6 papers
SeedER: Seed-and-Expand Retrieval from Knowledge Graphs
Hamed Shirzad, Frederik Wenkel, Dominique Beaini +2
Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense…
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…
TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction
Frederik Wenkel, Wilson Tu, Cassandra Masschelein +12
Accurately predicting cellular responses to genetic perturbations is essential for understanding disease mechanisms and designing effective therapies. Yet exhaustively exploring th…
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…
On the Scalability of GNNs for Molecular Graphs
Maciej Sypetkowski, Frederik Wenkel, Farimah Poursafaei +4
Scaling deep learning models has been at the heart of recent revolutions in language modelling and image generation. Practitioners have observed a strong relationship between model…
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
Philip Fradkin, Puria Azadi, Karush Suri +4
Predicting molecular impact on cellular function is a core challenge in therapeutic design. Phenomic experiments, designed to capture cellular morphology, utilize microscopy based…