14 papers
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…
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…
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 MartÃnez 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…