arXiv subjects

Ingo Scholtes

Publications and source records attributed to Ingo Scholtes.

At least 19 recordsLinked to original sources

arXiv2026

Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces

Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as "more elegant" or "more minimalist," typically encoded by a vision-language model (VLM). A practical question is whether state-of-the-art VLMs represent objects consistently in terms of the same concept. We audit 6 VLMs by ranking untextured 3D objects along Kansei adjective pairs, where Kansei describes affective impressions of product form, with each axis defined as the difference between the text representations of its two poles. Geometric pairs serve as positive controls, and pairs of unrelated adjectives establish an empirical null. Across 10 categories of ShapeNet database, affective axes converge above the null (mean pairwise rank correlation 0.36 vs. 0.14) but below the geometric ceiling (0.44). The agreement between models is partial and highly uneven: on the three axes shared by all categories, mean convergence ranges from 0.21 for bookshelves to 0.51 for jars. Convergence depends primarily on whether a category's representational variation aligns with the semantic direction being evaluated, rather than simply on how much the objects vary in shape overall. Cross-model convergence does not imply agreement with human judgments. Based on our findings, we implement a UI prototype that shows how the audit can inform which Kansei descriptors to expose as controls for a given object class and which to withhold.

cs.HC↗

arXiv2026

Can Graph Learning Learn Circuits?

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 behavior. Most established methods localize circuits independently for each model--task pair. We instead frame circuit localization as a graph machine learning problem in which the edges of a computation graph represent computational pathways, and graph neural networks (GNNs) model interactions among these pathways. We introduce Graph Circuit Learning (GCL), a supervised, amortized framework that trains a GNN across multiple model--task pairs and applies it to unseen cases. To provide sufficient data, we augment the InterpBench benchmark with additional cases derived from the TracrBench programs. Of the 14 evaluated GCL configurations, the highest scored a median edge AUROC of $0.902$ (interquartile interval $[0.861, 0.942]$) on the 16 original held-out InterpBench cases. This is close to the published InterpBench median of $0.910$ for EAP-IG while remaining below ACDC's $0.959$. Removing all message-passing edges reduces the median to $0.825$. We also adapt PGExplainer, a GNN explainability method, to circuit localization, obtaining a median edge AUROC of $0.858$ on the same cases. These preliminary results suggest that graph machine learning offers a natural and potentially powerful perspective on circuit localization, and we hope this perspective encourages closer exchange between the two communities.

cs.LG↗

arXiv2026

Single-Snapshot Inference of Network Couplings from Universal Dynamics at Relative Equilibrium

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 interactions typically require controlled perturbations, time-resolved observations or multiple independent snapshots, all of which are often unavailable in practice. Here we show that class-based coupling strengths can be inferred from a single snapshot of node states when the system is observed close to a relative equilibrium. In this regime, all nodes share a common velocity, which can be absorbed into an effective class bias, transforming the inverse problem into a homogeneous linear system. The coefficients of this linear system are determined entirely by the observed local neighbourhoods and their coupling mechanism, enabling the application to arbitrary known coupling functions. We validate the approach on three different linear and nonlinear dynamical systems, recovering relative class-based couplings and, in special cases, absolute couplings. These results show that spatial heterogeneity can substitute for temporal sampling, enabling single-snapshot inference of hidden coupling strengths in networked dynamical systems.

physics.soc-ph↗

arXiv2026

The Role of Node Features in Graph Pooling

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 analysing the interaction between node features and graph topology and their effect on pooling objectives. Our analysis reveals that pooling operators require node features that are well-aligned with the graph's topology -- a condition often overlooked and not guaranteed in empirical networks. We formalise fundamental requirements for node features to enable effective pooling, and introduce a quantitative measure of feature quality. Our empirical evaluation shows that, when these requirements are satisfied, pooling can be beneficial and improve performance on appropriate datasets.

cs.LG↗

arXiv2026

Learning Neural Operator Surrogates for the Black Hole Accretion Code

General-relativistic magnetohydrodynamic (GR-MHD) simulations are essential for studying black hole accretion, relativistic jets, and magnetic reconnection, yet their computational cost severely limits systematic parameter exploration. We investigate neural operator surrogates for two astrophysically relevant simulation scenarios produced by the Black Hole Accretion Code (\texttt{BHAC}). First, a Physics Informed Fourier Neural Operator (PINO) is trained on the special-relativistic resistive MHD (SRRMHD) evolution of the Orszag-Tang vortex over a range of resistivities spanning the Sweet-Parker and fast reconnection regimes. By embedding the governing equations as an additional loss term evaluated at finer temporal resolution than the available data supervision, the model learns dynamics at time steps where no simulation data is provided, enabling recovery of plasmoid formation that a data-only baseline trained on the same sparse snapshots fails to reproduce. To our knowledge, the present work is the first application of a physics informed neural operator to special relativistic resistive MHD, and the first to investigate the capability of such models to resolve plasmoid formation in SRRMHD. In a second line of investigation, an OFormer-style Transformer Neural Operator is trained on the evolution of spine-sheath relativistic jets created with \texttt{BHAC}, in special-relativistic MHD (SRMHD). The model is directly applied on the adaptive mesh, highlighting the need for linear attention due to long sequences. The neural surrogate model is capable of capturing most of the major details, especially in early predictions. To our knowledge, this constitutes the first application of a neural operator directly on a high resolution adaptive mesh refinement grid in the context of MHD simulations.

astro-ph.HE↗

arXiv2025

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

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 remain poorly understood. Analyzing commit histories across 51 major OSS communities, we find that developer contributions are strongly "bursty" in time. To test whether this burstiness reflects social responsiveness rather than individual habit alone, we model developer interactions as temporal co-editing networks and introduce a method to detect activity triggers, episodes in which one developer editing another's code is followed by an unusually rapid response, and the cascades they form. Benchmarking these against a null model that destroys the temporal ordering of co-edits while preserving each developer's activity rate, we find statistically significant cascades in 28 of 51 projects (55%) under our default configuration, though prevalence ranges from 24% to 82% across detection thresholds. Whether a project exhibits significant cascades is governed primarily by its scale rather than governance or commit concentration. Finally, as a secondary application, we test whether these signals inform developer churn: features capturing the recent (in)activity of a developer's collaborators add some predictive value, but a developer's own inactivity dominates, propagation over the co-editing graph adds little, and simple models match graph neural networks. Our results characterize developer responsiveness as a measurable component of collective OSS dynamics.

cs.SE↗

arXiv2025

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

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 time-respecting paths. The resulting patterns are often neglected by temporal graph neural networks (TGNNs). To formally analyze the expressive power of TGNNs, we lack a generalization of graph isomorphism to temporal graphs that fully captures their causal topology. Addressing this gap, we introduce the notion of consistent event graph isomorphism, which utilizes a time-unfolded representation of time-respecting paths in temporal graphs. We compare this definition with existing notions of temporal graph isomorphisms. We illustrate and highlight the advantages of our approach and develop a temporal generalization of the Weisfeiler-Leman algorithm to heuristically distinguish non-isomorphic temporal graphs. Building on this theoretical foundation, we derive a novel message passing scheme for temporal graph neural networks that operates on the event graph representation of temporal graphs. An experimental evaluation shows that our approach performs well in a temporal graph classification experiment.

cs.LG↗

arXiv2025

Deep Graph Learning will stall without Network Science

Deep graph learning focuses on flexible and generalizable models that learn patterns in an automated fashion. Network science focuses on models and measures revealing the organizational principles of complex systems with explicit assumptions. Both fields share the same goal: to better model and understand patterns in graph-structured data. However, deep graph learning prioritizes empirical performance but ignores fundamental insights from network science. Our position is that deep graph learning will stall without insights from network science. In this position paper, we formulate six Calls for Action to leverage untapped insights from network science to address current issues in deep graph learning, ensuring the field continues to make progress.

cs.LG↗

arXiv2024

MDL-Pool: Adaptive Multilevel Graph Pooling Based on Minimum Description Length

Graph pooling compresses graphs and summarises their topological properties and features in a vectorial representation. It is an essential part of deep graph representation learning and is indispensable in graph-level tasks like classification or regression. Current approaches pool hierarchical structures in graphs by iteratively applying shallow pooling operators up to a fixed depth. However, they disregard the interdependencies between structures at different hierarchical levels and do not adapt to datasets that contain graphs with different sizes that may require pooling with various depths. To address these issues, we propose MDL-Pool, a pooling operator based on the minimum description length (MDL) principle, whose loss formulation explicitly models the interdependencies between different hierarchical levels and facilitates a direct comparison between multiple pooling alternatives with different depths. MDP-Pool builds on the map equation, an information-theoretic objective function for community detection, which naturally implements Occam's razor and balances between model complexity and goodness-of-fit via the MDL. We demonstrate MDL-Pool's competitive performance in an empirical evaluation against various baselines across standard graph classification datasets.

cs.LG↗

arXiv2024

Generating Temporal Contact Graphs Using Random Walkers

We study human mobility networks through timeseries of contacts between individuals. Our proposed Random Walkers Induced temporal Graph (RWIG) model generates temporal graph sequences based on independent random walkers that traverse an underlying graph in discrete time steps. Co-location of walkers at a given node and time defines an individual-level contact. RWIG is shown to be a realistic model for temporal human contact graphs, which may place RWIG on a same footing as the Erdos-Renyi (ER) and Barabasi-Albert (BA) models for fixed graphs. Moreover, RWIG is analytically feasible: we derive closed form solutions for the probability distribution of contact graphs.

cs.SI↗

arXiv2024

Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs

The modelling of temporal patterns in dynamic graphs is an important current research issue in the development of time-aware GNNs. Whether or not a specific sequence of events in a temporal graph constitutes a temporal pattern not only depends on the frequency of its occurrence. We consider whether it deviates from what is expected in a temporal graph where timestamps are randomly shuffled. While accounting for such a random baseline is important to model temporal patterns, it has mostly been ignored by current temporal graph neural networks. To address this issue we propose HYPA-DBGNN, a novel two-step approach that combines (i) the inference of anomalous sequential patterns in time series data on graphs based on a statistically principled null model, with (ii) a neural message passing approach that utilizes a higher-order De Bruijn graph whose edges capture overrepresented sequential patterns. Our method leverages hypergeometric graph ensembles to identify anomalous edges within both first- and higher-order De Bruijn graphs, which encode the temporal ordering of events. The model introduces an inductive bias that enhances model interpretability. We evaluate our approach for static node classification using benchmark datasets and a synthetic dataset that showcases its ability to incorporate the observed inductive bias regarding over- and under-represented temporal edges. We demonstrate the framework's effectiveness in detecting similar patterns within empirical datasets, resulting in superior performance compared to baseline methods in node classification tasks. To the best of our knowledge, our work is the first to introduce statistically informed GNNs that leverage temporal and causal sequence anomalies. HYPA-DBGNN represents a path for bridging the gap between statistical graph inference and neural graph representation learning, with potential applications to static GNNs.

cs.LG↗

arXiv2024

Link Prediction with Untrained Message Passing Layers

Message passing neural networks (MPNNs) operate on graphs by exchanging information between neigbouring nodes. MPNNs have been successfully applied to various node-, edge-, and graph-level tasks in areas like molecular science, computer vision, natural language processing, and combinatorial optimization. However, most MPNNs require training on large amounts of labeled data, which can be costly and time-consuming. In this work, we explore the use of various untrained message passing layers in graph neural networks, i.e. variants of popular message passing architecture where we remove all trainable parameters that are used to transform node features in the message passing step. Focusing on link prediction, we find that untrained message passing layers can lead to competitive and even superior performance compared to fully trained MPNNs, especially in the presence of high-dimensional features. We provide a theoretical analysis of untrained message passing by relating the inner products of features implicitly produced by untrained message passing layers to path-based topological node similarity measures. As such, untrained message passing architectures can be viewed as a highly efficient and interpretable approach to link prediction.

cs.LG↗

arXiv2024

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

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 evaluated on continuous-time and discrete-time temporal graph datasets, typically using a traditional batch-oriented evaluation setup. However, as we show in this work, a batch-oriented evaluation is often unsuitable and can cause several issues. Grouping edges into fixed-sized batches regardless of their occurrence time leads to information loss or leakage, depending on the temporal granularity of the data. Furthermore, fixed-size batches create time windows with different durations, resulting in an inconsistent dynamic link prediction task. In this work, we empirically show how traditional batch-based evaluation leads to skewed model performance and hinders the fair comparison of methods. We mitigate this problem by reformulating dynamic link prediction as a link forecasting task that better accounts for temporal information present in the data.

cs.LG↗

arXiv2024

Flow Divergence: Comparing Maps of Flows with Relative Entropy

Networks represent how the entities of a system are connected and can be partitioned differently, prompting ways to compare partitions. Common approaches for comparing network partitions include information-theoretic measures based on mutual information and set-theoretic measures such as the Jaccard index. These measures are often based on computing the agreement in terms of overlap between different partitions of the same set. However, they ignore link patterns which are essential for the organisation of networks. We propose flow divergence, an information-theoretic divergence measure for comparing network partitions, inspired by the ideas behind the Kullback-Leibler divergence and the map equation for community detection. Similar to the Kullback-Leibler divergence, flow divergence adopts a coding perspective and compares two network partitions $\mathsf{M}_a$ and $\mathsf{M}_b$ by considering the expected extra number of bits required to describe a random walk on a network using $\mathsf{M}_b$ relative to reference partition $\mathsf{M}_a$. Because flow divergence is based on random walks, it can be used to compare partitions with arbitrary and different depths. We show that flow divergence distinguishes between partitions that traditional measures consider to be equally good when compared to a reference partition. Applied to real networks, we use flow divergence to estimate the cost of overfitting in incomplete networks and to visualise the solution landscape of network partitions.

cs.SI↗

arXiv2023

The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks

Many Graph Neural Networks (GNNs) add self-loops to a graph to include feature information about a node itself at each layer. However, if the GNN consists of more than one layer, this information can return to its origin via cycles in the graph topology. Intuition suggests that this "backflow" of information should be larger in graphs with self-loops compared to graphs without. In this work, we counter this intuition and show that for certain GNN architectures, the information a node gains from itself can be smaller in graphs with self-loops compared to the same graphs without. We adopt an analytical approach for the study of statistical graph ensembles with a given degree sequence and show that this phenomenon, which we call the self-loop paradox, can depend both on the number of GNN layers $k$ and whether $k$ is even or odd. We experimentally validate our theoretical findings in a synthetic node classification task and investigate its practical relevance in 23 real-world graphs.

cs.LG↗

arXiv2023

Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs

Node centralities play a pivotal role in network science, social network analysis, and recommender systems. In temporal data, static path-based centralities like closeness or betweenness can give misleading results about the true importance of nodes in a temporal graph. To address this issue, temporal generalizations of betweenness and closeness have been defined that are based on the shortest time-respecting paths between pairs of nodes. However, a major issue of those generalizations is that the calculation of such paths is computationally expensive. Addressing this issue, we study the application of De Bruijn Graph Neural Networks (DBGNN), a time-aware graph neural network architecture, to predict temporal path-based centralities in time series data. We experimentally evaluate our approach in 13 temporal graphs from biological and social systems and show that it considerably improves the prediction of betweenness and closeness centrality compared to (i) a static Graph Convolutional Neural Network, (ii) an efficient sampling-based approximation technique for temporal betweenness, and (iii) two state-of-the-art time-aware graph learning techniques for dynamic graphs.

cs.LG↗

arXiv2023

Inference of time-ordered multibody interactions

We introduce time-ordered multibody interactions to describe complex systems manifesting temporal as well as multibody dependencies. First, we show how the dynamics of multivariate Markov chains can be decomposed in ensembles of time-ordered multibody interactions. Then, we present an algorithm to extract those interactions from data capturing the system-level dynamics of node states and a measure to characterize the complexity of interaction ensembles. Finally, we experimentally validate the robustness of our algorithm against statistical errors and its efficiency at inferring parsimonious interaction ensembles.

physics.soc-ph↗

arXiv2023

The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets.

cs.LG↗