activity
20222026
most citedFederated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026★ 1 cited

Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection

Mihailo Ilić, Miloš Savić, Vladimir Kurbalija +3

Outlier detection in decentralized data environments is a challenging task for many machine learning implementations, particularly in settings where data cannot be shared. Recently…

cs.LG2026

Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection

Mihailo Ilić, Miloš Savić, Vladimir Kurbalija +3

Attention layers are the backbone of today's most powerful and impactful models. Models with multi-million and billion parameters rely on contextual knowledge provided by attention…