Syntactic vs Semantic Linear Abstraction and Refinement of
Neural Networks

D 2023

Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

CHAU, Calvin; Jan KŘETÍNSKÝ a Stefanie MOHR

Základní údaje

Originální název

Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

Autoři

CHAU, Calvin; Jan KŘETÍNSKÝ a Stefanie MOHR

Vydání

Singapore, Automated Technology for Verification and Analysis. ATVA 2023, od s. 401-421, 21 s. 2023

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/23:00133938

Organizační jednotka

Fakulta informatiky

ISBN

978-3-031-45328-1

ISSN

DOI

https://doi.org/10.1007/978-3-031-45329-8_19

UT WoS

001456127300019

EID Scopus

2-s2.0-85175948369

Klíčová slova anglicky

Abstraction; Machine learning; Neural network

Štítky

core_B, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 13. 8. 2025 18:28, Mgr. Petra Trembecká, Ph.D.

Anotace

V originále

Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that is similar enough. We can classify the similarity as defined either syntactically (using quantities on the connections between neurons) or semantically (on the activation values of neurons for various inputs). Unfortunately, the previous approaches only achieve moderate reductions, when implemented at all. In this work, we provide a more flexible framework, where a neuron can be replaced with a linear combination of other neurons, improving the reduction. We apply this approach both on syntactic and semantic abstractions, and implement and evaluate them experimentally. Further, we introduce a refinement method for our abstractions, allowing for finding a better balance between reduction and precision.

Citovat

CHAU, Calvin; Jan KŘETÍNSKÝ a Stefanie MOHR. Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks. Online. In Automated Technology for Verification and Analysis. ATVA 2023. Singapore: Springer, 2023, s. 401-421. ISBN 978-3-031-45328-1. Dostupné z: https://doi.org/10.1007/978-3-031-45329-8_19.

@inproceedings{2392233,
   author = {Chau, Calvin and Křetínský, Jan and Mohr, Stefanie},
   address = {Singapore},
   booktitle = {Automated Technology for Verification and Analysis. ATVA 2023},
   doi = {https://doi.org/10.1007/978-3-031-45329-8_19},
   keywords = {Abstraction; Machine learning; Neural network},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Singapore},
   isbn = {978-3-031-45328-1},
   pages = {401-421},
   publisher = {Springer},
   title = {Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks},
   year = {2023}
}

TY  - CONF
ID  - 2392233
AU  - Chau, Calvin - Křetínský, Jan - Mohr, Stefanie
PY  - 2023
TI  - Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks
PB  - Springer
CY  - Singapore
SN  - 9783031453281
KW  - Abstraction
KW  - Machine learning
KW  - Neural network
N2  - Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that is similar enough. We can classify the similarity as defined either syntactically (using quantities on the connections between neurons) or semantically (on the activation values of neurons for various inputs). Unfortunately, the previous approaches only achieve moderate reductions, when implemented at all. In this work, we provide a more flexible framework, where a neuron can be replaced with a linear combination of other neurons, improving the reduction. We apply this approach both on syntactic and semantic abstractions, and implement and evaluate them experimentally. Further, we introduce a refinement method for our abstractions, allowing for finding a better balance between reduction and precision.
ER  -

CHAU, Calvin; Jan KŘETÍNSKÝ a Stefanie MOHR. Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks. Online. In \textit{Automated Technology for Verification and Analysis. ATVA 2023}. Singapore: Springer, 2023, s.~401-421. ISBN~978-3-031-45328-1. Dostupné z: https://doi.org/10.1007/978-3-031-45329-8\_{}19.

Přehled o publikaci