Search Results for author:
Found 10 papers, 4 papers with code
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
We introduce $r$-loopy Weisfeiler-Leman ($r$-$\ell{}$WL), a novel hierarchy of graph isomorphism tests and a corresponding GNN framework, $r$-$\ell{}$MPNN, that can count cycles up to length $r + 2$.
An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning
The Rashomon Effect describes the following phenomenon: for a given dataset there may exist many models with equally good performance but with different solution strategies.
Expectation-Complete Graph Representations with Homomorphisms
We investigate novel random graph embeddings that can be computed in expected polynomial time and that are able to distinguish all non-isomorphic graphs in expectation.
A New Aligned Simple German Corpus
"Leichte Sprache", the German counterpart to Simple English, is a regulated language aiming to facilitate complex written language that would otherwise stay inaccessible to different groups of people.
Hidden Schema Networks
Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly.
Graph Filtration Kernels
The majority of popular graph kernels is based on the concept of Haussler's $\mathcal{R}$-convolution kernel and defines graph similarities in terms of mutual substructures.
Explainable Machine Learning with Prior Knowledge: An Overview
This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability.
A Generalized Weisfeiler-Lehman Graph Kernel
The Weisfeiler-Lehman graph kernels are among the most prevalent graph kernels due to their remarkable time complexity and predictive performance.
Multiple Texts as a Limiting Factor in Online Learning: Quantifying (Dis-)similarities of Knowledge Networks across Languages
From the perspective of educational science, the article develops a computational model of the information landscape from which multiple texts are drawn as typical input of web-based reading.
