Parallel Neurosymbolic Integration with Concordia

Jonathan Feldstein; Modestas  Jurcius; Efthymia  Tsamoura

Parallel Neurosymbolic Integration with Concordia

Jonathan Feldstein, Modestas Jurcius, Efthymia Tsamoura

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.

Original language	English
Title of host publication	Proceedings of the 40 th International Conference on Machine Learning
Publisher	PMLR
Pages	9870-9885
Number of pages	16
Volume	202
Publication status	Published - 10 Jul 2023
Event	The Fortieth International Conference on Machine Learning - Honolulu, United States Duration: 23 Jul 2023 → 29 Jul 2023 Conference number: 40 https://icml.cc/

Publication series

Name	Proceedings of Machine Learning Research
Publisher	PMLR
ISSN (Electronic)	2640-3498

Conference

Conference	The Fortieth International Conference on Machine Learning
Abbreviated title	ICML 2023
Country/Territory	United States
City	Honolulu
Period	23/07/23 → 29/07/23
Internet address	https://icml.cc/

Access to Document

Parallel Neurosymbolic_FELDSTEIN_DOA24042023_AFV_CC BYAccepted author manuscript, 576 KBLicence: Creative Commons: Attribution (CC-BY)
Parallel Neurosymbolic_FELDSTEIN_DOA24042023_VOR_CC BYFinal published version, 476 KBLicence: Creative Commons: Attribution (CC-BY)

https://proceedings.mlr.press/v202/feldstein23a.htmlLicence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{a22e2d6e45e8471f8248d2c3abd2eff8,

title = "Parallel Neurosymbolic Integration with Concordia",

abstract = "Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.",

author = "Jonathan Feldstein and Modestas Jurcius and Efthymia Tsamoura",

year = "2023",

month = jul,

day = "10",

language = "English",

volume = "202",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

pages = "9870--9885",

booktitle = "Proceedings of the 40 th International Conference on Machine Learning",

note = "The Fortieth International Conference on Machine Learning, ICML 2023 ; Conference date: 23-07-2023 Through 29-07-2023",

url = "https://icml.cc/",

}

Feldstein, J, Jurcius, M & Tsamoura, E 2023, Parallel Neurosymbolic Integration with Concordia. in Proceedings of the 40 th International Conference on Machine Learning. vol. 202, Proceedings of Machine Learning Research, PMLR, pp. 9870-9885, The Fortieth International Conference on Machine Learning, Honolulu, Hawaii, United States, 23/07/23. <https://proceedings.mlr.press/v202/feldstein23a.html>

TY - GEN

T1 - Parallel Neurosymbolic Integration with Concordia

AU - Feldstein, Jonathan

AU - Jurcius, Modestas

AU - Tsamoura, Efthymia

N1 - Conference code: 40

PY - 2023/7/10

Y1 - 2023/7/10

N2 - Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.

AB - Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.

M3 - Conference contribution

VL - 202

T3 - Proceedings of Machine Learning Research

SP - 9870

EP - 9885

BT - Proceedings of the 40 th International Conference on Machine Learning

PB - PMLR

T2 - The Fortieth International Conference on Machine Learning

Y2 - 23 July 2023 through 29 July 2023

ER -

Parallel Neurosymbolic Integration with Concordia

Abstract / Description of output

Publication series

Conference

Access to Document

Fingerprint

Cite this