15 citations · 35 across the 11 of their papers we have counts for
4 papers · 1 filter
Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets
Eren Akbiyik, Florian Grötschla, Beni Egressy +1
Graph Neural Networks (GNNs) have emerged as a powerful tool for learning from graph-structured data. However, even state-of-the-art architectures have limitations on what structur…
Realistic Synthetic Financial Transactions for Anti-Money Laundering Models
Erik Altman, Jovan Blanuša, Luc von Niederhäusern +3
With the widespread digitization of finance and the increasing popularity of cryptocurrencies, the sophistication of fraud schemes devised by cybercriminals is growing. Money laund…
Provably Powerful Graph Neural Networks for Directed Multigraphs
Béni Egressy, Luc von Niederhäusern, Jovan Blanusa +3
This paper analyses a set of simple adaptations that transform standard message-passing Graph Neural Networks (GNN) into provably powerful directed multigraph neural networks. The…
Cascaded Beam Search: Plug-and-Play Terminology-Forcing For Neural Machine Translation
Frédéric Odermatt, Béni Egressy, Roger Wattenhofer
This paper presents a plug-and-play approach for translation with terminology constraints. Terminology constraints are an important aspect of many modern translation pipelines. In…