Mojtaba Nayyeri

Mojtaba Nayyeri


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2020
Verified
Book Chapter
Closed access
PDF file
CXChenjin Xu
Chenjin Xu
MNMojtaba Nayyeri
Mojtaba Nayyeri
FAFouad Alkhoury
Fouad Alkhoury
HYHamed Yazdi
Hamed Yazdi
JLJens Lehmann
Jens Lehmann

20 October 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MNMojtaba Nayyeri
Mojtaba Nayyeri
CXChengjin Xu
Chengjin Xu
MAMirza Mohtashim Alam
Mirza Mohtashim Alam
JLJens Lehmann
Jens Lehmann
HYHamed Shariat Yazdi
Hamed Shariat Yazdi
Knowledge graph embedding models have gained significant attention in AI research. The aim of knowledge graph embedding is to embed the graphs into a vector space in which the structure of the graph is preserved. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. However, so far, most existing models do not allow the inclusion of rules. We address the challenge of including rules and present a new neural based embedding model (LogicENN). We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph. To the best of our knowledge, this has not been proved so far for the neural based family of embedding models. Moreover, we derive formulae for the inclusion of various rules, including (anti-)symmetric, inverse, irreflexive and transitive, implication, composition, equivalence and negation. Our formulation allows to avoid grounding for implication and equivalence relations. Our experiments show that LogicENN outperforms the existing models in link prediction.

30 April 2023
Verified
Conference Paper
Open access
CGCosimo Gregucci
Cosimo Gregucci
MNMojtaba Nayyeri
Mojtaba Nayyeri
DHDaniel Hernández
Daniel Hernández
SSSteffen Staab
Steffen Staab
Predicting missing links between entities in a knowledge graph is a fundamental task to deal with the incompleteness of data on the Web. Knowledge graph embeddings map nodes into a vector space to predict new links, scoring them according to geometric criteria. Relations in the graph may follow patterns that can be learned, e.g., some relations might be symmetric and others might be hierarchical. However, the learning capability of different embedding models varies for each pattern and, so far, no single model can learn all patterns equally well. In this paper, we combine the query representations from several models in a unified one to incorporate patterns that are independently captured by each model. Our combination uses attention to select the most suitable model to answer each query. The models are also mapped onto a non-Euclidean manifold, the Poincaré ball, to capture structural patterns, such as hierarchies, besides relational patterns, such as symmetry. We prove that our combination provides a higher expressiveness and inference power than each model on its own. As a result, the combined model can learn relational and structural patterns. We conduct extensive experimental analysis with various link prediction benchmarks showing that the combined model outperforms individual models, including state-of-the-art approaches.

1 January 2023
Verified
Conference Paper
Open access
PDF file
BXBo Xiong
Bo Xiong
MNMojtaba Nayyeri
Mojtaba Nayyeri
SPShirui Pan
Shirui Pan
SSSteffen Staab
Steffen Staab
Bo Xiong, Mojtaba Nayyeri, Shirui Pan, Steffen Staab. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
JPJiaxin Pan
Jiaxin Pan
MNMojtaba Nayyeri
Mojtaba Nayyeri
YLYinan Li
Yinan Li
SSSteffen Staab
Steffen Staab
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.

31 May 2022
Verified
Book Chapter
Closed access
PDF file
MNMojtaba Nayyeri
Mojtaba Nayyeri
SVSahar Vahdati
Sahar Vahdati
TKTansen Khan
Tansen Khan
MAMirza Mohtashim Alam
Mirza Mohtashim Alam
LWLisa Wenige
Lisa Wenige
JLJens Lehmann
Jens Lehmann