{"id":{"repo_id":"passau-thes","oai_identifier":"oai:kobv.de-opus4-uni-passau:1989"},"canonical_url":"https://search.dev.ndltd.org/etd/passau-thes/oai:kobv.de-opus4-uni-passau:1989","repository":{"repo_id":"passau-thes","name":"Universität Passau","base_url":"https://opus4.kobv.de/opus4-uni-passau/oai"},"display":{"title":"Structure-aware Deep Learning","abstract":"Graph structures permeate the digital landscape in explicit and implicit forms. They connect or construct artifacts by combining semantic and structural information. We also observe them in the systems designed to process this data, in their learning algorithms and the very nature of the tasks they solve. At the same time, machine learning methods are extremely data-hungry, requiring petabytes of data for training. Due to their complexity, graphs remain an under-utilized resource in this regard. Many approaches cannot incorporate them due to being fully structurally unaware or not suited to the specific flavour of graphs encountered in some domains. This disconnect is sub-optimal from an effectiveness and efficiency perspective. We present methods that extend the scope of structure-aware deep learning through structural knowledge integration and enrichment, structural performance prediction, and synergistic transfer learning. Knowledge graphs organize information and make it directly available for querying. They provide a structured inference interface for manual and automated inspection, though they can suffer from data quality issues and require careful schema design. We rephrase the reconciliation of knowledge in knowledge graphs as a link prediction task, making it tractable with adapted graph neural networks, while also benefiting conventional link prediction tasks. We further combine textual semantics and structural expression for legal reference prediction via adapted heterogeneous graph neural networks operating on complex meta-information enriched graphs. Additionally, we explore methods for the integration of intermediary expressions in strongly typed heterogeneous graphs, improving prediction via meta-path-based processing. We also develop methods for automated machine learning workflow analysis and performance prediction. This includes the learning of salient representations for management as well as improvement of workflows through automatic suggestion and refinement of components. These are then extended to the prediction of Neural Architecture Search performance prediction, including adaptation to operation-on-edge spaces. Finally, we investigate the transfer capability of pre-trained attention structures for text-based prediction tasks and find it to be both inferior to directly optimized attention masks as well as highly dependent on inherent domain knowledge. We also show that the exploitation of hierarchical task formulation can improve prediction performance through joint learning in diverse learning domains, including link prediction, performance prediction, and specialized and general argumentation mining. The dissertation contains previously published or submitted texts: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (eds): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, p 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, p 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, p 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (eds) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, p 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, p 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, p 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, submitted to the proceedings of the International Conference on Machine Learning, Optimization, and Data Science 2025, preprint published: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, p 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111.","abstract_html":"Graph structures permeate the digital landscape in explicit and implicit forms. They connect or construct artifacts by combining semantic and structural information. We also observe them in the systems designed to process this data, in their learning algorithms and the very nature of the tasks they solve. At the same time, machine learning methods are extremely data-hungry, requiring petabytes of data for training. Due to their complexity, graphs remain an under-utilized resource in this regard. Many approaches cannot incorporate them due to being fully structurally unaware or not suited to the specific flavour of graphs encountered in some domains. This disconnect is sub-optimal from an effectiveness and efficiency perspective. We present methods that extend the scope of structure-aware deep learning through structural knowledge integration and enrichment, structural performance prediction, and synergistic transfer learning. Knowledge graphs organize information and make it directly available for querying. They provide a structured inference interface for manual and automated inspection, though they can suffer from data quality issues and require careful schema design. We rephrase the reconciliation of knowledge in knowledge graphs as a link prediction task, making it tractable with adapted graph neural networks, while also benefiting conventional link prediction tasks. We further combine textual semantics and structural expression for legal reference prediction via adapted heterogeneous graph neural networks operating on complex meta-information enriched graphs. Additionally, we explore methods for the integration of intermediary expressions in strongly typed heterogeneous graphs, improving prediction via meta-path-based processing. We also develop methods for automated machine learning workflow analysis and performance prediction. This includes the learning of salient representations for management as well as improvement of workflows through automatic suggestion and refinement of components. These are then extended to the prediction of Neural Architecture Search performance prediction, including adaptation to operation-on-edge spaces. Finally, we investigate the transfer capability of pre-trained attention structures for text-based prediction tasks and find it to be both inferior to directly optimized attention masks as well as highly dependent on inherent domain knowledge. We also show that the exploitation of hierarchical task formulation can improve prediction performance through joint learning in diverse learning domains, including link prediction, performance prediction, and specialized and general argumentation mining. The dissertation contains previously published or submitted texts: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (eds): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, p 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, p 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, p 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (eds) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, p 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, p 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, p 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, submitted to the proceedings of the International Conference on Machine Learning, Optimization, and Data Science 2025, preprint published: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, p 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111.","abstract_has_math":false,"creators":["Wendlinger, Lorenz"],"institution":"Universität Passau","degree_name":null,"degree_level":"thesis.doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Granitzer, Michael","Helic, Denis"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12-05","date_published":"2025-12-05","updated_at":"2026-07-24T03:45:12Z","subjects":["graph neural networks","knowledge graphs","structural knowledge integration","structural performance prediction","synergistic transfer learning","link prediction tasks"],"languages":[],"rights":["Standardbedingung laut Einverständniserklärung"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://opus4.kobv.de/opus4-uni-passau/frontdoor/index/index/docId/1989","outbound_label":"Repository record","outbound_source":"source_url"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Granitzer, Michael","Helic, Denis"]},{"key":"dc:creator","label":"Author","values":["Wendlinger, Lorenz"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:publisher","label":"Institution","values":["Universität Passau"]},{"key":"dc:type","label":"Dc Type","values":["doctoralThesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["thesis.doctoral"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Universität Passau"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["graph neural networks","knowledge graphs","structural knowledge integration","structural performance prediction","synergistic transfer learning","link prediction tasks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Standardbedingung laut Einverständniserklärung"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Graph structures permeate the digital landscape in explicit and implicit forms. They connect or construct artifacts by combining semantic and structural information. We also observe them in the systems designed to process this data, in their learning algorithms and the very nature of the tasks they solve. At the same time, machine learning methods are extremely data-hungry, requiring petabytes of data for training. Due to their complexity, graphs remain an under-utilized resource in this regard. Many approaches cannot incorporate them due to being fully structurally unaware or not suited to the specific flavour of graphs encountered in some domains. This disconnect is sub-optimal from an effectiveness and efficiency perspective. We present methods that extend the scope of structure-aware deep learning through structural knowledge integration and enrichment, structural performance prediction, and synergistic transfer learning. Knowledge graphs organize information and make it directly available for querying. They provide a structured inference interface for manual and automated inspection, though they can suffer from data quality issues and require careful schema design. We rephrase the reconciliation of knowledge in knowledge graphs as a link prediction task, making it tractable with adapted graph neural networks, while also benefiting conventional link prediction tasks. We further combine textual semantics and structural expression for legal reference prediction via adapted heterogeneous graph neural networks operating on complex meta-information enriched graphs. Additionally, we explore methods for the integration of intermediary expressions in strongly typed heterogeneous graphs, improving prediction via meta-path-based processing. We also develop methods for automated machine learning workflow analysis and performance prediction. This includes the learning of salient representations for management as well as improvement of workflows through automatic suggestion and refinement of components. These are then extended to the prediction of Neural Architecture Search performance prediction, including adaptation to operation-on-edge spaces. Finally, we investigate the transfer capability of pre-trained attention structures for text-based prediction tasks and find it to be both inferior to directly optimized attention masks as well as highly dependent on inherent domain knowledge. We also show that the exploitation of hierarchical task formulation can improve prediction performance through joint learning in diverse learning domains, including link prediction, performance prediction, and specialized and general argumentation mining. The dissertation contains previously published or submitted texts: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (eds): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, p 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, p 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, p 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (eds) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, p 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, p 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, p 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, submitted to the proceedings of the International Conference on Machine Learning, Optimization, and Data Science 2025, preprint published: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, p 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111.","Graphenstrukturen durchdringen die digitale Landschaft in expliziten und impliziten Formen. Sie verbinden oder konstruieren Artefakte, indem sie semantische und strukturelle Informationen kombinieren. Wir beobachten sie auch in den Systemen, die zur Verarbeitung dieser Daten entwickelt wurden, in ihren Lernalgorithmen und in der Art der Aufgaben, die sie lösen. Gleichzeitig sind die Methoden des maschinellen Lernens extrem datenhungrig und benötigen Petabytes an Daten für das Training. Aufgrund ihrer Komplexität bleiben Graphen in dieser Hinsicht eine unzureichend genutzte Ressource. Viele Ansätze können sie nicht einbeziehen, weil sie die Struktur der Graphen nicht kennen oder nicht für die spezielle Art von Graphen geeignet sind, die in einigen Bereichen vorkommen. Diese Trennung ist aus Sicht der Effektivität und Effizienz suboptimal. Wir stellen Methoden vor, die den Anwendungsbereich des strukturbewussten Deep Learning durch strukturelle Wissensintegration und -anreicherung, strukturelle Leistungsvorhersage und synergetisches Transferlernen erweitern. Wissensgraphen organisieren Informationen und machen sie direkt für Abfragen verfügbar. Sie bieten eine strukturierte Inferenzschnittstelle für die manuelle und automatische Überprüfung, obwohl sie unter Problemen der Datenqualität leiden können und ein sorgfältiges Schemadesign erfordern. Wir formulieren den Abgleich von Wissen in Wissensgraphen als eine Aufgabe der Kantenvorhersage um, die mit angepassten neuronalen Netzen für Graphen durchführbar ist und auch konventionellen Kantenvorhersageaufgaben zugute kommt. Darüber hinaus kombinieren wir Textsemantik und strukturelle Ausdrücke für die Vorhersage rechtlicher Verweise mit Hilfe angepasster heterogener Graph neuronaler Netze, die auf komplexen, mit Metainformationen angereicherten Graphen arbeiten. Darüber hinaus erforschen wir Methoden zur Integration von intermediären Ausdrücken in stark typisierten heterogenen Graphen und verbessern die Vorhersage durch metapfadbasierte Verarbeitung. Wir entwickeln auch Methoden für die automatische Analyse von Prozessbeschreibungen und Leistungsvorhersagen für maschinelles Lernen. Dies beinhaltet das Lernen von bedeutungsvollen Repräsentationen für das Management sowie die Verbesserung von Prozessbeschreibungen durch automatische Vorschläge und Verfeinerung von Komponenten. Diese Methoden werden dann auf die Leistungsvorhersage der neuronalen Architektursuche ausgeweitet, einschließlich der Anpassung an die Operation-on-Edge-Räume. Schließlich untersuchen wir die Transferfähigkeit von vortrainierten Aufmerksamkeitsstrukturen für textbasierte Vorhersageaufgaben und stellen fest, dass diese sowohl den direkt optimierten Aufmerksamkeitsmasken unterlegen sind als auch in hohem Maße vom inhärenten Domänenwissen abhängen. Wir zeigen auch, dass die Ausnutzung hierarchischer Aufgabenformulierung die Vorhersageleistung durch gemeinsames Lernen in verschiedenen Lernbereichen verbessern kann, einschließlich Kantenvorhersage, Leistungsvorhersage und spezialisierter und allgemeiner Argumentationsanalyse. Die Dissertation beinhaltet bereits veröffentlichte oder zur Veröffentlichung vorgesehene Texte: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (Hgg.): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, S. 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, S. 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (Hgg.) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, S. 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (Hgg.) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, S. 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (Hgg.) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, S. 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, S. 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, eingereicht für die Proceedings der International Conference on Machine Learning, Optimization, and Data Science 2025, vorab veröffentlicht: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, S. 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Structure-aware Deep Learning"]}]}],"canonical_facts":{"dc:contributor":["Granitzer, Michael","Helic, Denis"],"dc:creator":["Wendlinger, Lorenz"],"dc:description.abstract":["Graph structures permeate the digital landscape in explicit and implicit forms. They connect or construct artifacts by combining semantic and structural information. We also observe them in the systems designed to process this data, in their learning algorithms and the very nature of the tasks they solve. At the same time, machine learning methods are extremely data-hungry, requiring petabytes of data for training. Due to their complexity, graphs remain an under-utilized resource in this regard. Many approaches cannot incorporate them due to being fully structurally unaware or not suited to the specific flavour of graphs encountered in some domains. This disconnect is sub-optimal from an effectiveness and efficiency perspective. We present methods that extend the scope of structure-aware deep learning through structural knowledge integration and enrichment, structural performance prediction, and synergistic transfer learning. Knowledge graphs organize information and make it directly available for querying. They provide a structured inference interface for manual and automated inspection, though they can suffer from data quality issues and require careful schema design. We rephrase the reconciliation of knowledge in knowledge graphs as a link prediction task, making it tractable with adapted graph neural networks, while also benefiting conventional link prediction tasks. We further combine textual semantics and structural expression for legal reference prediction via adapted heterogeneous graph neural networks operating on complex meta-information enriched graphs. Additionally, we explore methods for the integration of intermediary expressions in strongly typed heterogeneous graphs, improving prediction via meta-path-based processing. We also develop methods for automated machine learning workflow analysis and performance prediction. This includes the learning of salient representations for management as well as improvement of workflows through automatic suggestion and refinement of components. These are then extended to the prediction of Neural Architecture Search performance prediction, including adaptation to operation-on-edge spaces. Finally, we investigate the transfer capability of pre-trained attention structures for text-based prediction tasks and find it to be both inferior to directly optimized attention masks as well as highly dependent on inherent domain knowledge. We also show that the exploitation of hierarchical task formulation can improve prediction performance through joint learning in diverse learning domains, including link prediction, performance prediction, and specialized and general argumentation mining. The dissertation contains previously published or submitted texts: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (eds): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, p 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, p 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, p 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (eds) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, p 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, p 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, p 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, submitted to the proceedings of the International Conference on Machine Learning, Optimization, and Data Science 2025, preprint published: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, p 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111.","Graphenstrukturen durchdringen die digitale Landschaft in expliziten und impliziten Formen. Sie verbinden oder konstruieren Artefakte, indem sie semantische und strukturelle Informationen kombinieren. Wir beobachten sie auch in den Systemen, die zur Verarbeitung dieser Daten entwickelt wurden, in ihren Lernalgorithmen und in der Art der Aufgaben, die sie lösen. Gleichzeitig sind die Methoden des maschinellen Lernens extrem datenhungrig und benötigen Petabytes an Daten für das Training. Aufgrund ihrer Komplexität bleiben Graphen in dieser Hinsicht eine unzureichend genutzte Ressource. Viele Ansätze können sie nicht einbeziehen, weil sie die Struktur der Graphen nicht kennen oder nicht für die spezielle Art von Graphen geeignet sind, die in einigen Bereichen vorkommen. Diese Trennung ist aus Sicht der Effektivität und Effizienz suboptimal. Wir stellen Methoden vor, die den Anwendungsbereich des strukturbewussten Deep Learning durch strukturelle Wissensintegration und -anreicherung, strukturelle Leistungsvorhersage und synergetisches Transferlernen erweitern. Wissensgraphen organisieren Informationen und machen sie direkt für Abfragen verfügbar. Sie bieten eine strukturierte Inferenzschnittstelle für die manuelle und automatische Überprüfung, obwohl sie unter Problemen der Datenqualität leiden können und ein sorgfältiges Schemadesign erfordern. Wir formulieren den Abgleich von Wissen in Wissensgraphen als eine Aufgabe der Kantenvorhersage um, die mit angepassten neuronalen Netzen für Graphen durchführbar ist und auch konventionellen Kantenvorhersageaufgaben zugute kommt. Darüber hinaus kombinieren wir Textsemantik und strukturelle Ausdrücke für die Vorhersage rechtlicher Verweise mit Hilfe angepasster heterogener Graph neuronaler Netze, die auf komplexen, mit Metainformationen angereicherten Graphen arbeiten. Darüber hinaus erforschen wir Methoden zur Integration von intermediären Ausdrücken in stark typisierten heterogenen Graphen und verbessern die Vorhersage durch metapfadbasierte Verarbeitung. Wir entwickeln auch Methoden für die automatische Analyse von Prozessbeschreibungen und Leistungsvorhersagen für maschinelles Lernen. Dies beinhaltet das Lernen von bedeutungsvollen Repräsentationen für das Management sowie die Verbesserung von Prozessbeschreibungen durch automatische Vorschläge und Verfeinerung von Komponenten. Diese Methoden werden dann auf die Leistungsvorhersage der neuronalen Architektursuche ausgeweitet, einschließlich der Anpassung an die Operation-on-Edge-Räume. Schließlich untersuchen wir die Transferfähigkeit von vortrainierten Aufmerksamkeitsstrukturen für textbasierte Vorhersageaufgaben und stellen fest, dass diese sowohl den direkt optimierten Aufmerksamkeitsmasken unterlegen sind als auch in hohem Maße vom inhärenten Domänenwissen abhängen. Wir zeigen auch, dass die Ausnutzung hierarchischer Aufgabenformulierung die Vorhersageleistung durch gemeinsames Lernen in verschiedenen Lernbereichen verbessern kann, einschließlich Kantenvorhersage, Leistungsvorhersage und spezialisierter und allgemeiner Argumentationsanalyse. Die Dissertation beinhaltet bereits veröffentlichte oder zur Veröffentlichung vorgesehene Texte: Wendlinger, L., Hübscher, G., Ekelhart, A., Granitzer, M. (2022). Reconciliation of Mental Concepts with Graph Neural Networks. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (Hgg.): Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13427, S. 133-146. Springer, Cham. https://doi.org/10.1007/978-3-031-12426-6_11; Wendlinger, L., Granitzer M. (2024). Informed Heterogeneous Attention Networks for Metapath Based Learning. In: SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, S. 458-465, ACM, New York. https://doi.org/10.1145/3605098.3635890; Wendlinger, L., Nonn, S.A., Al Zubaer, A., Granitzer, M. (2026). The Missing Link: Joint Legal Citation Prediction Using Heterogeneous Graph Enrichment. In: Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (Hgg.) Database and Expert Systems Applications. DEXA 2025. Lecture Notes in Computer Science, vol 16047, S. 197-211. Springer, Cham. https://doi.org/10.1007/978-3-032-02088-8_14; Wendlinger, L., Stier, J., Granitzer, M. (2021). Evofficient: Reproducing a Cartesian Genetic Programming Method. In: Hu, T., Lourenço, N., Medvet, E. (Hgg.) Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, vol 12691, S. 162-178. Springer, Cham. https://doi.org/10.1007/978-3-030-72812-0_11; Wendlinger, L., Berndl, E., Granitzer, M. (2021). Methods for Automatic Machine-Learning Workflow Analysis. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (Hgg.) Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2021. Lecture Notes in Computer Science, vol 12979, S. 52-67. Springer, Cham. https://doi.org/10.1007/978-3-030-86517-7_4; Wendlinger, L., Granitzer, M., Fellicious, C. (2023). Pooling Graph Convolutional Networks for Structural Performance Prediction. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811, S. 1-16. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_1; Wendlinger, L., Braun, C., Zubaer, A., Nonn, S., Großkopf, S., Fellicious, C., Granitzer, M.: On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education, eingereicht für die Proceedings der International Conference on Machine Learning, Optimization, and Data Science 2025, vorab veröffentlicht: https://doi.org/10.48550/arXiv.2412.15902; Wendlinger, L., Kuhn, R., Mitrovic, J., Granitzer, M. (2025). Joint Learning for Efficient German Argument Mining. In: 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Greece, 2025, S. 770-777. IEEE, Los Alamitos. https://doi.org/10.1109/ICTAI66417.2025.00111."],"dc:format.medium":["application/pdf"],"dc:publisher":["Universität Passau"],"dc:rights":["Standardbedingung laut Einverständniserklärung"],"dc:subject":["graph neural networks","knowledge graphs","structural knowledge integration","structural performance prediction","synergistic transfer learning","link prediction tasks"],"dc:title":["Structure-aware Deep Learning"],"dc:type":["doctoralThesis"],"thesis:degree_level":["thesis.doctoral"],"thesis:institution_name":["Universität Passau"]},"updated_at":"2026-07-24T03:45:12Z"}