Publications
Selected research papers and preprints
2025
Gotta Embed Them All! - Knowledge-aware Recommendations Fusing Heterogeneous Multi-Modal Item Embeddings
Journal of Intelligent Information Systems, pp. 1–27. Springer.
Comparing Data Reduction Strategies for Energy-Efficient Green Recommender Systems
Journal of Intelligent Information Systems, pp. 1–27. Springer.
See the Movie, Hear the Song, Read the Book: Extending MovieLens-1M, Last.fm-2K, and DBbook with Multimodal Data
Proceedings of the 19th ACM Conference on Recommender Systems, pp. 847–856.
Training Green and Sustainable Recommendation Models: Introducing Carbon Footprint Data into Early Stopping Criteria
Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, pp. 341–346.
GAL-KARS: Exploiting LLMs for Graph Augmentation in Knowledge-Aware Recommender Systems
Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, pp. 73–82.
Human-Centered and Sustainable Recommender Systems (Tutorial)
Adjunt Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, pp. 10-12.
E-Mealio: An LLM-Powered Conversational Agent for Sustainable and Healthy Food Recommendation
Second International Workshop on Recommender Systems for Sustainability and Social Good. In press.
Estimating Product Carbon Footprint via Large Language Models for Sustainable Recommender Systems
Second International Workshop on Recommender Systems for Sustainability and Social Good. In press.
2024
Recommender Systems Based on Neuro-Symbolic Knowledge Graph Embeddings Encoding First-Order Logic Rules
User Modeling and User-Adapted Interaction 34(5), pp. 2039–2083. Springer.
Towards Green Recommender Systems: Investigating the Impact of Data Reduction on Carbon Footprint and Model Performances
Proceedings of the 18th ACM Conference on Recommender Systems.
Evaluating Content-based Pre-Training Strategies for a Knowledge-aware Recommender System based on Graph Neural Networks
Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, pp. 165–171.
Improving Transformer-based Sequential Conversational Recommendations through Knowledge Graph Embeddings
Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, pp. 172–182.
Recsys CarbonAtor: Predicting Carbon Footprint of Recommendation System Models
International Workshop on Recommender Systems for Sustainability and Social Good, Springer, pp. 98–110.
2023
Harnessing Distributional Semantics to Build Context-aware Justifications for Recommender Systems
User Modeling and User-Adapted Interaction. Springer.
Knowledge-Aware Recommender Systems based on Multi-Modal Information Sources
Proceedings of the 17th ACM Conference on Recommender Systems, pp. 1312–1317.
Towards Sustainability-aware Recommender Systems: Analyzing the Trade-off Between Algorithms Performance and Carbon Footprint
Proceedings of the 17th ACM Conference on Recommender Systems, pp. 856–862.
Combining Heterogeneous Embeddings for Knowledge-Aware Recommendation Models
Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, pp. 269–273.
Combining Graph Neural Networks and Sentence Encoders for Knowledge-aware Recommendations
Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, pp. 1–12.
2022
Knowledge-aware Recommendations Based on Neuro-Symbolic Graph Embeddings and First-Order Logical Rules
Proceedings of the 16th ACM Conference on Recommender Systems, pp. 616–621.
Exploiting Neuro-Symbolic Graph Embeddings based on First-Order Logical Rules for Knowledge-aware Recommendations.
DP@AI*IA, pp. 1–11.