Marta Moscati
💻 📚 🎸
I am a physicist turned computer scientist, currently a PhD student at the Multimedia Mining and Search Group of the Johannes Kepler University Linz, Austria. I am also Applied Scientist (L5) at Albatross AI.
My (current) fields of research are multimodal learning and recommender systems. I have a PhD in theoretical particle physics.
I love understanding and discussing maths and science. I have a passion for music and books. I enjoy doing sports. I have a thing for languages.
selected publications
-
SwapRec: Warming Up Cold Items Through Training-Time Similar-Content SwapsIn Proceedings of DaQuaMRec 2026, the 2nd International Workshop on Data Quality-Aware Multimodal Recommendation, co-located with the 20th ACM Conference on Recommender Systems (RecSys 2026), September 28 - October 2, 2026, Minneapolis, Minnesota, USA., Sep 2026 -
Emotion-calibrated Music RecommendationIn Proceedings of MuRS 2026, the 4th Workshop Music Recommender Systems Workshop, co-located with the 20th ACM Conference on Recommender Systems (RecSys 2026), September 28 - October 2, 2026, Minneapolis, Minnesota, USA., Sep 2026 -
Calibrating Recommendations on Ordinal AttributesIn Proceedings of the 20th ACM Conference on Recommender Systems (RecSys 2026), Minneapolis, Minnesota, US, Sep 2026 -
SPRIG: Semantic-ID-enhanced Paths for Knowledge Graph-based Generative RecommendationIn Proceedings of the 35th ACM International Conference on Information & Knowledge Management (CIKM), Rome, Italy, Nov 2026 -
Networked Tastes: Homophily for Music RecommendationIn Workshops Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP), Gothenburg, Sweden, Jun 2026 -
Audio, Lyrics, Videoclips, Interactions? An Analysis of Uni- and Multi-Modal Music Retrieval Systems in Terms of Accuracy and Beyond-Accuracy AspectsIn Proc. of the Workshop on Music Recommender Systems (MuRS) co-located with the ACM Conference on Recommender Systems (RecSys), Prague, Czech Republic, Sep 2025 -
Integrating the ACT-R Framework with Collaborative Filtering for Explainable Sequential Music RecommendationIn Proc. of ACM RecSys, Singapore, Sep 2023 -
Music4All-Onion – A Large-Scale Multi-Faceted Content-Centric Music Recommendation DatasetIn Proc. of CIKM, Oct 2022 -
Face-Voice Association with Inductive Bias for Maximum Class SeparationIn Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026