2025
Conference article
Open Access
Cross-modal distillation by additive importance measure in HITL autonomous driving
Bano S., Cassarà P., Gennaro C., Gotta A.
With the advent of Advanced Driver Assistance Systems (ADAS) and intelligent transport system applications, recognizing driver emotions has become essential for a decision support system (DSS) with humans in the loop (HITL). Multimodal approaches using visual cues, speech, physiological signals, and driving patterns improve emotion recognition but are challenging in resource-constrained environments where only a subset of modalities is available. This work addresses these challenges by combining multi-modal benefits with single-modality inference for emotion recognition using unlabeled external road condition data. Unlike traditional methods that average teachers' contribution, the proposed cross-modal distillation (CMD) weights teachers thanks to the Shapley additive global explanation (SAGE) aid, which improves the student model's accuracy and provides an interpretation of it. Experimental evaluations of the PPBEmo dataset show that XA-CMD improves emotion recognition accuracy with other baselines and provides deeper insights into decision-making.Source: IEEE VTS ... VEHICULAR TECHNOLOGY CONFERENCE, pp. 1-5. Oslo, Norway, 17 - 20 june 2025
DOI: 10.1109/vtc2025-spring65109.2025.11174460
Metrics:
Bano S., Cassarà P., Gennaro C., Gotta A.
With the advent of Advanced Driver Assistance Systems (ADAS) and intelligent transport system applications, recognizing driver emotions has become essential for a decision support system (DSS) with humans in the loop (HITL). Multimodal approaches using visual cues, speech, physiological signals, and driving patterns improve emotion recognition but are challenging in resource-constrained environments where only a subset of modalities is available. This work addresses these challenges by combining multi-modal benefits with single-modality inference for emotion recognition using unlabeled external road condition data. Unlike traditional methods that average teachers' contribution, the proposed cross-modal distillation (CMD) weights teachers thanks to the Shapley additive global explanation (SAGE) aid, which improves the student model's accuracy and provides an interpretation of it. Experimental evaluations of the PPBEmo dataset show that XA-CMD improves emotion recognition accuracy with other baselines and provides deeper insights into decision-making.Source: IEEE VTS ... VEHICULAR TECHNOLOGY CONFERENCE, pp. 1-5. Oslo, Norway, 17 - 20 june 2025
DOI: 10.1109/vtc2025-spring65109.2025.11174460
Metrics:
See at:
CNR IRIS 
| ieeexplore.ieee.org | doi.org 
| CNR IRIS | CNR IRIS
2025
Conference article
Open Access
GATSY: graph attention network for music artist similarity
Di Francesco A. G., Giampietro G., Spinelli I., Comminiello D.
The artist similarity quest has become a crucial subject in social and scientific contexts, driven by the desire to enhance music discovery according to user preferences. Modern research solutions facilitate music discovery according to user tastes. However, defining similarity among artists remains challenging due to its inherently subjective nature, which can impact recommendation accuracy. This paper introduces GATSY, a novel recommendation system built upon graph attention networks and driven by a clusterized embedding of artists. The proposed framework leverages the graph topology of the input data to achieve outstanding performance results without relying heavily on hand-crafted features. This flexibility allows us to include fictitious artists within a music dataset, facilitating connections between previously unlinked artists and enabling diverse recommendations from various and heterogeneous sources. Experimental results prove the effectiveness of the proposed method with respect to state-of-the-art solutions while maintaining flexibility. The code to reproduce these experiments is available at https://github.com/difra100/GATSY-Music_Artist_Similarity.Source: PROCEEDINGS OF ... INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, pp. 1-8. Roma, Italy, 2025
DOI: 10.1109/ijcnn64981.2025.11228629
DOI: 10.48550/arxiv.2311.00635
Metrics:
Di Francesco A. G., Giampietro G., Spinelli I., Comminiello D.
The artist similarity quest has become a crucial subject in social and scientific contexts, driven by the desire to enhance music discovery according to user preferences. Modern research solutions facilitate music discovery according to user tastes. However, defining similarity among artists remains challenging due to its inherently subjective nature, which can impact recommendation accuracy. This paper introduces GATSY, a novel recommendation system built upon graph attention networks and driven by a clusterized embedding of artists. The proposed framework leverages the graph topology of the input data to achieve outstanding performance results without relying heavily on hand-crafted features. This flexibility allows us to include fictitious artists within a music dataset, facilitating connections between previously unlinked artists and enabling diverse recommendations from various and heterogeneous sources. Experimental results prove the effectiveness of the proposed method with respect to state-of-the-art solutions while maintaining flexibility. The code to reproduce these experiments is available at https://github.com/difra100/GATSY-Music_Artist_Similarity.Source: PROCEEDINGS OF ... INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, pp. 1-8. Roma, Italy, 2025
DOI: 10.1109/ijcnn64981.2025.11228629
DOI: 10.48550/arxiv.2311.00635
Metrics:
See at:
arXiv.org e-Print Archive | CNR IRIS | ieeexplore.ieee.org | doi.org | doi.org | Archivio della ricerca- Università di Roma La Sapienza | CNR IRIS | CNR IRIS
2025
Conference article
Open Access
Link prediction with physics-inspired graph neural networks
Di Francesco A. G., Caso F., Bucarelli M. S., Silvestri F.
The message-passing mechanism underlying Graph Neural Networks (GNNs) is not naturally suited for heterophilic datasets, where adjacent nodes often have different labels. Most solutions to this problem remain confined to the task of node classification. In this article, we focus on the valuable task of link prediction under heterophily, an interesting problem for recommendation systems, social network analysis, and other applications. GNNs like GRAFF have improved node classification under heterophily by incorporating physics biases in the architecture. Similarly, we propose GRAFF-LP, an extension of GRAFF for link prediction. We show that GRAFF-LP effectively discriminates existing from non-existing edges by learning implicitly to separate the edge gradients. Based on this information, we propose a new readout function inspired by physics. Remarkably, this new function not only enhances the performance of GRAFF-LP but also improves that of other baseline models, leading us to reconsider how every link prediction experiment has been conducted so far. Finally, we provide evidence that even simple GNNs did not experience greater difficulty in predicting heterophilic links compared to homophilic ones. This leads us to believe in the necessity for heterophily measures specifically tailored for link prediction, distinct from those used in node classification. The code and appendix are available at https://github.com/difra100/Link_Prediction_with_PIGNN_IJCNN.Source: PROCEEDINGS OF ... INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, pp. 1-8. Roma, Italy, 30 June-5 July 2025
DOI: 10.1109/ijcnn64981.2025.11227954
DOI: 10.48550/arxiv.2402.14802
Metrics:
Di Francesco A. G., Caso F., Bucarelli M. S., Silvestri F.
The message-passing mechanism underlying Graph Neural Networks (GNNs) is not naturally suited for heterophilic datasets, where adjacent nodes often have different labels. Most solutions to this problem remain confined to the task of node classification. In this article, we focus on the valuable task of link prediction under heterophily, an interesting problem for recommendation systems, social network analysis, and other applications. GNNs like GRAFF have improved node classification under heterophily by incorporating physics biases in the architecture. Similarly, we propose GRAFF-LP, an extension of GRAFF for link prediction. We show that GRAFF-LP effectively discriminates existing from non-existing edges by learning implicitly to separate the edge gradients. Based on this information, we propose a new readout function inspired by physics. Remarkably, this new function not only enhances the performance of GRAFF-LP but also improves that of other baseline models, leading us to reconsider how every link prediction experiment has been conducted so far. Finally, we provide evidence that even simple GNNs did not experience greater difficulty in predicting heterophilic links compared to homophilic ones. This leads us to believe in the necessity for heterophily measures specifically tailored for link prediction, distinct from those used in node classification. The code and appendix are available at https://github.com/difra100/Link_Prediction_with_PIGNN_IJCNN.Source: PROCEEDINGS OF ... INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, pp. 1-8. Roma, Italy, 30 June-5 July 2025
DOI: 10.1109/ijcnn64981.2025.11227954
DOI: 10.48550/arxiv.2402.14802
Metrics:
See at:
arXiv.org e-Print Archive | CNR IRIS | ieeexplore.ieee.org | doi.org | doi.org | Archivio della ricerca- Università di Roma La Sapienza | CNR IRIS | CNR IRIS