activity
20242026
collaborators

6 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2024

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…

cs.LG2024

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…

q-bio.QM2024

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…