---
_id: '33734'
abstract:
- lang: eng
text: 'Many applications require explainable node classification in knowledge graphs.
Towards this end, a popular ``white-box'''' approach is class expression learning:
Given sets of positive and negative nodes, class expressions in description logics
are learned that separate positive from negative nodes. Most existing approaches
are search-based approaches generating many candidate class expressions and selecting
the best one. However, they often take a long time to find suitable class expressions.
In this paper, we cast class expression learning as a translation problem and
propose a new family of class expression learning approaches which we dub neural
class expression synthesizers. Training examples are ``translated'''' into class
expressions in a fashion akin to machine translation. Consequently, our synthesizers
are not subject to the runtime limitations of search-based approaches. We study
three instances of this novel family of approaches based on LSTMs, GRUs, and set
transformers, respectively. An evaluation of our approach on four benchmark datasets
suggests that it can effectively synthesize high-quality class expressions with
respect to the input examples in approximately one second on average. Moreover,
a comparison to state-of-the-art approaches suggests that we achieve better F-measures
on large datasets. For reproducibility purposes, we provide our implementation
as well as pretrained models in our public GitHub repository at https://github.com/dice-group/NeuralClassExpressionSynthesis'
author:
- first_name: N'Dah Jean
full_name: KOUAGOU, N'Dah Jean
id: '87189'
last_name: KOUAGOU
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Caglar
full_name: Demir, Caglar
id: '43817'
last_name: Demir
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Neural Class Expression
Synthesis. In: Pesquita C, Jimenez-Ruiz E, McCusker J, et al., eds. The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023). Vol 13870. Springer
International Publishing; 2023:209-226. doi:https://doi.org/10.1007/978-3-031-33455-9_13'
apa: KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2023).
Neural Class Expression Synthesis. In C. Pesquita, E. Jimenez-Ruiz, J. McCusker,
D. Faria, M. Dragoni, A. Dimou, R. Troncy, & S. Hertling (Eds.), The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023) (Vol. 13870, pp. 209–226).
Springer International Publishing. https://doi.org/10.1007/978-3-031-33455-9_13
bibtex: '@inproceedings{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2023, title={Neural
Class Expression Synthesis}, volume={13870}, DOI={https://doi.org/10.1007/978-3-031-33455-9_13},
booktitle={The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023)},
publisher={Springer International Publishing}, author={KOUAGOU, N’Dah Jean and
Heindorf, Stefan and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}, editor={Pesquita,
Catia and Jimenez-Ruiz, Ernesto and McCusker, Jamie and Faria, Daniel and Dragoni,
Mauro and Dimou, Anastasia and Troncy, Raphael and Hertling, Sven}, year={2023},
pages={209–226} }'
chicago: KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga
Ngomo. “Neural Class Expression Synthesis.” In The Semantic Web - 20th Extended
Semantic Web Conference (ESWC 2023), edited by Catia Pesquita, Ernesto Jimenez-Ruiz,
Jamie McCusker, Daniel Faria, Mauro Dragoni, Anastasia Dimou, Raphael Troncy,
and Sven Hertling, 13870:209–26. Springer International Publishing, 2023. https://doi.org/10.1007/978-3-031-33455-9_13.
ieee: 'N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Neural Class
Expression Synthesis,” in The Semantic Web - 20th Extended Semantic Web Conference
(ESWC 2023), Hersonissos, Crete, Greece, 2023, vol. 13870, pp. 209–226, doi:
https://doi.org/10.1007/978-3-031-33455-9_13.'
mla: KOUAGOU, N’Dah Jean, et al. “Neural Class Expression Synthesis.” The Semantic
Web - 20th Extended Semantic Web Conference (ESWC 2023), edited by Catia Pesquita
et al., vol. 13870, Springer International Publishing, 2023, pp. 209–26, doi:https://doi.org/10.1007/978-3-031-33455-9_13.
short: 'N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, in: C. Pesquita,
E. Jimenez-Ruiz, J. McCusker, D. Faria, M. Dragoni, A. Dimou, R. Troncy, S. Hertling
(Eds.), The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023),
Springer International Publishing, 2023, pp. 209–226.'
conference:
end_date: 2023-06-01
location: Hersonissos, Crete, Greece
name: 20th Extended Semantic Web Conference
start_date: 2023-05-28
date_created: 2022-10-15T19:20:11Z
date_updated: 2023-07-02T18:10:02Z
department:
- _id: '574'
- _id: '760'
doi: https://doi.org/10.1007/978-3-031-33455-9_13
editor:
- first_name: Catia
full_name: Pesquita, Catia
last_name: Pesquita
- first_name: Ernesto
full_name: Jimenez-Ruiz, Ernesto
last_name: Jimenez-Ruiz
- first_name: Jamie
full_name: McCusker, Jamie
last_name: McCusker
- first_name: Daniel
full_name: Faria, Daniel
last_name: Faria
- first_name: Mauro
full_name: Dragoni, Mauro
last_name: Dragoni
- first_name: Anastasia
full_name: Dimou, Anastasia
last_name: Dimou
- first_name: Raphael
full_name: Troncy, Raphael
last_name: Troncy
- first_name: Sven
full_name: Hertling, Sven
last_name: Hertling
external_id:
unknown:
- https://link.springer.com/chapter/10.1007/978-3-031-33455-9_13
intvolume: ' 13870'
keyword:
- Neural network
- Concept learning
- Description logics
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://2023.eswc-conferences.org/wp-content/uploads/2023/05/paper_Kouagou_2023_Neural.pdf
oa: '1'
page: 209 - 226
project:
- _id: '410'
name: 'KnowGraphs: KnowGraphs: Knowledge Graphs at Scale'
- _id: '407'
grant_number: '101070305'
name: 'ENEXA: Efficient Explainable Learning on Knowledge Graphs'
- _id: '285'
grant_number: NW21-059D
name: 'SAIL: SAIL: SustAInable Life-cycle of Intelligent Socio-Technical Systems'
publication: The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023)
publication_identifier:
unknown:
- 978-3-031-33455-9
publication_status: published
publisher: Springer International Publishing
status: public
title: Neural Class Expression Synthesis
type: conference
user_id: '11871'
volume: 13870
year: '2023'
...
---
_id: '34140'
abstract:
- lang: eng
text: In this paper, machine learning techniques will be used to classify different
PCB layouts given their electromagnetic frequency spectra. These spectra result
from a simulated near-field measurement of electric field strengths at different
locations. Measured values consist of real and imaginary parts (amplitude and
phase) in X, Y and Z directions. Training data was obtained in the time domain
by varying transmission line geometries (size, distance and signaling). It was
then transformed into the frequency domain and used as deep neural network input.
Principal component analysis was applied to reduce the sample dimension. The results
show that classifying different designs is possible with high accuracy based on
synthetic data. Future work comprises measurements of real, custom-made PCB with
varying parameters to adapt the simulation model and also test the neural network.
Finally, the trained model could be used to give hints about the error’s cause
when overshooting EMC limits.
author:
- first_name: Jad
full_name: Maalouly, Jad
last_name: Maalouly
- first_name: Dennis
full_name: Hemker, Dennis
last_name: Hemker
- first_name: Christian
full_name: Hedayat, Christian
last_name: Hedayat
- first_name: Christian
full_name: Rückert, Christian
last_name: Rückert
- first_name: Ivan
full_name: Kaufmann, Ivan
last_name: Kaufmann
- first_name: Marcel
full_name: Olbrich, Marcel
last_name: Olbrich
- first_name: Sven
full_name: Lange, Sven
id: '38240'
last_name: Lange
- first_name: Harald
full_name: Mathis, Harald
last_name: Mathis
citation:
ama: 'Maalouly J, Hemker D, Hedayat C, et al. AI Assisted Interference Classification
to Improve EMC Troubleshooting in Electronic System Development. In: 2022 Kleinheubach
Conference. IEEE; 2022.'
apa: Maalouly, J., Hemker, D., Hedayat, C., Rückert, C., Kaufmann, I., Olbrich,
M., Lange, S., & Mathis, H. (2022). AI Assisted Interference Classification
to Improve EMC Troubleshooting in Electronic System Development. 2022 Kleinheubach
Conference. 2022 Kleinheubach Conference, Miltenberg, Germany.
bibtex: '@inproceedings{Maalouly_Hemker_Hedayat_Rückert_Kaufmann_Olbrich_Lange_Mathis_2022,
place={Miltenberg, Germany}, title={AI Assisted Interference Classification to
Improve EMC Troubleshooting in Electronic System Development}, booktitle={2022
Kleinheubach Conference}, publisher={IEEE}, author={Maalouly, Jad and Hemker,
Dennis and Hedayat, Christian and Rückert, Christian and Kaufmann, Ivan and Olbrich,
Marcel and Lange, Sven and Mathis, Harald}, year={2022} }'
chicago: 'Maalouly, Jad, Dennis Hemker, Christian Hedayat, Christian Rückert, Ivan
Kaufmann, Marcel Olbrich, Sven Lange, and Harald Mathis. “AI Assisted Interference
Classification to Improve EMC Troubleshooting in Electronic System Development.”
In 2022 Kleinheubach Conference. Miltenberg, Germany: IEEE, 2022.'
ieee: J. Maalouly et al., “AI Assisted Interference Classification to Improve
EMC Troubleshooting in Electronic System Development,” presented at the 2022 Kleinheubach
Conference, Miltenberg, Germany, 2022.
mla: Maalouly, Jad, et al. “AI Assisted Interference Classification to Improve EMC
Troubleshooting in Electronic System Development.” 2022 Kleinheubach Conference,
IEEE, 2022.
short: 'J. Maalouly, D. Hemker, C. Hedayat, C. Rückert, I. Kaufmann, M. Olbrich,
S. Lange, H. Mathis, in: 2022 Kleinheubach Conference, IEEE, Miltenberg, Germany,
2022.'
conference:
end_date: 2022-09-29
location: Miltenberg, Germany
name: 2022 Kleinheubach Conference
start_date: 2022-09-27
date_created: 2022-11-24T14:21:17Z
date_updated: 2022-11-24T14:21:34Z
department:
- _id: '59'
- _id: '485'
keyword:
- emc
- pcb
- electronic system development
- machine learning
- neural network
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/9954484
place: Miltenberg, Germany
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: 2022 Kleinheubach Conference
publication_identifier:
eisbn:
- 978-3-948571-07-8
publication_status: published
publisher: IEEE
status: public
title: AI Assisted Interference Classification to Improve EMC Troubleshooting in Electronic
System Development
type: conference
user_id: '38240'
year: '2022'
...
---
_id: '35620'
abstract:
- lang: eng
text: Deep learning models fuel many modern decision support systems, because they
typically provide high predictive performance. Among other domains, deep learning
is used in real-estate appraisal, where it allows to extend the analysis from
hard facts only (e.g., size, age) to also consider more implicit information about
the location or appearance of houses in the form of image data. However, one downside
of deep learning models is their intransparent mechanic of decision making, which
leads to a trade-off between accuracy and interpretability. This limits their
applicability for tasks where a justification of the decision is necessary. Therefore,
in this paper, we first combine different perspectives on interpretability into
a multi-dimensional framework for a socio-technical perspective on explainable
artificial intelligence. Second, we measure the performance gains of using multi-view
deep learning which leverages additional image data (satellite images) for real
estate appraisal. Third, we propose and test a novel post-hoc explainability method
called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency
of convolutional neural networks (CNNs) for predicting continuous outcome variables.
With this, we try to reduce the accuracy-interpretability trade-off of multi-view
deep learning models. Our proposed network architecture outperforms traditional
hedonic regression models by 34% in terms of MAE. Furthermore, we find that the
used satellite images are the second most important predictor after square feet
in our model and that the network learns interpretable patterns about the neighborhood
structure and density.
article_type: original
author:
- first_name: Jan-Peter
full_name: Kucklick, Jan-Peter
id: '77066'
last_name: Kucklick
- first_name: Oliver
full_name: Müller, Oliver
id: '72849'
last_name: Müller
citation:
ama: 'Kucklick J-P, Müller O. Tackling the Accuracy–Interpretability Trade-off:
Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal.
ACM Transactions on Management Information Systems. Published online 2022.
doi:10.1145/3567430'
apa: 'Kucklick, J.-P., & Müller, O. (2022). Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate
Appraisal. ACM Transactions on Management Information Systems. https://doi.org/10.1145/3567430'
bibtex: '@article{Kucklick_Müller_2022, title={Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate
Appraisal}, DOI={10.1145/3567430},
journal={ACM Transactions on Management Information Systems}, publisher={Association
for Computing Machinery (ACM)}, author={Kucklick, Jan-Peter and Müller, Oliver},
year={2022} }'
chicago: 'Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate
Appraisal.” ACM Transactions on Management Information Systems, 2022. https://doi.org/10.1145/3567430.'
ieee: 'J.-P. Kucklick and O. Müller, “Tackling the Accuracy–Interpretability Trade-off:
Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal,”
ACM Transactions on Management Information Systems, 2022, doi: 10.1145/3567430.'
mla: 'Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate
Appraisal.” ACM Transactions on Management Information Systems, Association
for Computing Machinery (ACM), 2022, doi:10.1145/3567430.'
short: J.-P. Kucklick, O. Müller, ACM Transactions on Management Information Systems
(2022).
date_created: 2023-01-10T05:16:02Z
date_updated: 2023-01-10T05:20:18Z
department:
- _id: '195'
- _id: '196'
doi: 10.1145/3567430
keyword:
- Interpretability
- Convolutional Neural Network
- Accuracy-Interpretability Trade-Of
- Real Estate Appraisal
- Hedonic Pricing
- Grad-Ram
language:
- iso: eng
main_file_link:
- url: https://dl.acm.org/doi/pdf/10.1145/3567430
publication: ACM Transactions on Management Information Systems
publication_identifier:
issn:
- 2158-656X
- 2158-6578
publication_status: published
publisher: Association for Computing Machinery (ACM)
status: public
title: 'Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning
Models for Satellite Image-based Real Estate Appraisal'
type: journal_article
user_id: '77066'
year: '2022'
...
---
_id: '20504'
abstract:
- lang: eng
text: 'In recent years time domain speech separation has excelled over frequency
domain separation in single channel scenarios and noise-free environments. In
this paper we dissect the gains of the time-domain audio separation network (TasNet)
approach by gradually replacing components of an utterance-level permutation invariant
training (u-PIT) based separation system in the frequency domain until the TasNet
system is reached, thus blending components of frequency domain approaches with
those of time domain approaches. Some of the intermediate variants achieve comparable
signal-to-distortion ratio (SDR) gains to TasNet, but retain the advantage of
frequency domain processing: compatibility with classic signal processing tools
such as frequency-domain beamforming and the human interpretability of the masks.
Furthermore, we show that the scale invariant signal-to-distortion ratio (si-SDR)
criterion used as loss function in TasNet is related to a logarithmic mean square
error criterion and that it is this criterion which contributes most reliable
to the performance advantage of TasNet. Finally, we critically assess which gains
in a noise-free single channel environment generalize to more realistic reverberant
conditions.'
author:
- first_name: Jens
full_name: Heitkaemper, Jens
id: '27643'
last_name: Heitkaemper
- first_name: Darius
full_name: Jakobeit, Darius
last_name: Jakobeit
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Lukas
full_name: Drude, Lukas
last_name: Drude
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Heitkaemper J, Jakobeit D, Boeddeker C, Drude L, Haeb-Umbach R. Demystifying
TasNet: A Dissecting Approach. In: ICASSP 2020 Virtual Barcelona Spain.
; 2020.'
apa: 'Heitkaemper, J., Jakobeit, D., Boeddeker, C., Drude, L., & Haeb-Umbach,
R. (2020). Demystifying TasNet: A Dissecting Approach. ICASSP 2020 Virtual
Barcelona Spain.'
bibtex: '@inproceedings{Heitkaemper_Jakobeit_Boeddeker_Drude_Haeb-Umbach_2020, title={Demystifying
TasNet: A Dissecting Approach}, booktitle={ICASSP 2020 Virtual Barcelona Spain},
author={Heitkaemper, Jens and Jakobeit, Darius and Boeddeker, Christoph and Drude,
Lukas and Haeb-Umbach, Reinhold}, year={2020} }'
chicago: 'Heitkaemper, Jens, Darius Jakobeit, Christoph Boeddeker, Lukas Drude,
and Reinhold Haeb-Umbach. “Demystifying TasNet: A Dissecting Approach.” In ICASSP
2020 Virtual Barcelona Spain, 2020.'
ieee: 'J. Heitkaemper, D. Jakobeit, C. Boeddeker, L. Drude, and R. Haeb-Umbach,
“Demystifying TasNet: A Dissecting Approach,” 2020.'
mla: 'Heitkaemper, Jens, et al. “Demystifying TasNet: A Dissecting Approach.” ICASSP
2020 Virtual Barcelona Spain, 2020.'
short: 'J. Heitkaemper, D. Jakobeit, C. Boeddeker, L. Drude, R. Haeb-Umbach, in:
ICASSP 2020 Virtual Barcelona Spain, 2020.'
date_created: 2020-11-25T14:56:53Z
date_updated: 2022-01-13T08:47:32Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
content_type: application/pdf
creator: jensheit
date_created: 2020-12-11T12:36:37Z
date_updated: 2020-12-11T12:36:37Z
file_id: '20699'
file_name: ms.pdf
file_size: 3871374
relation: main_file
success: 1
file_date_updated: 2020-12-11T12:36:37Z
has_accepted_license: '1'
keyword:
- voice activity detection
- speech activity detection
- neural network
- statistical speech processing
language:
- iso: eng
license: https://creativecommons.org/publicdomain/zero/1.0/
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: ICASSP 2020 Virtual Barcelona Spain
quality_controlled: '1'
status: public
title: 'Demystifying TasNet: A Dissecting Approach'
type: conference
user_id: '40767'
year: '2020'
...
---
_id: '20505'
abstract:
- lang: eng
text: "Speech activity detection (SAD), which often rests on the fact that the noise
is \"more'' stationary than speech, is particularly challenging in non-stationary
environments, because the time variance of the acoustic scene makes it difficult
to discriminate speech from noise. We propose two approaches to SAD, where one
is based on statistical signal processing, while the other utilizes neural networks.
The former employs sophisticated signal processing to track the noise and speech
energies and is meant to support the case for a resource efficient, unsupervised
signal processing approach.\r\nThe latter introduces a recurrent network layer
that operates on short segments of the input speech to do temporal smoothing in
the presence of non-stationary noise. The systems are tested on the Fearless Steps
challenge database, which consists of the transmission data from the Apollo-11
space mission.\r\nThe statistical SAD achieves comparable detection performance
to earlier proposed neural network based SADs, while the neural network based
approach leads to a decision cost function of 1.07% on the evaluation set of the
2020 Fearless Steps Challenge, which sets a new state of the art."
author:
- first_name: Jens
full_name: Heitkaemper, Jens
id: '27643'
last_name: Heitkaemper
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Heitkaemper J, Schmalenstroeer J, Haeb-Umbach R. Statistical and Neural Network
Based Speech Activity Detection in Non-Stationary Acoustic Environments. In: INTERSPEECH
2020 Virtual Shanghai China. ; 2020.'
apa: Heitkaemper, J., Schmalenstroeer, J., & Haeb-Umbach, R. (2020). Statistical
and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic
Environments. INTERSPEECH 2020 Virtual Shanghai China.
bibtex: '@inproceedings{Heitkaemper_Schmalenstroeer_Haeb-Umbach_2020, title={Statistical
and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic
Environments}, booktitle={INTERSPEECH 2020 Virtual Shanghai China}, author={Heitkaemper,
Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2020} }'
chicago: Heitkaemper, Jens, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Statistical
and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic
Environments.” In INTERSPEECH 2020 Virtual Shanghai China, 2020.
ieee: J. Heitkaemper, J. Schmalenstroeer, and R. Haeb-Umbach, “Statistical and Neural
Network Based Speech Activity Detection in Non-Stationary Acoustic Environments,”
2020.
mla: Heitkaemper, Jens, et al. “Statistical and Neural Network Based Speech Activity
Detection in Non-Stationary Acoustic Environments.” INTERSPEECH 2020 Virtual
Shanghai China, 2020.
short: 'J. Heitkaemper, J. Schmalenstroeer, R. Haeb-Umbach, in: INTERSPEECH 2020
Virtual Shanghai China, 2020.'
date_created: 2020-11-25T15:03:19Z
date_updated: 2023-10-26T08:28:49Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: closed
content_type: application/pdf
creator: jensheit
date_created: 2020-12-11T12:33:04Z
date_updated: 2020-12-11T12:33:04Z
file_id: '20697'
file_name: ms.pdf
file_size: 998706
relation: main_file
success: 1
file_date_updated: 2020-12-11T12:33:04Z
has_accepted_license: '1'
keyword:
- voice activity detection
- speech activity detection
- neural network
- statistical speech processing
language:
- iso: eng
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: INTERSPEECH 2020 Virtual Shanghai China
status: public
title: Statistical and Neural Network Based Speech Activity Detection in Non-Stationary
Acoustic Environments
type: conference
user_id: '460'
year: '2020'
...