← Back to all news
arXiv Machine Learning By Mihailo Ili\'c, Milo\v{s} Savi\'c, Vladimir Kurbalija, Mirjana Ivanovi\'c, Giancarlo Fortino, Du\v{s}an Jakoveti\'c

Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

Read the original on arXiv Machine Learning →

arXiv:2608. 08906v1 Announce Type: new Abstract: Outlier detection in decentralized data environments is a challenging task for many machine learning implementations, particularly in settings where data cannot be shared.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Aug 3

CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection

While deep learning models have achieved state-of-the-art performance in time series anomaly detection, their complex architectures incur substantial inference overhead. Existing methods typically apply a uniform inference strategy across all data points, which is inefficient given that anomalies are inherently scarce and the vast majority of temporal data consists of predictable normal patterns.

benchmarks
More like this →
arXiv AI
Sep 25

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data

The paper introduces a deep positive‑unlabeled anomaly detection framework that combines positive‑unlabeled learning with deep models such as autoencoders and deep support vector data descriptions. It addresses the issue of contaminated unlabeled data by approximating anomaly scores for normal data using both unlabeled and labeled anomaly samples, allowing training without labeled normal data. The authors provide a theoretical generalization error bound and demonstrate improved detection performance over existing methods on several datasets.

By Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka
More like this →