Mojtaba Nayyeri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mojtaba Nayyeri has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Jens Lehmann
Faculty of Computer Science, TUD Dresden University of Technology, Dresden, Germany
12 shared publications - Steffen Staab
University of Stuttgart
8 shared publications Hamed Shariat Yazdi
Department of Computer Science, Smart Data Analytics Group, University of Bonn, Bonn, Germany
6 shared publications- Sahar Vahdati
TU Dresden
6 shared publications Chengjin Xu
SDA Research University of Bonn Bonn Germany
5 shared publicationsSahar Vahdati
InfAI Lab
4 shared publications
Latest Publications
- 23 October 2026
- Published by Springer Nature
- p. 25-57
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
- 23 October 2026
- Published by Springer Nature
- p. 25-57
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
- Open Access
- 21 October 2025
- Published by IOS Press
- p. 3202-3209
Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Similarly, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate across the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods use snapshot graphs to represent temporal evolution. In this paper, we introduce a full-history graph that instantiates one node for every entity at every timestep and separates two edge sets: (i) intra-timestep edges that capture relations within a single frame, and (ii) inter-timestep edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-timestep edges, a multi-head temporal-attention module attends over an entity’s inter-timestep history, and a fusion module combines the two messages after every layer. When evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6 % (vs. 74.1 %) and raising Elliptic++ illicit-class F1 to 88.1 % (vs. 60.4 %). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.
- 21 October 2025
- Published by IOS Press
- p. 3202-3209
Open AccessFull-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Similarly, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate across the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods use snapshot graphs to represent temporal evolution. In this paper, we introduce a full-history graph that instantiates one node for every entity at every timestep and separates two edge sets: (i) intra-timestep edges that capture relations within a single frame, and (ii) inter-timestep edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-timestep edges, a multi-head temporal-attention module attends over an entity’s inter-timestep history, and a fusion module combines the two messages after every layer. When evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6 % (vs. 74.1 %) and raising Elliptic++ illicit-class F1 to 88.1 % (vs. 60.4 %). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.
- Open Access
Retrieval-Augmented Generation of Ontologies from Relational Databases
Transforming relational databases into knowledge graphs with enriched ontologies enhances semantic interoperability and unlocks advanced graph-based learning and reasoning over data. However, previous approaches either demand significant manual effort to derive an ontology from a database schema or produce only a basic ontology. We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies, an LLM-driven approach that turns relational schemas into rich OWL ontologies with minimal human effort. RIGOR combines three sources via RAG, the database schema and its documentation, a repository of domain ontologies, and a growing core ontology, to prompt a generative LLM for producing successive, provenance-tagged delta ontology fragments. Each fragment is refined by a judge-LLM before being merged into the core ontology, and the process iterates table-by-table following foreign key constraints until coverage is complete. Applied to real-world databases, our approach outputs ontologies that score highly on standard quality dimensions such as accuracy, completeness, conciseness, adaptability, clarity, and consistency, while substantially reducing manual effort.
Open AccessRetrieval-Augmented Generation of Ontologies from Relational Databases
Transforming relational databases into knowledge graphs with enriched ontologies enhances semantic interoperability and unlocks advanced graph-based learning and reasoning over data. However, previous approaches either demand significant manual effort to derive an ontology from a database schema or produce only a basic ontology. We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies, an LLM-driven approach that turns relational schemas into rich OWL ontologies with minimal human effort. RIGOR combines three sources via RAG, the database schema and its documentation, a repository of domain ontologies, and a growing core ontology, to prompt a generative LLM for producing successive, provenance-tagged delta ontology fragments. Each fragment is refined by a judge-LLM before being merged into the core ontology, and the process iterates table-by-table following foreign key constraints until coverage is complete. Applied to real-world databases, our approach outputs ontologies that score highly on standard quality dimensions such as accuracy, completeness, conciseness, adaptability, clarity, and consistency, while substantially reducing manual effort.
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 4279-4286
Generating SROI− Ontologies via Knowledge Graph Query Embedding Learning
Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.
- 16 October 2024
- Published by IOS Press
- p. 4279-4286
Open AccessGenerating SROI− Ontologies via Knowledge Graph Query Embedding Learning
Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.
- Open Access
Approximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddings
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a statistical extension of the lightweight Description Logic EL. We provide proofs for runtime and soundness guarantees, and empirically evaluate the runtime and approximation quality of our approach.
Open AccessApproximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddings
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a statistical extension of the lightweight Description Logic EL. We provide proofs for runtime and soundness guarantees, and empirically evaluate the runtime and approximation quality of our approach.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 8913-8920
HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
Temporal knowledge graphs represent temporal facts (s,p,o,?) relating a subject s and an object o via a relation label p at time ?, where ? could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 8913-8920
Open AccessHGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
Temporal knowledge graphs represent temporal facts (s,p,o,?) relating a subject s and an object o via a relation label p at time ?, where ? could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.
- Open Access
- 22 January 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (1) , 49
Correntropy-Based Constructive One Hidden Layer Neural Network
One of the main disadvantages of the traditional mean square error (MSE)-based constructive networks is their poor performance in the presence of non-Gaussian noises. In this paper, we propose a new incremental constructive network based on the correntropy objective function (correntropy-based constructive neural network (C2N2)), which is robust to non-Gaussian noises. In the proposed learning method, input and output side optimizations are separated. It is proved theoretically that the new hidden node, which is obtained from the input side optimization problem, is not orthogonal to the residual error function. Regarding this fact, it is proved that the correntropy of the residual error converges to its optimum value. During the training process, the weighted linear least square problem is iteratively applied to update the parameters of the newly added node. Experiments on both synthetic and benchmark datasets demonstrate the robustness of the proposed method in comparison with the MSE-based constructive network, the radial basis function (RBF) network. Moreover, the proposed method outperforms other robust learning methods including the cascade correntropy network (CCOEN), Multi-Layer Perceptron based on the Minimum Error Entropy objective function (MLPMEE), Multi-Layer Perceptron based on the correntropy objective function (MLPMCC) and the Robust Least Square Support Vector Machine (RLS-SVM).
- 22 January 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (1) , 49
Open AccessCorrentropy-Based Constructive One Hidden Layer Neural Network
One of the main disadvantages of the traditional mean square error (MSE)-based constructive networks is their poor performance in the presence of non-Gaussian noises. In this paper, we propose a new incremental constructive network based on the correntropy objective function (correntropy-based constructive neural network (C2N2)), which is robust to non-Gaussian noises. In the proposed learning method, input and output side optimizations are separated. It is proved theoretically that the new hidden node, which is obtained from the input side optimization problem, is not orthogonal to the residual error function. Regarding this fact, it is proved that the correntropy of the residual error converges to its optimum value. During the training process, the weighted linear least square problem is iteratively applied to update the parameters of the newly added node. Experiments on both synthetic and benchmark datasets demonstrate the robustness of the proposed method in comparison with the MSE-based constructive network, the radial basis function (RBF) network. Moreover, the proposed method outperforms other robust learning methods including the cascade correntropy network (CCOEN), Multi-Layer Perceptron based on the Minimum Error Entropy objective function (MLPMEE), Multi-Layer Perceptron based on the correntropy objective function (MLPMCC) and the Robust Least Square Support Vector Machine (RLS-SVM).
- Open Access
HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
Temporal knowledge graphs represent temporal facts $(s,p,o,τ)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $τ$, where $τ$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.Open AccessHGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
Temporal knowledge graphs represent temporal facts $(s,p,o,τ)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $τ$, where $τ$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models. - Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5228-5231
Reasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings
Knowledge Graphs (KGs) are a collection of facts describing entities connected by relationships. KG embeddings map entities and relations into a vector space while preserving their relational semantics. This enables effective inference of missing knowledge from the embedding space. Most KG embedding approaches focused on triple-shaped KGs. A great amount of real-world knowledge, however, cannot simply be represented by triples. In this tutorial, we give a systematic introduction to KG embeddings that go beyond the triple representation. In particular, the tutorial will focus on temporal facts where the triples are enriched with temporal information, hyper-relational facts where the triples are enriched with qualifiers, n-ary facts describing relationships between multiple entities, and also facts that are augmented with literal and text descriptions. During the tutorial, we will introduce both fundamental knowledge and advanced topics for understanding recent embedding approaches for beyond-triple representations.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5228-5231
Open AccessReasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings
Knowledge Graphs (KGs) are a collection of facts describing entities connected by relationships. KG embeddings map entities and relations into a vector space while preserving their relational semantics. This enables effective inference of missing knowledge from the embedding space. Most KG embedding approaches focused on triple-shaped KGs. A great amount of real-world knowledge, however, cannot simply be represented by triples. In this tutorial, we give a systematic introduction to KG embeddings that go beyond the triple representation. In particular, the tutorial will focus on temporal facts where the triples are enriched with temporal information, hyper-relational facts where the triples are enriched with qualifiers, n-ary facts describing relationships between multiple entities, and also facts that are augmented with literal and text descriptions. During the tutorial, we will introduce both fundamental knowledge and advanced topics for understanding recent embedding approaches for beyond-triple representations.
- 8 July 2023
- Published by Springer Nature
- p. 255-274
Randomized Constructive Neural Network Based on Regularized Minimum Error Entropy
- 8 July 2023
- Published by Springer Nature
- p. 255-274
Randomized Constructive Neural Network Based on Regularized Minimum Error Entropy