activity
20232025
most citedPosition: Graph Learning Will Lose Relevance Due To Poor Benchmarks

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Generalizable Insights for Graph Transformers in Theory and Practice

Timo Stoll, Luis Müller, Christopher Morris

Graph Transformers (GTs) have shown strong empirical performance, yet current architectures vary widely in their use of attention mechanisms, positional embeddings (PEs), and expre…

cs.LG2025★ 2 cited

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca +9

While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and rele…