activity
20242026
collaborators

9 papers

cs.LG2026

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…

physics.soc-ph2026

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…

cs.SE2026

Bursts and Triggers: Socially-Driven Activity in Open-Source Co-Editing Networks

Lisi Qarkaxhija, Maximilian Capraro, Stefan Menzel +2

The long-term sustainability of Open Source Software (OSS) communities depends on the activity of their developers, yet the social mechanisms driving this collective behavior remai…

cs.LG2026

Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs

Franziska Heeg, Jonas Sauer, Petra Mutzel +1

An important characteristic of temporal graphs is how the directed arrow of time influences their causal topology, i.e., which nodes can possibly influence each other causally via…

cs.LG2026

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…

cs.LG2026

From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning

Moritz Lampert, Christopher Blöcker, Ingo Scholtes

Dynamic link prediction is an important problem considered in many recent works that propose approaches for learning temporal edge patterns. To assess their efficacy, models are ev…