2 citations · 3 across the 12 of their papers we have counts for
3 papers · 1 filter
Can Graph Learning Learn Circuits?
Chester Tan, Moritz Lampert, Courtney Maynard +3
Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient to reproduce a particular be…
Single-Snapshot Inference of Network Couplings from Universal Dynamics at Relative Equilibrium
Moritz Lampert, Dominic Grün, Ingo Scholtes
Many real-world systems can be modelled as complex networks whose collective behaviour is governed by hidden interactions between nodes. Existing methods for inferring these intera…
The Role of Node Features in Graph Pooling
Jan von Pichowski, Alžbeta Hrabošová, Ingo Scholtes +1
Graph pooling is commonly applied in graph classification, yet its empirical gains over standard WL-1 expressive GNNs are often marginal or inconsistent. We study this gap by analy…