Skip to main content

Showing 1–17 of 17 results for author: Vahdati, S

Searching in archive cs. Search in all archives.
.
  1. Retention Is All You Need

    Authors: Karishma Mohiuddin, Mirza Ariful Alam, Mirza Mohtashim Alam, Pascal Welke, Michael Martin, Jens Lehmann, Sahar Vahdati

    Abstract: Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support Sys… ▽ More

    Submitted 26 August, 2023; v1 submitted 6 April, 2023; originally announced April 2023.

    Comments: Accepted at CIKM 2023 Applied Research Track

  2. arXiv:2210.12113  [pdf

    eess.IV cs.CV cs.LG

    Multitask Brain Tumor Inpainting with Diffusion Models: A Methodological Report

    Authors: Pouria Rouzrokh, Bardia Khosravi, Shahriar Faghani, Mana Moassefi, Sanaz Vahdati, Bradley J. Erickson

    Abstract: Despite the ever-increasing interest in applying deep learning (DL) models to medical imaging, the typical scarcity and imbalance of medical datasets can severely impact the performance of DL models. The generation of synthetic data that might be freely shared without compromising patient privacy is a well-known technique for addressing these difficulties. Inpainting algorithms are a subset of DL… ▽ More

    Submitted 30 March, 2023; v1 submitted 21 October, 2022; originally announced October 2022.

    Comments: 17 pages, 7 figures

  3. arXiv:2209.02390  [pdf

    cs.AI

    ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion

    Authors: Mojtaba Moattari, Sahar Vahdati, Farhana Zulkernine

    Abstract: Knowledge Graph Embedding (KGE) methods have gained enormous attention from a wide range of AI communities including Natural Language Processing (NLP) for text generation, classification and context induction. Embedding a huge number of inter-relationships in terms of a small number of dimensions, require proper modeling in both cognitive and computational aspects. Recently, numerous objective fun… ▽ More

    Submitted 15 September, 2022; v1 submitted 15 August, 2022; originally announced September 2022.

  4. arXiv:2203.04703  [pdf, other

    cs.AI cs.LG

    LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings

    Authors: Md Rashad Al Hasan Rony, Mirza Mohtashim Alam, Semab Ali, Jens Lehmann, Sahar Vahdati

    Abstract: Knowledge Graph Embedding models have become an important area of machine learning.Those models provide a latent representation of entities and relations in a knowledge graph which can then be used in downstream machine learning tasks such as link prediction. The learning process of such models can be performed by contrasting positive and negative triples. While all triples of a KG are considered… ▽ More

    Submitted 15 October, 2022; v1 submitted 9 March, 2022; originally announced March 2022.

  5. arXiv:2107.03297  [pdf, other

    cs.AI cs.CL cs.DL cs.LG

    Trans4E: Link Prediction on Scholarly Knowledge Graphs

    Authors: Mojtaba Nayyeri, Gokce Muge Cil, Sahar Vahdati, Francesco Osborne, Mahfuzur Rahman, Simone Angioni, Angelo Salatino, Diego Reforgiato Recupero, Nadezhda Vassilyeva, Enrico Motta, Jens Lehmann

    Abstract: The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In th… ▽ More

    Submitted 3 July, 2021; originally announced July 2021.

  6. arXiv:2104.05003  [pdf, other

    cs.AI

    Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings

    Authors: Chengjin Xu, Mojtaba Nayyeri, Sahar Vahdati, Jens Lehmann

    Abstract: Among the top approaches of recent years, link prediction using knowledge graph embedding (KGE) models has gained significant attention for knowledge graph completion. Various embedding models have been proposed so far, among which, some recent KGE models obtain state-of-the-art performance on link prediction tasks by using embeddings with a high dimension (e.g. 1000) which accelerate the costs of… ▽ More

    Submitted 30 May, 2021; v1 submitted 11 April, 2021; originally announced April 2021.

    Comments: Accepted by the 2021 International Joint Conference on Neural Networks (IJCNN 2021)

  7. arXiv:2010.06684  [pdf, other

    cs.LG cs.AI

    Motif Learning in Knowledge Graphs Using Trajectories Of Differential Equations

    Authors: Mojtaba Nayyeri, Chengjin Xu, Jens Lehmann, Sahar Vahdati

    Abstract: Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space (usually a vector space). Ultimately, the plausibility of the predicted links is measured by using a scoring function over the learned embeddings (vectors). Therefore, the capability in preserving graph characteristics inclu… ▽ More

    Submitted 18 October, 2020; v1 submitted 13 October, 2020; originally announced October 2020.

  8. arXiv:2006.04986  [pdf, other

    cs.AI cs.LG

    5* Knowledge Graph Embeddings with Projective Transformations

    Authors: Mojtaba Nayyeri, Sahar Vahdati, Can Aykul, Jens Lehmann

    Abstract: Performing link prediction using knowledge graph embedding models has become a popular approach for knowledge graph completion. Such models employ a transformation function that maps nodes via edges into a vector space in order to measure the likelihood of the links. While mapping the individual nodes, the structure of subgraphs is also transformed. Most of the embedding models designed in Euclide… ▽ More

    Submitted 14 March, 2021; v1 submitted 8 June, 2020; originally announced June 2020.

    Comments: Accepted in AAAI 2021

  9. arXiv:1907.05336  [pdf, other

    cs.CL cs.AI cs.LG stat.ML

    Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function

    Authors: Mojtaba Nayyeri, Xiaotian Zhou, Sahar Vahdati, Hamed Shariat Yazdi, Jens Lehmann

    Abstract: Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency. Therefore, most of the earlier works have modified the score function of the TransE approach in order to improve the performance of link prediction tasks. Neve… ▽ More

    Submitted 9 July, 2019; originally announced July 2019.

  10. arXiv:1904.12211  [pdf, other

    cs.AI cs.IR cs.LG

    Soft Marginal TransE for Scholarly Knowledge Graph Completion

    Authors: Mojtaba Nayyeri, Sahar Vahdati, Jens Lehmann, Hamed Shariat Yazdi

    Abstract: Knowledge graphs (KGs), i.e. representation of information as a semantic graph, provide a significant test bed for many tasks including question answering, recommendation, and link prediction. Various amount of scholarly metadata have been made vailable as knowledge graphs from the diversity of data providers and agents. However, these high-quantities of data remain far from quality criteria in te… ▽ More

    Submitted 27 April, 2019; originally announced April 2019.

  11. arXiv:1807.06816  [pdf, other

    cs.DL physics.soc-ph

    Unveiling Scholarly Communities over Knowledge Graphs

    Authors: Sahar Vahdati, Guillermo Palma, Rahul Jyoti Nath, Christoph Lange, Sören Auer, Maria-Esther Vidal

    Abstract: Knowledge graphs represent the meaning of properties of real-world entities and relationships among them in a natural way. Exploiting semantics encoded in knowledge graphs enables the implementation of knowledge-driven tasks such as semantic retrieval, query processing, and question answering, as well as solutions to knowledge discovery tasks including pattern discovery and link prediction. In thi… ▽ More

    Submitted 18 July, 2018; originally announced July 2018.

    Comments: 12 pages. Paper accepted in the 22nd International Conference on Theory and Practice of Digital Libraries, 2018

  12. arXiv:1711.04548  [pdf, other

    cs.DL

    Towards a Cloud-Based Service for Maintaining and Analyzing Data About Scientific Events

    Authors: Andreas Behrend, Sahar Vahdati, Christoph Lange, Christiane Engels

    Abstract: We propose the new cloud-based service OpenResearch for managing and analyzing data about scientific events such as conferences and workshops in a persistent and reliable way. This includes data about scientific articles, participants, acceptance rates, submission numbers, impact values as well as organizational details such as program committees, chairs, fees and sponsors. OpenResearch is a centr… ▽ More

    Submitted 28 November, 2017; v1 submitted 13 November, 2017; originally announced November 2017.

    Comments: A completed version of this paper had been accepted in SAVE-SD workshop 2017 at WWW conference

  13. arXiv:1611.01820  [pdf, other

    cs.DL

    A Semi-Automatic Approach for Detecting Dataset References in Social Science Texts

    Authors: Behnam Ghavimi, Philipp Mayr, Christoph Lange, Sahar Vahdati, Sören AUER

    Abstract: Today, full-texts of scientific articles are often stored in different locations than the used datasets. Dataset registries aim at a closer integration by making datasets citable but authors typically refer to datasets using inconsistent abbreviations and heterogeneous metadata (e.g. title, publication year). It is thus hard to reproduce research results, to access datasets for further analysis, a… ▽ More

    Submitted 6 November, 2016; originally announced November 2016.

    Comments: Pre-print IS&U journal. arXiv admin note: substantial text overlap with arXiv:1603.01774

  14. arXiv:1603.01774  [pdf, other

    cs.DL cs.IR

    Identifying and Improving Dataset References in Social Sciences Full Texts

    Authors: Behnam Ghavimi, Philipp Mayr, Sahar Vahdati, Christoph Lange

    Abstract: Scientific full text papers are usually stored in separate places than their underlying research datasets. Authors typically make references to datasets by mentioning them for example by using their titles and the year of publication. However, in most cases explicit links that would provide readers with direct access to referenced datasets are missing. Manually detecting references to datasets in… ▽ More

    Submitted 29 March, 2016; v1 submitted 5 March, 2016; originally announced March 2016.

  15. arXiv:1508.06206  [pdf, other

    cs.DL

    Semantic Publishing Challenge - Assessing the Quality of Scientific Output by Information Extraction and Interlinking

    Authors: Angelo Di Iorio, Christoph Lange, Anastasia Dimou, Sahar Vahdati

    Abstract: The Semantic Publishing Challenge series aims at investigating novel approaches for improving scholarly publishing using Linked Data technology. In 2014 we had bootstrapped this effort with a focus on extracting information from non-semantic publications - computer science workshop proceedings volumes and their papers - to assess their quality. The objective of this second edition was to improve i… ▽ More

    Submitted 25 August, 2015; originally announced August 2015.

    Comments: To appear in: E. Cabrio and M. Stankovic and M. Dragoni and A. Gangemi and R. Navigli and V. Presutti and D. Garigliotti and A. L. Gentile and A. Nuzzolese and A. Di Iorio and A. Dimou and C. Lange and S. Vahdati and A. Freitas and C. Unger and D. Reforgiato Recupero (eds.). Semantic Web Evaluation Challenges 2015. Communications in Computer and Information Science, Springer, 2015. arXiv admin note: text overlap with arXiv:1408.3863

    ACM Class: H.3.7; I.7.4; H.3.3

  16. arXiv:1506.04006  [pdf, other

    cs.DB cs.DL cs.PF

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

    Authors: Sahar Vahdati, Farah Karim, Jyun-Yao Huang, Christoph Lange

    Abstract: OpenAIRE, the Open Access Infrastructure for Research in Europe, comprises a database of all EC FP7 and H2020 funded research projects, including metadata of their results (publications and datasets). These data are stored in an HBase NoSQL database, post-processed, and exposed as HTML for human consumption, and as XML through a web service interface. As an intermediate format to facilitate statis… ▽ More

    Submitted 6 July, 2015; v1 submitted 12 June, 2015; originally announced June 2015.

    Comments: Accepted in 0th Metadata and Semantics Research Conference

  17. OpenCourseWare Observatory -- Does the Quality of OpenCourseWare Live up to its Promise?

    Authors: Sahar Vahdati, Christoph Lange, Sören Auer

    Abstract: A vast amount of OpenCourseWare (OCW) is meanwhile being published online to make educational content accessible to larger audiences. The awareness of such courses among users and the popularity of systems providing such courses are increasing. However, from a subjective experience, OCW is frequently cursory, outdated or non-reusable. In order to obtain a better understanding of the quality of OCW… ▽ More

    Submitted 14 April, 2015; v1 submitted 21 October, 2014; originally announced October 2014.

    Comments: A later version of this paper was presented in the proceedings of the Fifth International Conference on Learning Analytics And Knowledge(2015), pages 73-82. http://dl.acm.org/citation.cfm?id=2723605 On Zenodo: https://zenodo.org/deposit/21264/

    ACM Class: K.3