],"architectural":[456],"alignments":[457],"target/noise":[460],"hypothesize":[463],"more":[468,477,540],"robust":[469],"labels":[472],"if":[473],"aligned":[478],"noise,":[485],"both":[489],"evidence":[493],"across":[494],"various":[495],"architectures":[498],"domains.":[501],"Last":[502],"but":[503],"least,":[505],"sample-efficient":[510],"approaches":[511],"decision-making":[514,517,564],"problems?":[515],"Many":[516],"problems":[518,561],"especially":[519],"ones":[521],"resource":[523,559],"management":[524,560],"bunch":[527],"heuristics":[530,537],"practice.":[535],"could":[538],"guidance":[541],"RL":[543,631],"agents":[544],"just":[546],"environmental":[548],"reward.":[549],"observe":[555],"requiring":[562],"uncertainty,":[566],"only":[568],"uncertainty":[569],"affecting":[570],"decision":[572],"outcomes":[573],"exogenous":[575],"variables":[576],"control":[579],"decision-maker":[582],"system,":[585],"historical":[595,625],"patterns":[596],"compute":[598],"demands":[599],"help":[601],"deal":[602],"uncertainties.":[605],"Therefore,":[606],"data-efficient":[612],"termed":[614],"Hindsight":[615],"(HL),":[617],"utilize":[620],"guide":[629],"agents.":[632]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}