Publications

Summary Federated learning enables collaboration in medicine, where data is scattered across multiple centers without the need to aggregate the data in a central cloud. While, in general, machine learning models can be applied to a wide range of data types, graph neural networks (GNNs) are particularly developed for graphs, which are very common in…

We explore the integration of domain knowledge graphs into Deep Learning for improved interpretability and explainability using Graph Neural Networks (GNNs). Specifically, a protein-protein interaction (PPI) network is masked over a deep neural network for classification, with patient-specific multi-modal genomic features enriched into the PPI graph’s nodes. Subnetworks that are relevant to the classification (referred…

Asymmetric Shapley values (ASVs) are an extension of Shapley values that allow a user to incorporate partial causal knowledge into the explanation process. Unfortunately, computing ASVs requires sampling permutations, which quickly becomes computationally expensive. We propose A-PDD-SHAP, an algorithm that employs a functional decomposition approach to approximate ASVs at a speed orders of magnitude faster…

Artificial intelligence (AI) today is very successful at standard pattern-recognition tasks due to the availability of large amounts of data and advances in statistical data-driven machine learning. However, there is still a large gap between AI pattern recognition and human-level concept learning. Humans can learn amazingly well even under uncertainty from just a few examples…

Background Machine learning and artificial intelligence have shown promising results in many areas and are driven by the increasing amount of available data. However, these data are often distributed across different institutions and cannot be easily shared owing to strict privacy regulations. Federated learning (FL) allows the training of distributed machine learning models without sharing…

Explainable AI (XAI) is an increasingly important area of research in machine learning, which in principle aims to make blackbox models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses counterfactual paths generated by conditional perturbations. Our method provides counterfactual explanations by identifying alternative paths that could have led…

One of the long-term goals of Digital Transformation in agriculture and forestry is for autonomous agents to be able to perform tasks that are currently done by human workers. For reasons of increasing safety, precision and resources, autonomous robots could efficiently navigate into the forests or fields, gathering different types of data (images, 3D point…

Correction: Generating Explanations for Conceptual Validation of Graph Neural Networks Page 1 CORRECTION KI – Künstliche Intelligenz https://doi.org/10.1007/s13218-022-00789-z Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original…

Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain’s and user’s perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs,…

BackgroundLack of trust in artificial intelligence (AI) models in medicine is still the key blockage for the use of AI in clinical decision support systems (CDSS). Although AI models are already performing excellently in systems medicine, their black-box nature entails that patient-specific decisions are incomprehensible for the physician. This is especially true for very complex…