Details
| Original language | English |
|---|---|
| Title of host publication | SIGMOD/PODS '21: Proceedings of the 2021 International Conference on Management of Data |
| Pages | 1345-1358 |
| Number of pages | 14 |
| Publication status | Published - 9 Jun 2021 |
Publication series
| Name | Proceedings of the ACM SIGMOD International Conference on Management of Data |
|---|---|
| ISSN (Print) | 0730-8078 |
Abstract
Responsible usage of Machine Learning (ML) systems in practice does not only require enforcing high prediction quality, but also accounting for other constraints, such as fairness, privacy, or execution time. One way to address multiple user-specified constraints on ML systems is feature selection. Yet, optimizing feature selection strategies for multiple metrics is difficult to implement and has been underrepresented in previous experimental studies. Here, we propose Declarative Feature Selection (DFS) to simplify the design and validation of ML systems satisfying diverse user-specified constraints. We benchmark and evaluate a representative series of feature selection algorithms. From our extensive experimental results, we derive concrete suggestions on when to use which strategy and show that a meta-learning-driven optimizer can accurately predict the right strategy for an ML task at hand. These results demonstrate that feature selection can help to build ML systems that meet combinations of user-specified constraints, independent of the ML methods used.
Keywords
- DFS, bias, declarative feature selection, declarative machine learning, declarative ml, fairness, feature selection, machine learning, meta learning, privacy, robustness
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
SIGMOD/PODS '21: Proceedings of the 2021 International Conference on Management of Data. 2021. p. 1345-1358 (Proceedings of the ACM SIGMOD International Conference on Management of Data).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Enforcing Constraints for Machine Learning Systems via Declarative Feature Selection
T2 - An Experimental Study.
AU - Neutatz, Felix
AU - Biessmann, Felix
AU - Abedjan, Ziawasch
PY - 2021/6/9
Y1 - 2021/6/9
N2 - Responsible usage of Machine Learning (ML) systems in practice does not only require enforcing high prediction quality, but also accounting for other constraints, such as fairness, privacy, or execution time. One way to address multiple user-specified constraints on ML systems is feature selection. Yet, optimizing feature selection strategies for multiple metrics is difficult to implement and has been underrepresented in previous experimental studies. Here, we propose Declarative Feature Selection (DFS) to simplify the design and validation of ML systems satisfying diverse user-specified constraints. We benchmark and evaluate a representative series of feature selection algorithms. From our extensive experimental results, we derive concrete suggestions on when to use which strategy and show that a meta-learning-driven optimizer can accurately predict the right strategy for an ML task at hand. These results demonstrate that feature selection can help to build ML systems that meet combinations of user-specified constraints, independent of the ML methods used.
AB - Responsible usage of Machine Learning (ML) systems in practice does not only require enforcing high prediction quality, but also accounting for other constraints, such as fairness, privacy, or execution time. One way to address multiple user-specified constraints on ML systems is feature selection. Yet, optimizing feature selection strategies for multiple metrics is difficult to implement and has been underrepresented in previous experimental studies. Here, we propose Declarative Feature Selection (DFS) to simplify the design and validation of ML systems satisfying diverse user-specified constraints. We benchmark and evaluate a representative series of feature selection algorithms. From our extensive experimental results, we derive concrete suggestions on when to use which strategy and show that a meta-learning-driven optimizer can accurately predict the right strategy for an ML task at hand. These results demonstrate that feature selection can help to build ML systems that meet combinations of user-specified constraints, independent of the ML methods used.
KW - DFS
KW - bias
KW - declarative feature selection
KW - declarative machine learning
KW - declarative ml
KW - fairness
KW - feature selection
KW - machine learning
KW - meta learning
KW - privacy
KW - robustness
UR - http://www.scopus.com/inward/record.url?scp=85108980866&partnerID=8YFLogxK
U2 - 10.1145/3448016.3457295
DO - 10.1145/3448016.3457295
M3 - Conference contribution
T3 - Proceedings of the ACM SIGMOD International Conference on Management of Data
SP - 1345
EP - 1358
BT - SIGMOD/PODS '21: Proceedings of the 2021 International Conference on Management of Data
ER -