Antonio Ferrara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Antonio Ferrara has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Tommaso Di Noia
Politecnico di Bari, Italy
12 shared publications - Fedelucio Narducci
Politecnico di Bari, Bari, Italy
9 shared publications - Vito Walter Anelli
Politecnico di Bari, Italy
9 shared publications - Claudio Pomo
Politecnico di Bari, Bari, Italy
7 shared publications - Daniele Malitesta
LUISS Guido Carli University, Rome, Italy
7 shared publications - Alberto Carlo Maria Mancino
Politecnico di Bari, Bari, Italy
5 shared publications
Latest Publications
- Open Access
- 30 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 354
Tuning conventional recommender systems for beyond-accuracy objectives
- 30 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 354
Open AccessTuning conventional recommender systems for beyond-accuracy objectives
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4186-4198
Doc2Test: An Industrial Multi-agent Framework for Document-Driven End-to-End Selenium Test Generation
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4186-4198
Open AccessDoc2Test: An Industrial Multi-agent Framework for Document-Driven End-to-End Selenium Test Generation
- Open Access
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 54-59
Distribution-Robust Reranking for Conversational Music Recommendation: PoliBaJukebox at the ACM RecSys Challenge 2026
We describe the PoliBaJukebox submission to the ACM RecSys Challenge 2026 on conversational music recommendation over the TalkPlayData 2 corpus. Our system implements a modular two-stage pipeline: a first stage retrieves candidates from the full track catalog using ten heterogeneous sources, fuses them with weighted Reciprocal Rank Fusion (wRRF), and reranks with gradient-boosted models; a second stage writes the reply through a two-pass, fact-grounded LLM pipeline. Our central finding is methodological: on this task, offline development metrics can move against the blind leaderboard rather than track it, so components validated offline routinely failed or regressed on the blind split. We trace this to a large, measurable covariate shift between development and blind sessions (an adversarial classifier separates them at AUC 0.937 from input-side descriptors alone); a standard correction for it, reweighting training toward blind-like cases, lowers development nDCG@20 yet is what let the ranker transfer. Under this shift, the offline selection criterion itself must change, not just the model. Our compliant submission achieved a composite score of 0.576 (nDCG@20 0.445), placing PoliBaJukebox in the final top 5. All codes and weights are released for exact reproduction: https://github.com/lopsandrea/music-crs-team2.
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 54-59
Open AccessDistribution-Robust Reranking for Conversational Music Recommendation: PoliBaJukebox at the ACM RecSys Challenge 2026
We describe the PoliBaJukebox submission to the ACM RecSys Challenge 2026 on conversational music recommendation over the TalkPlayData 2 corpus. Our system implements a modular two-stage pipeline: a first stage retrieves candidates from the full track catalog using ten heterogeneous sources, fuses them with weighted Reciprocal Rank Fusion (wRRF), and reranks with gradient-boosted models; a second stage writes the reply through a two-pass, fact-grounded LLM pipeline. Our central finding is methodological: on this task, offline development metrics can move against the blind leaderboard rather than track it, so components validated offline routinely failed or regressed on the blind split. We trace this to a large, measurable covariate shift between development and blind sessions (an adversarial classifier separates them at AUC 0.937 from input-side descriptors alone); a standard correction for it, reweighting training toward blind-like cases, lowers development nDCG@20 yet is what let the ranker transfer. Under this shift, the offline selection criterion itself must change, not just the model. Our compliant submission achieved a composite score of 0.576 (nDCG@20 0.445), placing PoliBaJukebox in the final top 5. All codes and weights are released for exact reproduction: https://github.com/lopsandrea/music-crs-team2.
- Open Access
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 39-44
Beyond Single-Signal Retrieval: A Graph-Aware Agentic Framework for Conversational Music Recommendation
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 39-44
Open AccessBeyond Single-Signal Retrieval: A Graph-Aware Agentic Framework for Conversational Music Recommendation
- 3 August 2026
- Published by Elsevier in International Journal of Human-Computer Studies
- Vol. 217
Re-centering the user in recommender system research: Preface to the special issue
- 3 August 2026
- Published by Elsevier in International Journal of Human-Computer Studies
- Vol. 217
Re-centering the user in recommender system research: Preface to the special issue
- Open Access
- 18 July 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
AMIUgraph: analysis and modeling of interactions for utility-driven benchmarking of graph-based models in healthcare
Graph-based machine learning approaches, including Knowledge Graph Embedding (KGE) methods and Graph Neural Networks (GNNs), have emerged as powerful tools
- 18 July 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
Open AccessAMIUgraph: analysis and modeling of interactions for utility-driven benchmarking of graph-based models in healthcare
Graph-based machine learning approaches, including Knowledge Graph Embedding (KGE) methods and Graph Neural Networks (GNNs), have emerged as powerful tools
- Open Access
WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting required for distributed industrial engines. To bridge this gap, we present WarpRec, a high-performance framework that eliminates this trade-off through a novel, backend-agnostic architecture. It includes 50+ state-of-the-art algorithms, 40 metrics, and 19 filtering and splitting strategies that seamlessly transition from local execution to distributed training and optimization. The framework enforces ecological responsibility by integrating CodeCarbon for real-time energy tracking, showing that scalability need not come at the cost of scientific integrity or sustainability. Furthermore, WarpRec anticipates the shift toward Agentic AI, leading Recommender Systems to evolve from static ranking engines into interactive tools within the Generative AI ecosystem. In summary, WarpRec not only bridges the gap between academia and industry but also can serve as the architectural backbone for the next generation of sustainable, agent-ready Recommender Systems. Code is available at https://github.com/sisinflab/warprec/
Open AccessWarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
Innovation in Recommender Systems is currently impeded by a fractured ecosystem, where researchers must choose between the ease of in-memory experimentation and the costly, complex rewriting required for distributed industrial engines. To bridge this gap, we present WarpRec, a high-performance framework that eliminates this trade-off through a novel, backend-agnostic architecture. It includes 50+ state-of-the-art algorithms, 40 metrics, and 19 filtering and splitting strategies that seamlessly transition from local execution to distributed training and optimization. The framework enforces ecological responsibility by integrating CodeCarbon for real-time energy tracking, showing that scalability need not come at the cost of scientific integrity or sustainability. Furthermore, WarpRec anticipates the shift toward Agentic AI, leading Recommender Systems to evolve from static ranking engines into interactive tools within the Generative AI ecosystem. In summary, WarpRec not only bridges the gap between academia and industry but also can serve as the architectural backbone for the next generation of sustainable, agent-ready Recommender Systems. Code is available at https://github.com/sisinflab/warprec/
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 122220-122241
Derivative-Free Emergent Optimization via Local Rules and Cellular Automata
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 122220-122241
Open AccessDerivative-Free Emergent Optimization via Local Rules and Cellular Automata
- 12 October 2025
- Published by Springer Nature
- p. 423-426
Enhancing Reproducibility and Replicability in Information Retrieval: A Path Towards Scientific Integrity and Effective Research
- 12 October 2025
- Published by Springer Nature
- p. 423-426
Enhancing Reproducibility and Replicability in Information Retrieval: A Path Towards Scientific Integrity and Effective Research
- Open Access
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 41-45
One Paradigm for All: Relational Deep Learning for Representation of Universal Behavioral Profiles
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 41-45
Open AccessOne Paradigm for All: Relational Deep Learning for Representation of Universal Behavioral Profiles