Nature-Inspired Machine Learning (NIMI)

Group leader

Nature-Inspired Machine Learning (NIMI)

Sahar Vahdati is a Professor of AI for Scholarly Communication at TIB – Leibniz Information Centre for Science and Technology and Hannover University. Passionate about the transformative power of artificial intelligence, Sahar is dedicated to exploring its positive impact on life, humanity, nature, and the environment.

She leads the Nature-Inspired Machine Learning Research Group, a cross-organizational initiative uniting expertise from Hannover, Leipzig, and Dresden. Her research focuses on advancing representation learning and foundational models, with the goal of addressing scientific and societal challenges. Sahar has contributed to more than 100 scholarly publications, which are frequently cited and have significantly influenced the AI and machine learning communities.

In addition to her research leadership, Sahar serves as the General Chair of the SEMANTiCS conference, where she champions the mission of bringing science into practice with tangible, positive impacts. With a vision rooted in innovation and collaboration, she is committed to using AI as a force for good.

Proof. Vahdati is deeply passionate about integrating AI into science and education, aiming to enhance learning experiences and accelerate scientific discovery. In her spare time, she is working on Enigmia, an innovative application designed to solve complex math riddles and puzzles, showcasing her dedication to blending creativity and AI for educational purposes.

Here is the list of my academic degrees and the research organizations in which I conducted my research over the past years:

  • Research Group Lead at the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig.

  • Research Group Lead of Nature-Inspired Machine Intelligence at the Institute for Applied In-formatics (InfAI) Institute in Dresden.

  • Postdoctoral Fellow in the Intelligent Information Systems group at the Department of Computer Science, University of Oxford, UK – led by Prof. Georg Gottlob.

  • Postdoctoral Fellow in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn.

  • PhD of Natural Science (Dr. rer. nat) in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – doctoral dissertation under supervision of Prof. S¨oren Auer at the Enterprise Information System (EIS) group.

  • Master of Computer Science in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – master thesis under the supervision of Prof. Rainer Manthey, and Prof. Andreas Behrend at the the Intelligent Databases (IDB) group.

  • Bachelor of Software Engineering in Tabriz, Iran – bachelor thesis under the supervision of Prof. Farhad Pourreza.

The details related to the development of my research in each of the above-mentioned career steps can be summarized as the following disciplines:

Knowledge-driven AI

Since 1st September 2023, I joined TU Dresden and the Scdas.AI center as research group. I mainly target to build up a group with a focus on the connection of knowledge graphs and large language models, and the role of Neuro-symbolic methods for future learning models. My position is funded with additional two doctoral students with whom I am exploring the above-mentioned topics.

Representation Learning

Since I joined InfAI in 2020 a research group leader, I worked on my vision of Nature-Inspired Machine Intel-ligence. We acquired group budget through EKFZ funding, and EU projects. I have been directing the group research activities, and research mainly on my vision for research in machine intelligence inspired by natural science that can result in innovations to address weaknesses of current ML approaches. The main activities of the group and planned research directions are focused on representation learning.

Learning and Reasoning in Large Scale Knowledge Graphs.

Shortly before finishing my dissertation, I became very interested in using link prediction techniques over the scholarly knowledge graph we had constructed by then. I used link prediction techniques to provide recommendations in the context of scholarly communication. Initially, I used graph partition approaches relying on semantic similarity measures to determine the relatedness between scholarly entities. I further continued with this line of research by using knowledge graph embedding (KGE) models in several other use cases, as well proposing new models. This is still a focal research direction of myself and my group.

Knowledge Graph-empowered Intelligent Information Systems

The core of my PhD topic was to explore the challenges and approaches for automated knowledge acquisition and curation, integration and management of heterogeneous metadata on the Web towards. This research has been conducted using the example of scholarly metadata towards a collaborative construction and management of a science knowledge graph. The aim was to facilitate the integrated use of different knowledge-aware AI-based methods, analytical techniques, and tools for improving scholarly communication. My research contributions provide useful approaches by following the FAIR data principles and providing metadata in a findable, accessible, interoperable, and reusable format. Efficient and scalable methods for integrating large amounts of data, as well as knowledge representation and discovery, were key challenges that I tackled. As a major part of my research activities, I constructed a specific knowledge graph for which I also provided quality-based assessments and meta research analytics by applying data mining and link discovery approaches.

Scientific publishing I published at venues that target core of artificial intelligence that deals with knowledge representation, learning and management such as ECAI, AAAI, EMNLP, IJCNN, IEEE Access, PAKDD, EDBT, ILP, ESWC, EKAW, TPDL, ICSC, MTSR, ECIR, and SEMANTiCS. I value collaborative research work and have conducted research not only with members of the Computer Science department at the University of Bonn and University of Oxford but also with the Knowledge Media Institute at the Open University London – UK, the CNR research council of Italy, Institute Mihajlo Pupin, Belgrade in Serbia, the University Hospital Dresden, the University Hospital Leipzig, the L3S Research Center in Hanover, and University of Vienna . Community involvement and Event Organization Active community involvement is very rewarding and beneficial for increasing the impact of science in general. I am the co-general chair of SEMANTICS conference with approximately 500 visitors per year.

91 entries « 29 of 31 »

2015

Vahdati, Sahar; Lange, Christoph; Auer, Sören

OpenCourseWare observatory: does the quality of OpenCourseWare live up to its promise? Proceedings Article

In: Baron, Josh; Lynch, Grace; Maziarz, Nicole; Blikstein, Paulo; Merceron, Agathe; Siemens, George (Ed.): Proceedings of the Fifth International Conference on Learning Analytics And Knowledge, LAK '15, Poughkeepsie, NY, USA, March 16-20, 2015, pp. 73–82, ACM, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Proceedings Article

In: Garoufallou, Emmanouel; Hartley, Richard J.; Gaitanou, Panorea (Ed.): Metadata and Semantics Research - 9th Research Conference, MTSR 2015, Manchester, UK, September 9-11, 2015, Proceedings, pp. 261–273, Springer, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Journal Article

In: CoRR, vol. abs/1506.04006, 2015.

BibTeX | Links:

91 entries « 29 of 31 »

Prof. Dr. Sahar Vahdati

Group leader

Nature-Inspired Machine Learning (NIMI)

Sahar Vahdati is a Professor of AI for Scholarly Communication at TIB – Leibniz Information Centre for Science and Technology and Hannover University. Passionate about the transformative power of artificial intelligence, Sahar is dedicated to exploring its positive impact on life, humanity, nature, and the environment.

She leads the Nature-Inspired Machine Learning Research Group, a cross-organizational initiative uniting expertise from Hannover, Leipzig, and Dresden. Her research focuses on advancing representation learning and foundational models, with the goal of addressing scientific and societal challenges. Sahar has contributed to more than 100 scholarly publications, which are frequently cited and have significantly influenced the AI and machine learning communities.

In addition to her research leadership, Sahar serves as the General Chair of the SEMANTiCS conference, where she champions the mission of bringing science into practice with tangible, positive impacts. With a vision rooted in innovation and collaboration, she is committed to using AI as a force for good.

Proof. Vahdati is deeply passionate about integrating AI into science and education, aiming to enhance learning experiences and accelerate scientific discovery. In her spare time, she is working on Enigmia, an innovative application designed to solve complex math riddles and puzzles, showcasing her dedication to blending creativity and AI for educational purposes.

Here is the list of my academic degrees and the research organizations in which I conducted my research over the past years:

  • Research Group Lead at the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig.

  • Research Group Lead of Nature-Inspired Machine Intelligence at the Institute for Applied In-formatics (InfAI) Institute in Dresden.

  • Postdoctoral Fellow in the Intelligent Information Systems group at the Department of Computer Science, University of Oxford, UK – led by Prof. Georg Gottlob.

  • Postdoctoral Fellow in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn.

  • PhD of Natural Science (Dr. rer. nat) in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – doctoral dissertation under supervision of Prof. S¨oren Auer at the Enterprise Information System (EIS) group.

  • Master of Computer Science in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – master thesis under the supervision of Prof. Rainer Manthey, and Prof. Andreas Behrend at the the Intelligent Databases (IDB) group.

  • Bachelor of Software Engineering in Tabriz, Iran – bachelor thesis under the supervision of Prof. Farhad Pourreza.

The details related to the development of my research in each of the above-mentioned career steps can be summarized as the following disciplines:

Knowledge-driven AI

Since 1st September 2023, I joined TU Dresden and the Scdas.AI center as research group. I mainly target to build up a group with a focus on the connection of knowledge graphs and large language models, and the role of Neuro-symbolic methods for future learning models. My position is funded with additional two doctoral students with whom I am exploring the above-mentioned topics.

Representation Learning

Since I joined InfAI in 2020 a research group leader, I worked on my vision of Nature-Inspired Machine Intel-ligence. We acquired group budget through EKFZ funding, and EU projects. I have been directing the group research activities, and research mainly on my vision for research in machine intelligence inspired by natural science that can result in innovations to address weaknesses of current ML approaches. The main activities of the group and planned research directions are focused on representation learning.

Learning and Reasoning in Large Scale Knowledge Graphs.

Shortly before finishing my dissertation, I became very interested in using link prediction techniques over the scholarly knowledge graph we had constructed by then. I used link prediction techniques to provide recommendations in the context of scholarly communication. Initially, I used graph partition approaches relying on semantic similarity measures to determine the relatedness between scholarly entities. I further continued with this line of research by using knowledge graph embedding (KGE) models in several other use cases, as well proposing new models. This is still a focal research direction of myself and my group.

Knowledge Graph-empowered Intelligent Information Systems

The core of my PhD topic was to explore the challenges and approaches for automated knowledge acquisition and curation, integration and management of heterogeneous metadata on the Web towards. This research has been conducted using the example of scholarly metadata towards a collaborative construction and management of a science knowledge graph. The aim was to facilitate the integrated use of different knowledge-aware AI-based methods, analytical techniques, and tools for improving scholarly communication. My research contributions provide useful approaches by following the FAIR data principles and providing metadata in a findable, accessible, interoperable, and reusable format. Efficient and scalable methods for integrating large amounts of data, as well as knowledge representation and discovery, were key challenges that I tackled. As a major part of my research activities, I constructed a specific knowledge graph for which I also provided quality-based assessments and meta research analytics by applying data mining and link discovery approaches.

Scientific publishing I published at venues that target core of artificial intelligence that deals with knowledge representation, learning and management such as ECAI, AAAI, EMNLP, IJCNN, IEEE Access, PAKDD, EDBT, ILP, ESWC, EKAW, TPDL, ICSC, MTSR, ECIR, and SEMANTiCS. I value collaborative research work and have conducted research not only with members of the Computer Science department at the University of Bonn and University of Oxford but also with the Knowledge Media Institute at the Open University London – UK, the CNR research council of Italy, Institute Mihajlo Pupin, Belgrade in Serbia, the University Hospital Dresden, the University Hospital Leipzig, the L3S Research Center in Hanover, and University of Vienna . Community involvement and Event Organization Active community involvement is very rewarding and beneficial for increasing the impact of science in general. I am the co-general chair of SEMANTICS conference with approximately 500 visitors per year.

91 entries « 29 of 31 »

2015

Vahdati, Sahar; Lange, Christoph; Auer, Sören

OpenCourseWare observatory: does the quality of OpenCourseWare live up to its promise? Proceedings Article

In: Baron, Josh; Lynch, Grace; Maziarz, Nicole; Blikstein, Paulo; Merceron, Agathe; Siemens, George (Ed.): Proceedings of the Fifth International Conference on Learning Analytics And Knowledge, LAK '15, Poughkeepsie, NY, USA, March 16-20, 2015, pp. 73–82, ACM, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Proceedings Article

In: Garoufallou, Emmanouel; Hartley, Richard J.; Gaitanou, Panorea (Ed.): Metadata and Semantics Research - 9th Research Conference, MTSR 2015, Manchester, UK, September 9-11, 2015, Proceedings, pp. 261–273, Springer, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Journal Article

In: CoRR, vol. abs/1506.04006, 2015.

BibTeX | Links:

91 entries « 29 of 31 »

Publications

Group leader

Nature-Inspired Machine Learning (NIMI)

Sahar Vahdati is a Professor of AI for Scholarly Communication at TIB – Leibniz Information Centre for Science and Technology and Hannover University. Passionate about the transformative power of artificial intelligence, Sahar is dedicated to exploring its positive impact on life, humanity, nature, and the environment.

She leads the Nature-Inspired Machine Learning Research Group, a cross-organizational initiative uniting expertise from Hannover, Leipzig, and Dresden. Her research focuses on advancing representation learning and foundational models, with the goal of addressing scientific and societal challenges. Sahar has contributed to more than 100 scholarly publications, which are frequently cited and have significantly influenced the AI and machine learning communities.

In addition to her research leadership, Sahar serves as the General Chair of the SEMANTiCS conference, where she champions the mission of bringing science into practice with tangible, positive impacts. With a vision rooted in innovation and collaboration, she is committed to using AI as a force for good.

Proof. Vahdati is deeply passionate about integrating AI into science and education, aiming to enhance learning experiences and accelerate scientific discovery. In her spare time, she is working on Enigmia, an innovative application designed to solve complex math riddles and puzzles, showcasing her dedication to blending creativity and AI for educational purposes.

Here is the list of my academic degrees and the research organizations in which I conducted my research over the past years:

  • Research Group Lead at the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig.

  • Research Group Lead of Nature-Inspired Machine Intelligence at the Institute for Applied In-formatics (InfAI) Institute in Dresden.

  • Postdoctoral Fellow in the Intelligent Information Systems group at the Department of Computer Science, University of Oxford, UK – led by Prof. Georg Gottlob.

  • Postdoctoral Fellow in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn.

  • PhD of Natural Science (Dr. rer. nat) in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – doctoral dissertation under supervision of Prof. S¨oren Auer at the Enterprise Information System (EIS) group.

  • Master of Computer Science in the department of Intelligent Systems (Institute of Computer Science III) at the University of Bonn, Germany – master thesis under the supervision of Prof. Rainer Manthey, and Prof. Andreas Behrend at the the Intelligent Databases (IDB) group.

  • Bachelor of Software Engineering in Tabriz, Iran – bachelor thesis under the supervision of Prof. Farhad Pourreza.

The details related to the development of my research in each of the above-mentioned career steps can be summarized as the following disciplines:

Knowledge-driven AI

Since 1st September 2023, I joined TU Dresden and the Scdas.AI center as research group. I mainly target to build up a group with a focus on the connection of knowledge graphs and large language models, and the role of Neuro-symbolic methods for future learning models. My position is funded with additional two doctoral students with whom I am exploring the above-mentioned topics.

Representation Learning

Since I joined InfAI in 2020 a research group leader, I worked on my vision of Nature-Inspired Machine Intel-ligence. We acquired group budget through EKFZ funding, and EU projects. I have been directing the group research activities, and research mainly on my vision for research in machine intelligence inspired by natural science that can result in innovations to address weaknesses of current ML approaches. The main activities of the group and planned research directions are focused on representation learning.

Learning and Reasoning in Large Scale Knowledge Graphs.

Shortly before finishing my dissertation, I became very interested in using link prediction techniques over the scholarly knowledge graph we had constructed by then. I used link prediction techniques to provide recommendations in the context of scholarly communication. Initially, I used graph partition approaches relying on semantic similarity measures to determine the relatedness between scholarly entities. I further continued with this line of research by using knowledge graph embedding (KGE) models in several other use cases, as well proposing new models. This is still a focal research direction of myself and my group.

Knowledge Graph-empowered Intelligent Information Systems

The core of my PhD topic was to explore the challenges and approaches for automated knowledge acquisition and curation, integration and management of heterogeneous metadata on the Web towards. This research has been conducted using the example of scholarly metadata towards a collaborative construction and management of a science knowledge graph. The aim was to facilitate the integrated use of different knowledge-aware AI-based methods, analytical techniques, and tools for improving scholarly communication. My research contributions provide useful approaches by following the FAIR data principles and providing metadata in a findable, accessible, interoperable, and reusable format. Efficient and scalable methods for integrating large amounts of data, as well as knowledge representation and discovery, were key challenges that I tackled. As a major part of my research activities, I constructed a specific knowledge graph for which I also provided quality-based assessments and meta research analytics by applying data mining and link discovery approaches.

Scientific publishing I published at venues that target core of artificial intelligence that deals with knowledge representation, learning and management such as ECAI, AAAI, EMNLP, IJCNN, IEEE Access, PAKDD, EDBT, ILP, ESWC, EKAW, TPDL, ICSC, MTSR, ECIR, and SEMANTiCS. I value collaborative research work and have conducted research not only with members of the Computer Science department at the University of Bonn and University of Oxford but also with the Knowledge Media Institute at the Open University London – UK, the CNR research council of Italy, Institute Mihajlo Pupin, Belgrade in Serbia, the University Hospital Dresden, the University Hospital Leipzig, the L3S Research Center in Hanover, and University of Vienna . Community involvement and Event Organization Active community involvement is very rewarding and beneficial for increasing the impact of science in general. I am the co-general chair of SEMANTICS conference with approximately 500 visitors per year.

91 entries « 29 of 31 »

2015

Vahdati, Sahar; Lange, Christoph; Auer, Sören

OpenCourseWare observatory: does the quality of OpenCourseWare live up to its promise? Proceedings Article

In: Baron, Josh; Lynch, Grace; Maziarz, Nicole; Blikstein, Paulo; Merceron, Agathe; Siemens, George (Ed.): Proceedings of the Fifth International Conference on Learning Analytics And Knowledge, LAK '15, Poughkeepsie, NY, USA, March 16-20, 2015, pp. 73–82, ACM, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Proceedings Article

In: Garoufallou, Emmanouel; Hartley, Richard J.; Gaitanou, Panorea (Ed.): Metadata and Semantics Research - 9th Research Conference, MTSR 2015, Manchester, UK, September 9-11, 2015, Proceedings, pp. 261–273, Springer, 2015.

BibTeX | Links:

Vahdati, Sahar; Karim, Farah; Huang, Jyun-Yao; Lange, Christoph

Mapping Large Scale Research Metadata to Linked Data: A Performance Comparison of HBase, CSV and XML Journal Article

In: CoRR, vol. abs/1506.04006, 2015.

BibTeX | Links:

91 entries « 29 of 31 »

Recent Tweets