15 citations · 42 across the 10 of their papers we have counts for
16 papers
Approaching I/O-optimality for Approximate Attention
Pál András Papp, Aleksandros Sobczyk, Anastasios Zouzias
We revisit the I/O complexity of attention in large language models. Given query-key-value matrices , and a machine with fast memory size , the g…
DAG Scheduling in the BSP Model
Pál András Papp, Georg Anegg, A. N. Yzelman
We study the problem of scheduling an arbitrary computational DAG on a fixed number of processors while minimizing the makespan. While previous works have mostly studied this probl…
Partitioning Hypergraphs is Hard: Models, Inapproximability, and Applications
Pál András Papp, Georg Anegg, A. N. Yzelman
We study the balanced -way hypergraph partitioning problem, with a special focus on its practical applications to manycore scheduling. Given a hypergraph on nodes, our goal…
Agent-based Graph Neural Networks
Karolis Martinkus, Pál András Papp, Benedikt Schesch +1
We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computatio…
A Theoretical Comparison of Graph Neural Network Extensions
Pál András Papp, Roger Wattenhofer
We study and compare different Graph Neural Network extensions that increase the expressive power of GNNs beyond the Weisfeiler-Leman test. We focus on (i) GNNs based on higher ord…
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Pál András Papp, Karolis Martinkus, Lukas Faber +1
This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs…