activity
20162026
most citedReactive Soft Prototype Computing for Concept Drift Streams

169 citations · 177 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2026

Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates

Manuel Röder, Bibin Babu, Frank-Michael Schleif

Detecting orchestrated cyberattack campaigns that span multiple organizations traditionally requires sharing sensitive telemetry and threat intelligence across institutional bounda…

cs.LG2025

Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation

Manuel Röder, Christoph Raab, Frank-Michael Schleif

Federated Learning has emerged as a leading paradigm for decentralized, privacy-preserving learning, particularly relevant in the era of interconnected edge devices equipped with s…

cs.LG2024

Deep Transfer Hashing for Adaptive Learning on Federated Streaming Data

Manuel Röder, Frank-Michael Schleif

This extended abstract explores the integration of federated learning with deep transfer hashing for distributed prediction tasks, emphasizing resource-efficient client training fr…

cs.LG2024

Sparse Uncertainty-Informed Sampling from Federated Streaming Data

Manuel Röder, Frank-Michael Schleif

We present a numerically robust, computationally efficient approach for non-I.I.D. data stream sampling in federated client systems, where resources are limited and labeled data fo…

cs.LG2023

Efficient Cross-Domain Federated Learning by MixStyle Approximation

Manuel Röder, Leon Heller, Maximilian Münch +1

With the advent of interconnected and sensor-equipped edge devices, Federated Learning (FL) has gained significant attention, enabling decentralized learning while maintaining data…

cs.LG2022

Revisiting Memory Efficient Kernel Approximation: An Indefinite Learning Perspective

Simon Heilig, Maximilian Münch, Frank-Michael Schleif

Matrix approximations are a key element in large-scale algebraic machine learning approaches. The recently proposed method MEKA (Si et al., 2014) effectively employs two common ass…