4 papers
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
Daria Fomina, Daniil Krasylnikov, Alexey Boykov +3
Graph Neural Networks (GNNs) are bottlenecked by sparse, irregular memory access. Popular frameworks such as DGL and PyTorch Geometric support general message passing, but complex…
Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
Fedor Velikonivtsev, Oleg Platonov, Ekaterina Alimaskina +2
Modeling traffic dynamics is a critical challenge for urban computing, with applications from real-time traffic management to infrastructure planning. However, progress in this are…
AutoJudge: Judge Decoding Without Manual Annotation
Roman Garipov, Fedor Velikonivtsev, Ivan Ermakov +3
We introduce AutoJudge, a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding. Instead of matching the original model output…
Challenges of Generating Structurally Diverse Graphs
Fedor Velikonivtsev, Mikhail Mironov, Liudmila Prokhorenkova
For many graph-related problems, it can be essential to have a set of structurally diverse graphs. For instance, such graphs can be used for testing graph algorithms or their neura…