15 citations · 44 across the 17 of their papers we have counts for
18 papers
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
Shiqiang Wang, Herbert Woisetschläger, Hans Arno Jacobsen +1
Data is fundamental to large language models (LLMs). However, understanding of what makes certain data useful for different stages of an LLM workflow, including training, tuning, a…
FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
Huanchi Wang, Zihang Huang, Yifang Tian +3
Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the spe…
EmbedPart: Embedding-Driven Graph Partitioning for Scalable Graph Neural Network Training
Nikolai Merkel, Ruben Mayer, Volker Markl +1
Graph Neural Networks (GNNs) are widely used for learning on graph-structured data, but scaling GNN training to massive graphs remains challenging. To enable scalable distributed t…
GPoS: Geospatially-aware Proof of Stake
Shashank Motepalli, Naman Garg, Gengrui Zhang +1
Geospatial decentralization is essential for blockchains, ensuring regulatory resilience, robustness, and fairness. We empirically analyze five major Proof of Stake (PoS) blockchai…
MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees
Herbert Woisetschläger, Ryan Zhang, Shiqiang Wang +1
Open-weight large language model (LLM) zoos provide access to numerous high-quality models, but selecting the appropriate model for specific tasks remains challenging and requires…
WaveGAS: Waveform Relaxation for Scaling Graph Neural Networks
Jana Vatter, Mykhaylo Zayats, Marcos Martínez Galindo +4
With the ever-growing size of real-world graphs, numerous techniques to overcome resource limitations when training Graph Neural Networks (GNNs) have been developed. One such appro…
Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Daouda Sow, Herbert Woisetschläger, Saikiran Bulusu +3
Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current…
MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees
Ryan Zhang, Herbert Woisetschläger, Shiqiang Wang +1
Open-weight large language model (LLM) zoos allow users to quickly integrate state-of-the-art models into systems. Despite increasing availability, selecting the most appropriate m…
Can Graph Reordering Speed Up Graph Neural Network Training? An Experimental Study
Nikolai Merkel, Pierre Toussing, Ruben Mayer +1
Graph neural networks (GNNs) are a type of neural network capable of learning on graph-structured data. However, training GNNs on large-scale graphs is challenging due to iterative…
Federated Learning and AI Regulation in the European Union: Who is Responsible? -- An Interdisciplinary Analysis
Herbert Woisetschläger, Simon Mertel, Christoph Krönke +2
The European Union Artificial Intelligence Act mandates clear stakeholder responsibilities in developing and deploying machine learning applications to avoid substantial fines, pri…
Should my Blockchain Learn to Drive? A Study of Hyperledger Fabric
Jeeta Ann Chacko, Ruben Mayer, Hans-Arno Jacobsen
Similar to other transaction processing frameworks, blockchain systems need to be dynamically reconfigured to adapt to varying workloads and changes in network conditions. However,…
Federated Computing -- Survey on Building Blocks, Extensions and Systems
René Schwermer, Ruben Mayer, Hans-Arno Jacobsen
In response to the increasing volume and sensitivity of data, traditional centralized computing models face challenges, such as data security breaches and regulatory hurdles. Feder…
Federated Learning Priorities Under the European Union Artificial Intelligence Act
Herbert Woisetschläger, Alexander Erben, Bill Marino +4
The age of AI regulation is upon us, with the European Union Artificial Intelligence Act (AI Act) leading the way. Our key inquiry is how this will affect Federated Learning (FL),…
Choosing a Classical Planner with Graph Neural Networks
Jana Vatter, Ruben Mayer, Hans-Arno Jacobsen +2
Online planner selection is the task of choosing a solver out of a predefined set for a given planning problem. As planning is computationally hard, the performance of solvers vari…
A Survey on Efficient Federated Learning Methods for Foundation Model Training
Herbert Woisetschläger, Alexander Isenko, Shiqiang Wang +2
Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. However, new approaches to FL oft…
An End-to-End Performance Comparison of Seven Permissioned Blockchain Systems
Frank Christian Geyer, Hans-Arno Jacobsen, Ruben Mayer +1
The emergence of more and more blockchain solutions with innovative approaches to optimising performance, scalability, privacy and governance complicates performance analysis. Reas…
Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly
Herbert Woisetschläger, Alexander Isenko, Shiqiang Wang +2
Large Language Models (LLM) and foundation models are popular as they offer new opportunities for individuals and businesses to improve natural language processing, interact with d…
FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems
Herbert Woisetschläger, Alexander Erben, Ruben Mayer +2
Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. Heterogeneous hardware, unreliable client devic…