- E-mailmehdi.elahi@uib.no
- Phone+47 55 58 91 79
- Visitor AddressFosswinckels gate 6Lauritz Meltzers hus5007 Bergen
- Postal AddressPostboks 78025020 Bergen
Mehdi Elahi is an Associate Professor at University of Bergen (Norway). He received M.Sc. degree in Electrical Engineering (Sweden) in 2010, and Ph.D. degree in Computer Science (Italy) in 2014. Over the last 3 years, he has been serving as an Assistant Professor at Free University of Bozen - Bolzano (Italy), where has researched on various aspects of Recommender Systems. As a result of his research work, he served as a primary author or co-author of more than 60 peer-reviewed publications in AI, RS, and HCI related conferences and journals. He has been actively involved in co-authorship of a US-patent as well as co-authorship of several EU research proposals. He has been awarded a number of industry and academic research grants, e.g., by a world-class company (Amazon), and a well-known academic institute in Italy (Polytechnic University of Milan). He has provided various types of community services such as co-organization of the ACM RecSys challenge 2017 (organized by XING), and advisor of RecSys challenge 2018 (organized by Spotify).
- (2022). Social Data Analytics. CRC Press.
- (2023). Benchmarking equivariance for Deep Learning based optical flow estimators. Signal processing. Image communication.
- (2022). Parallel fractional stochastic gradient descent with adaptive learning for recommender systems. IEEE Transactions on Parallel and Distributed Systems.
- (2022). Developing and Evaluating a University Recommender System. Frontiers in Artificial Intelligence.
- (2022). Adaptive trust-aware collaborative filtering for cold start recommendation. Behaviormetrika.
- (2022). A Convolutional Attention Network for Unifying General and Sequential Recommenders. Information Processing & Management.
- (2021). Responsible media technology and AI: challenges and research directions. AI and Ethics.
- (2021). Investigating the impact of recommender systems on user-based and item-based popularity bias. Information Processing & Management.
- (2020). From Trustworthy Data to Trustworthy IoT: A Data Collection Methodology Based on Blockchain. ACM Transactions on Cyber-Physical Systems.
- (2020). Addressing the New Item problem in video recommender systems by incorporation of visual features with restricted Boltzmann machines. Expert systems.
- (2021). MORS 2021: Multi-Objective Recommender Systems 2021. Association for Computing Machinery (ACM).
- (2022). Movie recommendation based on stylistic visual features.
- (2021). Video Recommendations Based on Visual Features Extracted with Deep Learning.
- (2021). Novel Methods Using Human Emotion and Visual Features for Recommending Movies.
- (2022). Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches. 9 pages.
- (2022). Hybrid Recommendation of Movies based on Deep Content Features.
- (2021). Recommending Videos in Cold Start With Automatic Visual Tags.
- (2021). MORS 2021: 1st Workshop on Multi Objective Recommender Systems.
- (2021). Beyond Algorithmic Fairness in Recommender Systems.
- (2020). Visually-Aware Video Recommendation in the Cold Start. 5 pages.
- (2020). Towards Generating Personalized Country Recommendation. 6 pages.
- (2020). Simulating the Impact of Recommender Systems on the Evolution of Collective Users' Choices. 6 pages.
- (2022). Capacity-Based Trust System in Untrusted MEC Environments.
- (2021). Enhanced Movie Recommendation Incorporating Visual Features.
- (2021). Beyond Algorithmic Fairness in Recommender System.
- (2021). Towards Responsible Media Recommendation. AI and Ethics. 12 pages.
More information in national current research information system (CRIStin)