Szczegóły publikacji
Opis bibliograficzny
AD-NEv++ : the multi-architecture neuroevolution-based multivariate anomaly detection framework / Marcin PIETROŃ, Dominik ŻUREK, Kamil FABER, Anna WÓJCIK, Roberto Corizzo // W: GECCO'24 Companion [Dokument elektroniczny] : proceedings of the Genetic and Evolutionary Computation Conference Companion : Melbourne, Australia, July 14-18, 2024 / Association for Computing Machinery. — Wersja do Windows. — Dane tekstowe. — New York : Association for Computing Machinery, cop. 2024. — e-ISBN: 979-8-4007-0495-6. — S. 607-610. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://dl.acm.org/doi/pdf/10.1145/3638530.3654360 [2024-08-05]. — Bibliogr. s. 610, Abstr.
Autorzy (5)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 154816 |
|---|---|
| Data dodania do BaDAP | 2024-09-06 |
| DOI | 10.1145/3638530.3654360 |
| Rok publikacji | 2024 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | Genetic and Evolutionary Computations 2024 |
Abstract
Anomaly detection tools and methods enable key analytical capabilities in modern cyberphysical and sensor-based systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given dataset is a cumbersome and time-consuming process. Neuroevolution could be an effective and efficient solution to this problem, as a fully automated search method for learning optimal neural networks, supporting both gradient and non-gradient fine tuning. However, existing frameworks incorporating neuroevolution lack of support for new layers and architectures and are typically limited to convolutional and LSTM layers. In this paper we propose AD-NEv++, a three-stage neuroevolution-based method that synergically combines subspace evolution, model evolution, and fine-tuning. Our method overcomes the limitations of existing approaches by optimizing the mutation operator in the neuroevolution process, while supporting a wide spectrum of neural layers, including attention, dense, and graph convolutional layers. Our extensive experimental evaluation was conducted with widely adopted multivariate anomaly detection benchmark datasets, and showed that the models generated by AD-NEv++ outperform well-known deep learning architectures and neuroevolution-based approaches for anomaly detection. Moreover, results show that AD-NEv++ can improve and outperform the state-of-the-art GNN (Graph Neural Networks) model architecture in all anomaly detection benchmarks.
