Adaptive Variational Autoencoders for Outlier Detection in Data Streams: Unterschied zwischen den Versionen

Aus SDQ-Institutsseminar
Keine Bearbeitungszusammenfassung
Keine Bearbeitungszusammenfassung
 
(11 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt)
Zeile 5: Zeile 5:
|betreuer=Edouard Fouché
|betreuer=Edouard Fouché
|termin=Institutsseminar/2019-03-29
|termin=Institutsseminar/2019-03-29
|kurzfassung=Outlier detection targets at the discovery of abnormal data patterns. An Adaptive Variational Autoencoder (AVA) is a novel approach for unsupervised outlier detection in data streams.
|kurzfassung=Outlier detection targets the discovery of abnormal data patterns. Typical scenarios, such as are fraud detection and predictive maintenance are particularly challenging, since the data is available as an infinite and ever evolving stream. In this thesis, we propose Adaptive Variational Autoencoders (AVA), a novel approach for unsupervised outlier detection in data streams.


First, we present a streaming framework for training arbitrary generative models such as Variational Autoencoders (VAE), which we name Adaptive Generative Networks (AGN), in data streams.
Our contribution is two-fold: (1) we introduce a general streaming framework for training arbitrary generative models on data streams. Here, generative models are useful to capture the history of the stream. (2) We instantiate this framework with a Variational Autoencoder, which adapts its network architecture to the dimensionality of incoming data.
The unique property of a generative model is its ability of generating samples from the model.
 
Second, we introduce Adaptive Variational Autoencoders (AVA) for unsupervised outlier detection in data streams.
Adaptive Variational Autoencoders instantiate the AGN framework with a Variational Autoencoder as generative model and automatically adapt the model to an occurring concept drift.
Furthermore, AVA generates its network architecture based on the dimensionality of incoming data.


Our experiments against several benchmark outlier data sets show that AVA outperforms the state of the art and successfully adapts to streams with concept drift.
Our experiments against several benchmark outlier data sets show that AVA outperforms the state of the art and successfully adapts to streams with concept drift.
}}
}}

Aktuelle Version vom 26. März 2019, 22:19 Uhr

Vortragende(r) Florian Pieper
Vortragstyp Masterarbeit
Betreuer(in) Edouard Fouché
Termin Fr 29. März 2019
Vortragsmodus
Kurzfassung Outlier detection targets the discovery of abnormal data patterns. Typical scenarios, such as are fraud detection and predictive maintenance are particularly challenging, since the data is available as an infinite and ever evolving stream. In this thesis, we propose Adaptive Variational Autoencoders (AVA), a novel approach for unsupervised outlier detection in data streams.

Our contribution is two-fold: (1) we introduce a general streaming framework for training arbitrary generative models on data streams. Here, generative models are useful to capture the history of the stream. (2) We instantiate this framework with a Variational Autoencoder, which adapts its network architecture to the dimensionality of incoming data.

Our experiments against several benchmark outlier data sets show that AVA outperforms the state of the art and successfully adapts to streams with concept drift.