Mirko Polato

selected publications

1. CSURJ14

   A Survey on Hypergraph Representation Learning

   Antelmi, Alessia, Cordasco, Gennaro,  Polato, Mirko, Scarano, Vittorio, Spagnuolo, Carmine, and Yang, Dingqi

   ACM Comput. Surv. 2023

   Abs Bib

   Hypergraphs have attracted increasing attention in recent years thanks to their flexibility in naturally modeling a broad range of systems where high-order relationships exist among their interacting parts. This survey reviews the newly born hypergraph representation learning problem, whose goal is to learn a function to project objects - most commonly nodes - of an input hyper-network into a latent space such that both the structural and relational properties of the network can be encoded and preserved. We provide a thorough overview of existing literature and offer a new taxonomy of hypergraph embedding methods by identifying three main families of techniques, i.e., spectral, proximity-preserving, and (deep) neural networks. For each family, we describe its characteristics and our insights in a single yet flexible framework and then discuss the peculiarities of individual methods, as well as their pros and cons. We then review the main tasks, datasets, and settings in which hypergraph embeddings are typically used. We finally identify and discuss open challenges that would inspire further research in this field.

   @article{Antelmi2023csur,
     author = {Antelmi, Alessia and Cordasco, Gennaro and Polato, Mirko and Scarano, Vittorio and Spagnuolo, Carmine and Yang, Dingqi},
     title = {A Survey on Hypergraph Representation Learning},
     year = {2023},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     issn = {0360-0300},
     url = {https://doi.org/10.1145/3605776},
     doi = {10.1145/3605776},
     note = {Just Accepted},
     journal = {ACM Comput. Surv.},
     keywords = {Hypergraph Attention, Hypergraph Neural Networks, Hypergraph Representation Learning, Hypergraph Convolution, Hypergraph Embedding},
   }

2. IJCNNC21

   Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent

   Polato, M., Esposito, R., and Aldinucci, M.

   In International Joint Conference on Neural Networks 2022

   Bib Code

   @inproceedings{Polato2022ijcnn,
     author = {Polato, M. and Esposito, R. and Aldinucci, M.},
     title = {Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent},
     booktitle = {International Joint Conference on Neural Networks},
     year = {2022},
     volume = {},
     doi = {10.1109/IJCNN55064.2022.9892284},
     url = {},
     document_type = {Conference Paper},
     source = {},
     note = {},
     code = {https://github.com/ml-unito/federation_boosting},
   }

3. NEUCOMJ12

   PRL: A game theoretic large margin method for interpretable feature learning

   Polato, M., Faggioli, G., and Aiolli, F.

   Neurocomputing 2022

   Bib HTML Code

   @article{Polato2022neucom,
     author = {Polato, M. and Faggioli, G. and Aiolli, F.},
     title = {PRL: A game theoretic large margin method for interpretable feature learning},
     journal = {Neurocomputing},
     year = {2022},
     volume = {479},
     pages = {106-120},
     doi = {10.1016/j.neucom.2022.01.016},
     url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123636162&doi=10.1016%2fj.neucom.2022.01.016&partnerID=40&md5=4bac852c5560981ca25a09c88fe2c1a9},
     document_type = {Article},
     source = {Scopus},
     code = {https://github.com/makgyver/PRL},
     html = {https://www.sciencedirect.com/science/article/pii/S0925231222000339},
   }

4. IJCNNC20

   Federated Variational Autoencoder for Collaborative Filtering

   Polato, M.

   In International Joint Conference on Neural Networks 2021

   Bib HTML Code

   @inproceedings{Polato2021ijcnn,
     author = {Polato, M.},
     title = {Federated Variational Autoencoder for Collaborative Filtering},
     booktitle = {International Joint Conference on Neural Networks},
     year = {2021},
     volume = {2021-July},
     doi = {10.1109/IJCNN52387.2021.9533358},
     url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116461340&doi=10.1109%2fIJCNN52387.2021.9533358&partnerID=40&md5=fd064184a372bcc1b09e3ee1d2fda604},
     document_type = {Conference Paper},
     source = {Scopus},
     code = {https://colab.research.google.com/drive/1sOx8QZYwRoEvOc6kBiQnVqZNVdbAEofM?usp=sharing},
     html = {https://ieeexplore.ieee.org/abstract/document/9533358},
   }

5. PATRECJ08

   Learning deep kernels in the space of monotone conjunctive polynomials

   Lauriola, I.,  Polato, M., and Aiolli, F.

   Pattern Recognition Letters 2020

   Bib HTML Code

   @article{Lauriola2020patrec,
     author = {Lauriola, I. and Polato, M. and Aiolli, F.},
     title = {Learning deep kernels in the space of monotone conjunctive polynomials},
     journal = {Pattern Recognition Letters},
     year = {2020},
     volume = {140},
     pages = {200-206},
     doi = {10.1016/j.patrec.2020.10.013},
     url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093985808&doi=10.1016%2fj.patrec.2020.10.013&partnerID=40&md5=ac677a2d73e0ce9db10672102d4553aa},
     document_type = {Article},
     source = {Scopus},
     html = {https://www.sciencedirect.com/science/article/pii/S0167865520304013},
     code = {https://github.com/IvanoLauriola/MKLpy},
   }

6. UMAPC17

   Recency Aware Collaborative Filtering for Next Basket Recommendation

   Faggioli, G.,  Polato, M., and Aiolli, F.

   In Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization 2020

   Bib HTML Code

   @inproceedings{Faggioli202080,
     author = {Faggioli, G. and Polato, M. and Aiolli, F.},
     title = {Recency Aware Collaborative Filtering for Next Basket Recommendation},
     booktitle = {Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization},
     year = {2020},
     pages = {80-87},
     doi = {10.1145/3340631.3394850},
     url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089352467&doi=10.1145%2f3340631.3394850&partnerID=40&md5=49092a855ef9f1928ac126d40bd46019},
     document_type = {Conference Paper},
     source = {Scopus},
     code = {https://github.com/MayloIFERR/RACF},
     html = {https://dl.acm.org/doi/abs/10.1145/3340631.3394850},
   }

7. ESORICSC16

   Big Enough to Care Not Enough to Scare! Crawling to Attack Recommender Systems

   Aiolli, F., Conti, M., Picek, S., and Polato, M.

   In 25th European Symposium on Research in Computer Security, ESORICS 2020 2020

   Bib HTML

   @inproceedings{Aiolli2020esorics,
     author = {Aiolli, F. and Conti, M. and Picek, S. and Polato, M.},
     title = {Big Enough to Care Not Enough to Scare! Crawling to Attack Recommender Systems},
     year = {2020},
     isbn = {978-3-030-59012-3},
     publisher = {Springer-Verlag},
     address = {Berlin, Heidelberg},
     url = {https://doi.org/10.1007/978-3-030-59013-0_9},
     doi = {10.1007/978-3-030-59013-0_9},
     booktitle = {25th European Symposium on Research in Computer Security, ESORICS 2020},
     pages = {165–184},
     numpages = {20},
     keywords = {Crawling, Recommender systems, Shilling attack, Security, Collaborative filtering},
     location = {Guildford, United Kingdom},
     html = {https://dl.acm.org/doi/abs/10.1007/978-3-030-59013-0_9},
   }

8. AAAIC15

   Interpretable preference learning: A game theoretic framework for large margin on-line feature and rule learning

   Polato, M., and Aiolli, F.

   In 33rd AAAI Conference on Artificial Intelligence 2019

   Bib HTML Code

   @inproceedings{Polato2019aaai,
     author = {Polato, M. and Aiolli, F.},
     title = {Interpretable preference learning: A game theoretic framework for large margin on-line feature and rule learning},
     booktitle = {33rd AAAI Conference on Artificial Intelligence},
     year = {2019},
     pages = {4723-4730},
     url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85090808191&partnerID=40&md5=dcf1bd412a92da6087a84ff0ca1f9347},
     document_type = {Conference Paper},
     source = {Scopus},
     code = {https://github.com/makgyver/PRL},
     html = {https://ojs.aaai.org/index.php/AAAI/article/view/4398/4276},
   }