6 papers · 1 filter
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
Robin Yadav, Qi Yan, Guy Wolf +2
A fundamental problem in organic chemistry is identifying and predicting the series of reactions that synthesize a desired target product molecule. Due to the combinatorial nature…
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
Semih Cantürk, Semih Cantürk, Thomas Sabourin +3
A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a given set of tasks to new tasks unseen dur…
GraIP: A Benchmarking Framework For Neural Graph Inverse Problems
Semih Cantürk, Andrei Manolache, Arman Mielke +5
A wide range of graph learning tasks, such as structure discovery, temporal graph analysis, and combinatorial optimization, focus on inferring graph structures from data, rather th…
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Billy Joe Franks, Moshe Eliasof, Semih Cantürk +4
Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced their performance across various graph learn…
Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs
Frederik Wenkel, Semih Cantürk, Stefan Horoi +2
Graph neural networks (GNNs) have achieved great success for a variety of tasks such as node classification, graph classification, and link prediction. However, the use of GNNs (an…