Search Results for author:
Found 16 papers, 7 papers with code
The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks
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.
Using Causality-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
We experimentally evaluate our approach in 13 temporal graphs from biological and social systems and show that it considerably improves the prediction of both betweenness and closeness centrality compared to a static Graph Convolutional Neural Network.
The Map Equation Goes Neural
We consider the map equation, an information-theoretic objective function for unsupervised community detection.
Bayesian Inference of Transition Matrices from Incomplete Graph Data with a Topological Prior
Lastly, we show that this higher accuracy improves the results for downstream network analysis tasks like cluster detection and node ranking, which highlights the practical relevance of our method for analyses of various networked systems.
One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien's Legendarium
Natural Language Processing and Machine Learning have considerably advanced Computational Literary Studies.
De Bruijn goes Neural: Causality-Aware Graph Neural Networks for Time Series Data on Dynamic Graphs
Our architecture builds on multiple layers of higher-order De Bruijn graphs, an iterative line graph construction where nodes in a De Bruijn graph of order k represent walks of length k-1, while edges represent walks of length k. We develop a graph neural network architecture that utilizes De Bruijn graphs to implement a message passing scheme that follows a non-Markovian dynamics, which enables us to learn patterns in the causal topology of a dynamic graph.
Inference of time-ordered multibody interactions
We introduce time-ordered multibody interactions to describe complex systems manifesting temporal as well as multibody dependencies.
Predicting Influential Higher-Order Patterns in Temporal Network Data
We compare MOGen-based centralities to equivalent measures for network models and path data in a prediction experiment where we aim to identify influential nodes in out-of-sample data.
Predicting Sequences of Traversed Nodes in Graphs using Network Models with Multiple Higher Orders
We propose a novel sequence prediction method for sequential data capturing node traversals in graphs.
Learning the Markov order of paths in a network
We study the problem of learning the Markov order in categorical sequences that represent paths in a network, i. e. sequences of variable lengths where transitions between states are constrained to a known graph.
HOTVis: Higher-Order Time-Aware Visualisation of Dynamic Graphs
Addressing this gap, we present a novel dynamic graph visualisation algorithm that utilises higher-order graphical models of causal paths in time series data to compute time-aware static graph visualisations.
Detecting Path Anomalies in Time Series Data on Networks
Anomaly detection has been extensively studied in categorical sequences, however we often have access to time series data that contain paths through networks.
Social and Information Networks Physics and Society
git2net - Mining Time-Stamped Co-Editing Networks from Large git Repositories
Data from software repositories have become an important foundation for the empirical study of software engineering processes.
Software Engineering
From Relational Data to Graphs: Inferring Significant Links using Generalized Hypergeometric Ensembles
We show how this framework can be used to assess the significance of links in noisy relational data.
Social and Information Networks Physics and Society Methodology 05C82, 91D30, 60C99, 62H10, 62H99
When is a Network a Network? Multi-Order Graphical Model Selection in Pathways and Temporal Networks
An application to eight real-world data sets on pathways and temporal networks shows that it allows to infer graphical models which capture both topological and temporal characteristics of such data.
Social and Information Networks Disordered Systems and Neural Networks Data Analysis, Statistics and Probability Physics and Society H.2.8; G.3
Generalized Hypergeometric Ensembles: Statistical Hypothesis Testing in Complex Networks
Studying empirical and synthetic data, we show that our approach provides broad perspectives for model selection and statistical hypothesis testing in data on complex networks.
Physics and Society Social and Information Networks Combinatorics Data Analysis, Statistics and Probability 05C82 (Primary), 62H15 (Secondary)
