Dr. Anna Saranti

AI Engineer, Speaker, Researcher

Portrait of Dr. Anna Saranti

Anna Saranti

Dr. techn. Dipl.-Ing.

Welcome to my blog; a place where I am inspired and creative about AI and non-AI topics.

AI Engineer with a master’s degree (Dipl.-Ing.) and PhD (Dr.techn.)
with distinction from Graz University of Technology (TUGraz).
Worked both in industry as a Data Scientist, AI Engineer and Software Developer as well as a researcher at universities with an h-index of 22.


Contact me on Linkedin.

  • Efficient approximation of asymmetric shapley values using functional decomposition

    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…

  • Human-in-the-loop integration with domain-knowledge graphs for explainable federated deep learning

    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…

  • Toward human-level concept learning: Pattern benchmarking for AI algorithms

    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…

  • The FeatureCloud platform for federated learning in biomedicine: unified approach

    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 with counterfactual paths

    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…

  • Tree marking recognition and classification from 3D LiDAR point clouds-Internship report

    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…