Quantified neural Markov logic networks

Markov Logic Networks (MLNs) are discrete generative models in the exponential family. However, specifying these rules requires considerable expertise and can pose a significant challenge. To overcome this limitation, Neural MLNs (NMLNs) have been introduced, enabling the specification of potential...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of approximate reasoning Jg. 171; S. 109172
Hauptverfasser: Jung, Peter, Marra, Giuseppe, Kuželka, Ondřej
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.08.2024
Schlagworte:
ISSN:0888-613X, 1873-4731
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Markov Logic Networks (MLNs) are discrete generative models in the exponential family. However, specifying these rules requires considerable expertise and can pose a significant challenge. To overcome this limitation, Neural MLNs (NMLNs) have been introduced, enabling the specification of potential functions as neural networks. Thanks to the compact representation of their neural potential functions, NMLNs have shown impressive performance in modeling complex domains like molecular data. Despite the superior performance of NMLNs, their theoretical expressiveness is still equivalent to that of MLNs without quantifiers. In this paper, we propose a new class of NMLN, called Quantified NMLN, that extends the expressivity of NMLNs to the quantified setting. Furthermore, we demonstrate how to leverage the neural nature of NMLNs to employ learnable aggregation functions as quantifiers, increasing expressivity even further. We demonstrate the competitiveness of Quantified NMLNs over original NMLNs and state-of-the-art diffusion models in molecule generation experiments.
AbstractList Markov Logic Networks (MLNs) are discrete generative models in the exponential family. However, specifying these rules requires considerable expertise and can pose a significant challenge. To overcome this limitation, Neural MLNs (NMLNs) have been introduced, enabling the specification of potential functions as neural networks. Thanks to the compact representation of their neural potential functions, NMLNs have shown impressive performance in modeling complex domains like molecular data. Despite the superior performance of NMLNs, their theoretical expressiveness is still equivalent to that of MLNs without quantifiers. In this paper, we propose a new class of NMLN, called Quantified NMLN, that extends the expressivity of NMLNs to the quantified setting. Furthermore, we demonstrate how to leverage the neural nature of NMLNs to employ learnable aggregation functions as quantifiers, increasing expressivity even further. We demonstrate the competitiveness of Quantified NMLNs over original NMLNs and state-of-the-art diffusion models in molecule generation experiments.
ArticleNumber 109172
Author Jung, Peter
Kuželka, Ondřej
Marra, Giuseppe
Author_xml – sequence: 1
  givenname: Peter
  surname: Jung
  fullname: Jung, Peter
  email: jungpete@fel.cvut.cz
  organization: Faculty of Electrical Engineering, Czech Technical University in Prague, Czechia
– sequence: 2
  givenname: Giuseppe
  surname: Marra
  fullname: Marra, Giuseppe
  email: giuseppe.marra@kuleuven.be
  organization: Department of Computer Science, KU Leuven, Belgium
– sequence: 3
  givenname: Ondřej
  orcidid: 0000-0002-6523-9114
  surname: Kuželka
  fullname: Kuželka, Ondřej
  email: ondrej.kuzelka@fel.cvut.cz
  organization: Faculty of Electrical Engineering, Czech Technical University in Prague, Czechia
BookMark eNp9j01LxDAURYOMYGf0D7jqzlVrvppEcCODXzAigoK7kCappFMbSTIj_ntT6srFrB7cd8_jnSVYjH60AJwjWCOI2GVfu16FGkNMc3CFOD4CBRKcVJQTtAAFFEJUDJH3E7CMsYcQMk5FAS5edmpMrnPWlKPdBTWUTyps_b4c_IfTOUvfPmzjKTju1BDt2d9cgbe729f1Q7V5vn9c32wqTSBMFWm51ZyyFmtuOGOImaYlGLUNtVBjZkjXEo2oEV0uMJy3CBLWkPwfbrAiK4Dnuzr4GIPt5Fdwnyr8SATlpCp7OanKSVXOqhkS_yDtkkrOjykoNxxGr2fUZqm9s0FG7eyorXHB6iSNd4fwX3LhcDk
CitedBy_id crossref_primary_10_1016_j_ijar_2024_109206
crossref_primary_10_3390_app15084424
Cites_doi 10.1093/nar/gky1075
10.1007/s10994-006-5833-1
10.1016/j.artint.2021.103504
10.1093/bioinformatics/btp421
10.1613/jair.1.12320
10.1613/jair.1.11203
10.1016/0004-3702(90)90019-V
10.1016/j.artint.2015.08.011
10.3389/fphar.2020.565644
10.1007/BF02551274
10.1016/j.artint.2023.104062
10.1016/0893-6080(89)90020-8
ContentType Journal Article
Copyright 2024 Elsevier Inc.
Copyright_xml – notice: 2024 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.ijar.2024.109172
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-4731
ExternalDocumentID 10_1016_j_ijar_2024_109172
S0888613X24000598
GroupedDBID --K
--M
.~1
0R~
0SF
1B1
1RT
1~.
1~5
29J
4.4
457
4G.
5GY
5VS
6I.
7-5
71M
8P~
9JN
9JO
AAAKF
AACTN
AAEDT
AAEDW
AAFTH
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABAOU
ABBOA
ABFNM
ABJNI
ABMAC
ABUCO
ABVKL
ABXDB
ACDAQ
ACGFS
ACNCT
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AEXQZ
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGVJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
GBLVA
GBOLZ
HAMUX
HVGLF
HZ~
IHE
IXB
J1W
JJJVA
KOM
LG9
LY1
M41
MHUIS
MO0
N9A
NCXOZ
O-L
O9-
OAUVE
OK1
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SES
SEW
SPC
SPCBC
SSB
SSD
SST
SSV
SSW
SSZ
T5K
UHS
WUQ
XPP
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c300t-3b7ec746b2c7d76616d5b321b54e0c26d3fb3c14d8fc7d62d5b103653088252a3
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001255581200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0888-613X
IngestDate Tue Nov 18 22:15:21 EST 2025
Sat Nov 29 04:42:33 EST 2025
Tue Jun 18 08:52:23 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Statistical relational learning
Markov logic networks
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-3b7ec746b2c7d76616d5b321b54e0c26d3fb3c14d8fc7d62d5b103653088252a3
ORCID 0000-0002-6523-9114
ParticipantIDs crossref_primary_10_1016_j_ijar_2024_109172
crossref_citationtrail_10_1016_j_ijar_2024_109172
elsevier_sciencedirect_doi_10_1016_j_ijar_2024_109172
PublicationCentury 2000
PublicationDate August 2024
2024-08-00
PublicationDateYYYYMMDD 2024-08-01
PublicationDate_xml – month: 08
  year: 2024
  text: August 2024
PublicationDecade 2020
PublicationTitle International journal of approximate reasoning
PublicationYear 2024
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References De Raedt, Kimmig, Toivonen (br0040) 2007
Kazemi, Kimmig, Van den Broeck, Poole (br0510) 2016
Winters, Marra, Manhaeve, De Raedt (br0290) 2022
S.H. Bach, M. Broecheler, B. Huang, L. Getoor, Hinge-loss Markov random fields and probabilistic soft logic, 2017.
Cybenko (br0180) 1989; 2
Ellis, Morales, Sablé-Meyer, Solar-Lezama, Tenenbaum (br0360) 2018
Kuželka, Wang, Davis, Schockaert (br0210) 2018
Manhaeve, Dumančić, Kimmig, Demeester, De Raedt (br0280) 2018
(br0420) Feb. 2023
Van den Broeck, Meert, Darwiche (br0490) 2014
Chen, Natarajan, Ruozzi (br0070) 2022; vol. 151
Svatoš, Jung, Železný, Marra, Kuželka (br0460) 2022
Pinsker (br0150) 1964
Getoor, Taskar (br0010) 2007
Richardson, Domingos (br0450) 2006; 62
De Raedt, Dumančić, Manhaeve, Marra (br0080) 2020
Richardson, Domingos (br0020) 2006; 62
Halpern (br0090) 1990; 46
Van den Broeck (br0480) 2011
Kuzelka, Davis, Schockaert (br0120) 2015
Rocktäschel, Riedel (br0270) 2017
Beame, Van den Broeck, Gribkoff, Suciu (br0530) 2015
Kuzelka (br0500) 2021; 70
Manhaeve, Dumančić, Kimmig, Demeester, De Raedt (br0050) 2021; 298
Marra, Dumančić, Manhaeve, De Raedt (br0100) 2021
Donadello, Serafini, d'Avila Garcez (br0320) 2017
Zaheer, Kottur, Ravanbakhsh, Poczos, Salakhutdinov, Smola (br0140) 2017; 30
Polykovskiy, Zhebrak, Sanchez-Lengeling, Golovanov, Tatanov, Belyaev, Kurbanov, Artamonov, Aladinskiy, Veselov, Kadurin, Johansson, Chen, Nikolenko, Aspuru-Guzik, Zhavoronkov (br0410) 2020; 11
Besold, d. Garcez, Bader, Bowman, Domingos, Hitzler, Kühnberger, Lamb, Lowd, Lima (br0230) 2017
Mendez, Gaulton, Bento, Chambers, De Veij, Félix, Magariños, Mosquera, Mutowo, Nowotka, Gordillo-Marañón, Hunter, Junco, Mugumbate, Rodriguez-Lopez, Atkinson, Bosc, Radoux, Segura-Cabrera, Hersey, Leach (br0400) 2018; 47
Sourek, Aschenbrenner, Zelezný, Schockaert, Kuzelka (br0390) 2018; 62
Vignac, Krawczuk, Siraudin, Wang, Cevher, Frossard (br0440) 2023
den Broeck, Taghipour, Meert, Davis, Raedt (br0470) 2011
Kuzelka, Kungurtsev, Wang (br0200) 2020; vol. 138
Sajjadi, Bachem, Lucic, Bousquet, Gelly (br0430) 2018; 31
Marra, Giannini, Diligenti, Gori (br0340) 2019
Marra, Kuzelka (br0060) 2021; vol. 161
Goodfellow, Bengio, Courville (br0160) 2016
Diligenti, Gori, Saccà (br0310) 2017; 244
Riegel, Gray, Luus, Khan, Makondo, Akhalwaya, Qian, Fagin, Barahona, Sharma (br0260) 2020
Wagstaff, Fuchs, Engelcke, Osborne, Posner (br0190) 2022; 23
Minervini, Bošnjak, Rocktäschel, Riedel, Grefenstette (br0380) 2020
Hornik, Stinchcombe, White (br0170) 1989; 2
Lippi, Frasconi (br0330) 2009; 25
Buchman, Poole (br0220) 2015
Šourek, Aschenbrenner, Zelezný, Schockaert, Kuželka (br0250) 2018; 62
van Bremen, Kuzelka (br0520) 2021
Gutiérrez-Basulto, Jung, Kuzelka (br0130) 2018
Rocktäschel, Riedel (br0370) 2017
Koller, Friedman (br0540) 2009
Dubois, Lang, Prade (br0110) 1994
Yang, Ishay, Lee (br0300) 2020
Marra, Dumančić, Manhaeve, De Raedt (br0240) 2024
Marra, Diligenti, Giannini, Gori, Maggini (br0350) 2020
den Broeck (10.1016/j.ijar.2024.109172_br0470) 2011
Sourek (10.1016/j.ijar.2024.109172_br0390) 2018; 62
Marra (10.1016/j.ijar.2024.109172_br0350) 2020
Donadello (10.1016/j.ijar.2024.109172_br0320) 2017
De Raedt (10.1016/j.ijar.2024.109172_br0040) 2007
Kuzelka (10.1016/j.ijar.2024.109172_br0500) 2021; 70
Pinsker (10.1016/j.ijar.2024.109172_br0150) 1964
Beame (10.1016/j.ijar.2024.109172_br0530) 2015
Diligenti (10.1016/j.ijar.2024.109172_br0310) 2017; 244
Rocktäschel (10.1016/j.ijar.2024.109172_br0370) 2017
Šourek (10.1016/j.ijar.2024.109172_br0250) 2018; 62
Cybenko (10.1016/j.ijar.2024.109172_br0180) 1989; 2
Buchman (10.1016/j.ijar.2024.109172_br0220) 2015
Besold (10.1016/j.ijar.2024.109172_br0230)
Kuzelka (10.1016/j.ijar.2024.109172_br0200) 2020; vol. 138
Minervini (10.1016/j.ijar.2024.109172_br0380) 2020
Koller (10.1016/j.ijar.2024.109172_br0540) 2009
Goodfellow (10.1016/j.ijar.2024.109172_br0160) 2016
Rocktäschel (10.1016/j.ijar.2024.109172_br0270) 2017
Marra (10.1016/j.ijar.2024.109172_br0340) 2019
Marra (10.1016/j.ijar.2024.109172_br0060) 2021; vol. 161
Polykovskiy (10.1016/j.ijar.2024.109172_br0410) 2020; 11
Mendez (10.1016/j.ijar.2024.109172_br0400) 2018; 47
Vignac (10.1016/j.ijar.2024.109172_br0440)
Richardson (10.1016/j.ijar.2024.109172_br0020) 2006; 62
Richardson (10.1016/j.ijar.2024.109172_br0450) 2006; 62
Hornik (10.1016/j.ijar.2024.109172_br0170) 1989; 2
Winters (10.1016/j.ijar.2024.109172_br0290) 2022
Ellis (10.1016/j.ijar.2024.109172_br0360) 2018
Van den Broeck (10.1016/j.ijar.2024.109172_br0480) 2011
Wagstaff (10.1016/j.ijar.2024.109172_br0190) 2022; 23
Van den Broeck (10.1016/j.ijar.2024.109172_br0490) 2014
Sajjadi (10.1016/j.ijar.2024.109172_br0430) 2018; 31
Svatoš (10.1016/j.ijar.2024.109172_br0460) 2022
Kazemi (10.1016/j.ijar.2024.109172_br0510) 2016
Halpern (10.1016/j.ijar.2024.109172_br0090) 1990; 46
van Bremen (10.1016/j.ijar.2024.109172_br0520) 2021
Getoor (10.1016/j.ijar.2024.109172_br0010) 2007
10.1016/j.ijar.2024.109172_br0030
Kuželka (10.1016/j.ijar.2024.109172_br0210) 2018
De Raedt (10.1016/j.ijar.2024.109172_br0080) 2020
Chen (10.1016/j.ijar.2024.109172_br0070) 2022; vol. 151
Riegel (10.1016/j.ijar.2024.109172_br0260)
Dubois (10.1016/j.ijar.2024.109172_br0110) 1994
Gutiérrez-Basulto (10.1016/j.ijar.2024.109172_br0130) 2018
Kuzelka (10.1016/j.ijar.2024.109172_br0120) 2015
Yang (10.1016/j.ijar.2024.109172_br0300) 2020
Marra (10.1016/j.ijar.2024.109172_br0240) 2024
Marra (10.1016/j.ijar.2024.109172_br0100)
Manhaeve (10.1016/j.ijar.2024.109172_br0280) 2018
Lippi (10.1016/j.ijar.2024.109172_br0330) 2009; 25
Manhaeve (10.1016/j.ijar.2024.109172_br0050) 2021; 298
Zaheer (10.1016/j.ijar.2024.109172_br0140) 2017; 30
References_xml – volume: 298
  year: 2021
  ident: br0050
  article-title: Neural probabilistic logic programming in deepproblog
  publication-title: Artif. Intell.
– volume: 25
  start-page: 2326
  year: 2009
  end-page: 2333
  ident: br0330
  article-title: Prediction of protein
  publication-title: Bioinformatics
– volume: 11
  year: 2020
  ident: br0410
  article-title: Molecular sets (moses): a benchmarking platform for molecular generation models
  publication-title: Front. Pharmacol.
– volume: 2
  start-page: 303
  year: 1989
  end-page: 314
  ident: br0180
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Math. Control Signals Syst.
– volume: 47
  start-page: D930
  year: 2018
  end-page: D940
  ident: br0400
  article-title: ChEMBL: towards direct deposition of bioassay data
  publication-title: Nucleic Acids Res.
– volume: 46
  start-page: 311
  year: 1990
  end-page: 350
  ident: br0090
  article-title: An analysis of first-order logics of probability
  publication-title: Artif. Intell.
– year: 2017
  ident: br0320
  article-title: Logic tensor networks for semantic image interpretation
  publication-title: IJCAI
– year: 2023
  ident: br0440
  article-title: Digress: discrete denoising diffusion for graph generation
– year: 2018
  ident: br0360
  article-title: Learning libraries of subroutines for neurally-guided bayesian program induction
  publication-title: NeurIPS
– start-page: 3788
  year: 2017
  end-page: 3800
  ident: br0370
  article-title: End-to-end differentiable proving
  publication-title: Advances in Neural Information Processing Systems
– start-page: 2022
  year: 2022
  ident: br0460
  article-title: Learning to generate molecules from small datasets using neural Markov logic networks
  publication-title: Inductive Logic Programming: Late-Breaking Papers
– volume: 31
  year: 2018
  ident: br0430
  article-title: Assessing generative models via precision and recall
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 244
  year: 2017
  ident: br0310
  article-title: Semantic-based regularization for learning and inference
  publication-title: Artif. Intell.
– volume: 62
  start-page: 107
  year: 2006
  end-page: 136
  ident: br0020
  article-title: Markov logic networks
  publication-title: Mach. Learn.
– year: 2009
  ident: br0540
  article-title: Probabilistic Graphical Models - Principles and Techniques
– start-page: 10090
  year: 2022
  end-page: 10100
  ident: br0290
  article-title: Deepstochlog: neural stochastic logic programming
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36
– year: 2020
  ident: br0380
  article-title: Differentiable reasoning on large knowledge bases and natural language
  publication-title: AAAI
– year: Feb. 2023
  ident: br0420
– volume: 62
  start-page: 69
  year: 2018
  end-page: 100
  ident: br0390
  article-title: Lifted relational neural networks: efficient learning of latent relational structures
  publication-title: J. Artif. Intell. Res.
– start-page: 454
  year: 2015
  end-page: 463
  ident: br0120
  article-title: Encoding Markov logic networks in possibilistic logic
  publication-title: Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence
– volume: 70
  start-page: 1281
  year: 2021
  end-page: 1307
  ident: br0500
  article-title: Weighted first-order model counting in the two-variable fragment with counting quantifiers
  publication-title: J. Artif. Intell. Res.
– start-page: 602
  year: 2018
  end-page: 612
  ident: br0130
  article-title: Quantified Markov logic networks
  publication-title: Principles of Knowledge Representation and Reasoning: Proceedings of the Sixteenth International Conference
– start-page: 517
  year: 2019
  end-page: 532
  ident: br0340
  article-title: Integrating learning and reasoning with deep logic models
  publication-title: Joint European Conference on Machine Learning and Knowledge Discovery in Databases
– start-page: 313
  year: 2015
  end-page: 328
  ident: br0530
  article-title: Symmetric weighted first-order model counting
  publication-title: PODS
– volume: 2
  start-page: 359
  year: 1989
  end-page: 366
  ident: br0170
  article-title: Multilayer feedforward networks are universal approximators
  publication-title: Neural Netw.
– year: 2015
  ident: br0220
  article-title: Representing aggregators in relational probabilistic models
  publication-title: Twenty-Ninth AAAI Conference on Artificial Intelligence
– start-page: 439
  year: 1994
  end-page: 513
  ident: br0110
  article-title: Possibilistic logic
  publication-title: Handbook of Logic in Artificial Intelligence and Logic Programming (vol. 3) Nonmonotonic Reasoning and Uncertain Reasoning
– volume: 62
  year: 2018
  ident: br0250
  article-title: Lifted relational neural networks: efficient learning of latent relational structures
  publication-title: J. Artif. Intell. Res.
– volume: vol. 161
  start-page: 908
  year: 2021
  end-page: 917
  ident: br0060
  article-title: Neural Markov logic networks
  publication-title: Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence
– start-page: 1386
  year: 2011
  end-page: 1394
  ident: br0480
  article-title: On the completeness of first-order knowledge compilation for lifted probabilistic inference
  publication-title: NIPS
– year: 2016
  ident: br0160
  article-title: Deep Learning
– volume: vol. 151
  start-page: 8260
  year: 2022
  end-page: 8269
  ident: br0070
  article-title: Relational neural Markov random fields
  publication-title: International Conference on Artificial Intelligence and Statistics
– year: 2007
  ident: br0010
  article-title: Introduction to Statistical Relational Learning, vol. 1
– start-page: 1755
  year: 2020
  end-page: 1762
  ident: br0300
  article-title: Neurasp: embracing neural networks into answer set programming
  publication-title: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
– volume: 62
  year: 2006
  ident: br0450
  article-title: Markov logic networks
  publication-title: Mach. Learn.
– volume: 30
  year: 2017
  ident: br0140
  article-title: Deep sets
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2021
  ident: br0100
  article-title: From statistical relational to neural symbolic artificial intelligence: a survey
– year: 2020
  ident: br0260
  article-title: Logical neural networks
– year: 2014
  ident: br0490
  article-title: Skolemization for weighted first-order model counting
  publication-title: KR
– year: 2018
  ident: br0210
  article-title: Relational marginal problems: theory and estimation
  publication-title: Thirty-Second AAAI Conference on Artificial Intelligence
– volume: 23
  start-page: 1
  year: 2022
  end-page: 56
  ident: br0190
  article-title: Universal approximation of functions on sets
  publication-title: J. Mach. Learn. Res.
– year: 2020
  ident: br0350
  article-title: Relational neural machines
  publication-title: ECAI
– volume: vol. 138
  start-page: 269
  year: 2020
  end-page: 280
  ident: br0200
  article-title: Lifted weight learning of Markov logic networks (revisited one more time)
  publication-title: International Conference on Probabilistic Graphical Models
– year: 2018
  ident: br0280
  article-title: Deepproblog: neural probabilistic logic programming
  publication-title: NeurIPS
– start-page: 3117
  year: 2016
  end-page: 3125
  ident: br0510
  article-title: New liftable classes for first-order probabilistic inference
  publication-title: NIPS
– year: 2024
  ident: br0240
  article-title: From statistical relational to neurosymbolic artificial intelligence: a survey
  publication-title: Artif. Intell.
– year: 2017
  ident: br0270
  article-title: End-to-end differentiable proving
  publication-title: NIPS
– start-page: 599
  year: 2021
  end-page: 608
  ident: br0520
  article-title: Lifted inference with tree axioms
  publication-title: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning
– start-page: 2178
  year: 2011
  end-page: 2185
  ident: br0470
  article-title: Lifted probabilistic inference by first-order knowledge compilation
  publication-title: IJCAI 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence
– reference: S.H. Bach, M. Broecheler, B. Huang, L. Getoor, Hinge-loss Markov random fields and probabilistic soft logic, 2017.
– year: 1964
  ident: br0150
  article-title: Information and Information Stability of Random Variables and Processes
– year: 2020
  ident: br0080
  article-title: From statistical relational to neural symbolic artificial intelligence
  publication-title: IJCAI 2020
– year: 2017
  ident: br0230
  article-title: Neural-symbolic learning and reasoning: a survey and interpretation
– start-page: 2462
  year: 2007
  end-page: 2467
  ident: br0040
  article-title: Problog: a probabilistic prolog and its application in link discovery
  publication-title: IJCAI, Vol. 7
– start-page: 1755
  year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0300
  article-title: Neurasp: embracing neural networks into answer set programming
– volume: 47
  start-page: D930
  issue: D1
  year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0400
  article-title: ChEMBL: towards direct deposition of bioassay data
  publication-title: Nucleic Acids Res.
  doi: 10.1093/nar/gky1075
– ident: 10.1016/j.ijar.2024.109172_br0440
– year: 2017
  ident: 10.1016/j.ijar.2024.109172_br0270
  article-title: End-to-end differentiable proving
– start-page: 2022
  year: 2022
  ident: 10.1016/j.ijar.2024.109172_br0460
  article-title: Learning to generate molecules from small datasets using neural Markov logic networks
– volume: 62
  year: 2006
  ident: 10.1016/j.ijar.2024.109172_br0450
  article-title: Markov logic networks
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-006-5833-1
– volume: 298
  year: 2021
  ident: 10.1016/j.ijar.2024.109172_br0050
  article-title: Neural probabilistic logic programming in deepproblog
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2021.103504
– year: 2007
  ident: 10.1016/j.ijar.2024.109172_br0010
– volume: vol. 138
  start-page: 269
  year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0200
  article-title: Lifted weight learning of Markov logic networks (revisited one more time)
– year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0280
  article-title: Deepproblog: neural probabilistic logic programming
– start-page: 517
  year: 2019
  ident: 10.1016/j.ijar.2024.109172_br0340
  article-title: Integrating learning and reasoning with deep logic models
– start-page: 3788
  year: 2017
  ident: 10.1016/j.ijar.2024.109172_br0370
  article-title: End-to-end differentiable proving
– start-page: 439
  year: 1994
  ident: 10.1016/j.ijar.2024.109172_br0110
  article-title: Possibilistic logic
– start-page: 1386
  year: 2011
  ident: 10.1016/j.ijar.2024.109172_br0480
  article-title: On the completeness of first-order knowledge compilation for lifted probabilistic inference
– ident: 10.1016/j.ijar.2024.109172_br0100
– year: 2014
  ident: 10.1016/j.ijar.2024.109172_br0490
  article-title: Skolemization for weighted first-order model counting
– volume: vol. 151
  start-page: 8260
  year: 2022
  ident: 10.1016/j.ijar.2024.109172_br0070
  article-title: Relational neural Markov random fields
– year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0210
  article-title: Relational marginal problems: theory and estimation
– start-page: 10090
  year: 2022
  ident: 10.1016/j.ijar.2024.109172_br0290
  article-title: Deepstochlog: neural stochastic logic programming
– volume: 30
  year: 2017
  ident: 10.1016/j.ijar.2024.109172_br0140
  article-title: Deep sets
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 25
  start-page: 2326
  issue: 18
  year: 2009
  ident: 10.1016/j.ijar.2024.109172_br0330
  article-title: Prediction of protein β-residue contacts by Markov logic networks with grounding-specific weights
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btp421
– start-page: 599
  year: 2021
  ident: 10.1016/j.ijar.2024.109172_br0520
  article-title: Lifted inference with tree axioms
– start-page: 313
  year: 2015
  ident: 10.1016/j.ijar.2024.109172_br0530
  article-title: Symmetric weighted first-order model counting
– volume: 70
  start-page: 1281
  year: 2021
  ident: 10.1016/j.ijar.2024.109172_br0500
  article-title: Weighted first-order model counting in the two-variable fragment with counting quantifiers
  publication-title: J. Artif. Intell. Res.
  doi: 10.1613/jair.1.12320
– start-page: 454
  year: 2015
  ident: 10.1016/j.ijar.2024.109172_br0120
  article-title: Encoding Markov logic networks in possibilistic logic
– year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0380
  article-title: Differentiable reasoning on large knowledge bases and natural language
– year: 2015
  ident: 10.1016/j.ijar.2024.109172_br0220
  article-title: Representing aggregators in relational probabilistic models
– year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0360
  article-title: Learning libraries of subroutines for neurally-guided bayesian program induction
– start-page: 2462
  year: 2007
  ident: 10.1016/j.ijar.2024.109172_br0040
  article-title: Problog: a probabilistic prolog and its application in link discovery
– year: 2016
  ident: 10.1016/j.ijar.2024.109172_br0160
– year: 1964
  ident: 10.1016/j.ijar.2024.109172_br0150
– volume: vol. 161
  start-page: 908
  year: 2021
  ident: 10.1016/j.ijar.2024.109172_br0060
  article-title: Neural Markov logic networks
– volume: 62
  year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0250
  article-title: Lifted relational neural networks: efficient learning of latent relational structures
  publication-title: J. Artif. Intell. Res.
  doi: 10.1613/jair.1.11203
– start-page: 602
  year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0130
  article-title: Quantified Markov logic networks
– volume: 46
  start-page: 311
  issue: 3
  year: 1990
  ident: 10.1016/j.ijar.2024.109172_br0090
  article-title: An analysis of first-order logics of probability
  publication-title: Artif. Intell.
  doi: 10.1016/0004-3702(90)90019-V
– start-page: 2178
  year: 2011
  ident: 10.1016/j.ijar.2024.109172_br0470
  article-title: Lifted probabilistic inference by first-order knowledge compilation
– start-page: 3117
  year: 2016
  ident: 10.1016/j.ijar.2024.109172_br0510
  article-title: New liftable classes for first-order probabilistic inference
– volume: 62
  start-page: 69
  year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0390
  article-title: Lifted relational neural networks: efficient learning of latent relational structures
  publication-title: J. Artif. Intell. Res.
  doi: 10.1613/jair.1.11203
– year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0080
  article-title: From statistical relational to neural symbolic artificial intelligence
– volume: 244
  year: 2017
  ident: 10.1016/j.ijar.2024.109172_br0310
  article-title: Semantic-based regularization for learning and inference
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2015.08.011
– volume: 11
  year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0410
  article-title: Molecular sets (moses): a benchmarking platform for molecular generation models
  publication-title: Front. Pharmacol.
  doi: 10.3389/fphar.2020.565644
– year: 2020
  ident: 10.1016/j.ijar.2024.109172_br0350
  article-title: Relational neural machines
– volume: 2
  start-page: 303
  issue: 4
  year: 1989
  ident: 10.1016/j.ijar.2024.109172_br0180
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Math. Control Signals Syst.
  doi: 10.1007/BF02551274
– ident: 10.1016/j.ijar.2024.109172_br0030
– volume: 31
  year: 2018
  ident: 10.1016/j.ijar.2024.109172_br0430
  article-title: Assessing generative models via precision and recall
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 23
  start-page: 1
  issue: 151
  year: 2022
  ident: 10.1016/j.ijar.2024.109172_br0190
  article-title: Universal approximation of functions on sets
  publication-title: J. Mach. Learn. Res.
– year: 2024
  ident: 10.1016/j.ijar.2024.109172_br0240
  article-title: From statistical relational to neurosymbolic artificial intelligence: a survey
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2023.104062
– year: 2017
  ident: 10.1016/j.ijar.2024.109172_br0320
  article-title: Logic tensor networks for semantic image interpretation
– ident: 10.1016/j.ijar.2024.109172_br0230
– ident: 10.1016/j.ijar.2024.109172_br0260
– year: 2009
  ident: 10.1016/j.ijar.2024.109172_br0540
– volume: 62
  start-page: 107
  issue: 1–2
  year: 2006
  ident: 10.1016/j.ijar.2024.109172_br0020
  article-title: Markov logic networks
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-006-5833-1
– volume: 2
  start-page: 359
  issue: 5
  year: 1989
  ident: 10.1016/j.ijar.2024.109172_br0170
  article-title: Multilayer feedforward networks are universal approximators
  publication-title: Neural Netw.
  doi: 10.1016/0893-6080(89)90020-8
SSID ssj0006748
Score 2.4084098
Snippet Markov Logic Networks (MLNs) are discrete generative models in the exponential family. However, specifying these rules requires considerable expertise and can...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109172
SubjectTerms Markov logic networks
Statistical relational learning
Title Quantified neural Markov logic networks
URI https://dx.doi.org/10.1016/j.ijar.2024.109172
Volume 171
WOSCitedRecordID wos001255581200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-4731
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006748
  issn: 0888-613X
  databaseCode: AIEXJ
  dateStart: 20211211
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3PT9swFLZG2WEXYBto_FQOQztUQY3txMkRUGFsExsaSL1FtuNI7VCoSIv65_Oe7YQWJjQmcUkrJ64Tf9bL916f30fIZ1FoGanEhFIKGfJIqFAyzCIUPC7LEndAWaR_iPPzdDDIfnn9ztrKCYiqSmezbPyqUEMbgI1bZ18Ad_uj0ADfAXQ4Auxw_CfgL6bSJgDh__rGFtXA_Tg3d11r5aDN5n3X86x0MSw4V0zCVhyfDYHVorqKrG3stk268XZiIcUXxrLKRd3T4bQ243G7br5P94_j_aO-uf5jz_-sCmzIMjOajzxQ3ua9-XBYsyVmIWMTrFYK_qgV-YUXjLOqqWAhF97cN2bXSa88MeEumjA6GI4k1mulHCteRU7f51Fp7N84GI6FibDAE9MlskwFfHbI8uFZf_CtfSejpIrzJ9zN-e1TLtPv8Uh_pyhztONyjax4fyE4dDi_J29M9YGsNlocgTfNH8mXB9gDB3vgYA8s7EED-zq5OulfHn8NvQhGqFmvNwmZEkYLniiqRSGATSVFrBiNVMxNT9OkYKViOuJFWsIFCYWzEbCSmKHvFFPJNkinuqnMJxJoKRhnhQGvlXLW4zJVQO_AoVRxVhZSbZKoee5c-wrxKFRynTepgKMc5yrHucrdXG2Sbttn7OqjPHt13Exn7hmeY245oP9Mv63_7LdN3j0s3B3SmdxOzS55q-8mw_p2zy-Se2uccrM
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Quantified+neural+Markov+logic+networks&rft.jtitle=International+journal+of+approximate+reasoning&rft.au=Jung%2C+Peter&rft.au=Marra%2C+Giuseppe&rft.au=Ku%C5%BEelka%2C+Ond%C5%99ej&rft.date=2024-08-01&rft.pub=Elsevier+Inc&rft.issn=0888-613X&rft.eissn=1873-4731&rft.volume=171&rft_id=info:doi/10.1016%2Fj.ijar.2024.109172&rft.externalDocID=S0888613X24000598
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0888-613X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0888-613X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0888-613X&client=summon