Publications

2024

1. ArXiv

   ResiDual Transformer Alignment with Spectral Decomposition

   Valentino Maiorca*, Lorenzo Basile*, Luca Bortolussi, Emanuele Rodolà, and Francesco Locatello

   arXiv preprint, 2024

   arXiv Bib

   @article{maiorca2024residual,
     title = {ResiDual Transformer Alignment with Spectral Decomposition},
     author = {Maiorca*, Valentino and Basile*, Lorenzo and Bortolussi, Luca and Rodol{\`a}, Emanuele and Locatello, Francesco},
     journal = {arXiv preprint},
     year = {2024},
     url = {https://arxiv.org/abs/2411.00246},
   }

2. COSYNE

   Multi-subject neural decoding via relative representations

   Valentino Maiorca, Simone Azeglio, Marco Fumero, Clémentine Dominé, Emanuele Rodolà, and Francesco Locatello

   In Cosyne Abstracts, 2024
3. NeurIPS

   Latent Functional Maps

   Marco Fumero, Marco Pegoraro, Valentino Maiorca, Francesco Locatello, and Emanuele Rodolà

   2024

   arXiv Bib

   @misc{fumero2024latentfunctionalmaps,
     title = {Latent Functional Maps},
     author = {Fumero, Marco and Pegoraro, Marco and Maiorca, Valentino and Locatello, Francesco and Rodolà, Emanuele},
     year = {2024},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2406.14183},
     booktitle = {Thirty-eight Conference on Neural Information Processing Systems},
   }

4. ArXiv

   Latent Space Translation via Inverse Relative Projection

   Valentino Maiorca, Luca Moschella, Marco Fumero, Francesco Locatello, and Emanuele Rodolà

   2024

   arXiv Bib

   @misc{maiorca2024latentspacetranslationinverse,
     title = {Latent Space Translation via Inverse Relative Projection},
     author = {Maiorca, Valentino and Moschella, Luca and Fumero, Marco and Locatello, Francesco and Rodolà, Emanuele},
     year = {2024},
     eprint = {2406.15057},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2406.15057},
   }

5. ArXiv

   Scalable unsupervised alignment of general metric and non-metric structures

   Sanketh Vedula, Valentino Maiorca, Lorenzo Basile, Francesco Locatello, and Alex Bronstein

   2024

   arXiv Bib

   @misc{vedula2024scalableunsupervisedalignmentgeneral,
     title = {Scalable unsupervised alignment of general metric and non-metric structures},
     author = {Vedula, Sanketh and Maiorca, Valentino and Basile, Lorenzo and Locatello, Francesco and Bronstein, Alex},
     year = {2024},
     eprint = {2406.13507},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2406.13507},
   }

6. ICLR

   From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication

   Irene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, and Emanuele Rodolà

   In The Twelfth International Conference on Learning Representations, 2024

   arXiv Bib

   @inproceedings{cannistraci2024from,
     title = {From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication},
     author = {Cannistraci, Irene and Moschella, Luca and Fumero, Marco and Maiorca, Valentino and Rodol{\`a}, Emanuele},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024},
     url = {https://openreview.net/forum?id=vngVydDWft},
   }

7. It’s All Relative: Relative Uncertainty in Latent Spaces using Relative Representations

   Fabian Mager, Valentino Maiorca, and Lars Kai Hansen

   In NeurIPS 2024 UniReps Workshop, 2024

2023

1. ICLR

   Relative representations enable zero-shot latent space communication

   Luca Moschella*, Valentino Maiorca*, Marco Fumero, Antonio Norelli, Francesco Locatello, and Emanuele Rodolà

   In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023, 2023

   arXiv Bib Code

   @inproceedings{relrep,
     author = {Moschella*, Luca and Maiorca*, Valentino and Fumero, Marco and Norelli, Antonio and Locatello, Francesco and Rodol{\`{a}}, Emanuele},
     title = {Relative representations enable zero-shot latent space communication},
     booktitle = {The Eleventh International Conference on Learning Representations,
                      {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
     publisher = {OpenReview.net},
     year = {2023},
     url = {https://openreview.net/pdf?id=SrC-nwieGJ},
     timestamp = {Fri, 30 Jun 2023 14:55:52 +0200},
     biburl = {https://dblp.org/rec/conf/iclr/MoschellaMFNLR23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

2. NeurIPS

   ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training

   Antonio Norelli, Marco Fumero, Valentino Maiorca, Luca Moschella, Emanuele Rodolà, and Francesco Locatello

   In Thirty-seventh Conference on Neural Information Processing Systems, 2023

   arXiv Bib Code

   @inproceedings{norelli2023asif,
     title = {{ASIF}: Coupled Data Turns Unimodal Models to Multimodal without Training},
     author = {Norelli, Antonio and Fumero, Marco and Maiorca, Valentino and Moschella, Luca and Rodol{\`a}, Emanuele and Locatello, Francesco},
     booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
     year = {2023},
     url = {https://openreview.net/forum?id=XjOj3ZmWEl},
   }

3. Sparse Vicious Attacks on Graph Neural Networks

   Giovanni Trappolini, Valentino Maiorca, Silvio Severino, Emanuele Rodola, Fabrizio Silvestri, and Gabriele Tolomei

   IEEE Transactions on Artificial Intelligence, 2023

   arXiv Bib Code

   @article{trappolini2023sparse,
     title = {Sparse Vicious Attacks on Graph Neural Networks},
     author = {Trappolini, Giovanni and Maiorca, Valentino and Severino, Silvio and Rodola, Emanuele and Silvestri, Fabrizio and Tolomei, Gabriele},
     journal = {IEEE Transactions on Artificial Intelligence},
     year = {2023},
     publisher = {IEEE},
   }

4. Bootstrapping Parallel Anchors for Relative Representations

   Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, and Emanuele Rodolà

   In The First Tiny Papers Track at ICLR 2023, Tiny Papers @ ICLR 2023, Kigali, Rwanda, May 5, 2023, 2023

   arXiv Bib

   @inproceedings{DBLP:conf/iclr/CannistraciMMFN23,
     author = {Cannistraci, Irene and Moschella, Luca and Maiorca, Valentino and Fumero, Marco and Norelli, Antonio and Rodol{\`{a}}, Emanuele},
     editor = {Maughan, Krystal and Liu, Rosanne and Burns, Thomas F.},
     title = {Bootstrapping Parallel Anchors for Relative Representations},
     booktitle = {The First Tiny Papers Track at {ICLR} 2023, Tiny Papers @ {ICLR} 2023,
                      Kigali, Rwanda, May 5, 2023},
     publisher = {OpenReview.net},
     year = {2023},
     url = {https://openreview.net/pdf?id=VBuUL2IWlq},
     timestamp = {Wed, 19 Jul 2023 17:21:16 +0200},
     biburl = {https://dblp.org/rec/conf/iclr/CannistraciMMFN23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

5. Attention-likelihood relationship in Transformers

   Valeria Ruscio, Valentino Maiorca, and Fabrizio Silvestri

   In The First Tiny Papers Track at ICLR 2023, Tiny Papers @ ICLR 2023, Kigali, Rwanda, May 5, 2023, 2023

   arXiv Bib Code

   @inproceedings{ruscio2023attention,
     author = {Ruscio, Valeria and Maiorca, Valentino and Silvestri, Fabrizio},
     editor = {Maughan, Krystal and Liu, Rosanne and Burns, Thomas F.},
     title = {Attention-likelihood relationship in Transformers},
     booktitle = {The First Tiny Papers Track at {ICLR} 2023, Tiny Papers @ {ICLR} 2023,
                      Kigali, Rwanda, May 5, 2023},
     publisher = {OpenReview.net},
     year = {2023},
     url = {https://openreview.net/pdf?id=R82eeIF4rP\_},
     timestamp = {Wed, 19 Jul 2023 17:21:16 +0200},
     biburl = {https://dblp.org/rec/conf/iclr/RuscioMS23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

6. ACL

   Accelerating Transformer Inference for Translation via Parallel Decoding

   Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, and Emanuele Rodolà

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023

   Abs Bib

   Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model, trading inference speed at the cost of the translation quality. In this paper, we propose to address the problem from the point of view of decoding algorithms, as a less explored but rather compelling direction. We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference. This formulation allows to speed up existing models without training or modifications while retaining translation quality. We present three parallel decoding algorithms and test them on different languages and models showing how the parallelization introduces a speedup up to 38% w.r.t. the standard autoregressive decoding and nearly 2x when scaling the method on parallel resources. Finally, we introduce a decoding dependency graph visualizer (DDGviz) that let us see how the model has learned the conditional dependence between tokens and inspect the decoding procedure.

   @inproceedings{santilli-etal-2023-accelerating,
     title = {Accelerating Transformer Inference for Translation via Parallel Decoding},
     author = {Santilli, Andrea and Severino, Silvio and Postolache, Emilian and Maiorca, Valentino and Mancusi, Michele and Marin, Riccardo and Rodol{\`{a}}, Emanuele},
     editor = {Rogers, Anna and Boyd-Graber, Jordan and Okazaki, Naoaki},
     booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2023},
     address = {Toronto, Canada},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2023.acl-long.689},
     doi = {10.18653/v1/2023.acl-long.689},
     pages = {12336--12355},
   }

7. Infusing invariances in neural representations

   Irene Cannistraci, Marco Fumero, Luca Moschella, Valentino Maiorca, and Emanuele Rodolà

   Jul 2023

   Bib

   @article{cannistraci2023infusing,
     title = {Infusing invariances in neural representations},
     author = {Cannistraci, Irene and Fumero, Marco and Moschella, Luca and Maiorca, Valentino and Rodol{\`a}, Emanuele},
     year = {2023},
   }

8. Zero-shot stitching in Reinforcement Learning using Relative Representations

   Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella, and Emanuele Rodolà

   In Sixteenth European Workshop on Reinforcement Learning, Jul 2023

   Bib

   @inproceedings{ricciardi2023zero,
     title = {Zero-shot stitching in Reinforcement Learning using Relative Representations},
     author = {Ricciardi, Antonio Pio and Maiorca, Valentino and Moschella, Luca and Rodol{\`a}, Emanuele},
     booktitle = {Sixteenth European Workshop on Reinforcement Learning},
     year = {2023},
   }

9. NeurIPS

   Latent Space Translation via Semantic Alignment

   Valentino Maiorca, Luca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, and Emanuele Rodolà

   In Thirty-seventh Conference on Neural Information Processing Systems, Jul 2023

   arXiv Bib

   @inproceedings{maiorca2023latent,
     title = {Latent Space Translation via Semantic Alignment},
     author = {Maiorca, Valentino and Moschella, Luca and Norelli, Antonio and Fumero, Marco and Locatello, Francesco and Rodol{\`a}, Emanuele},
     booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
     year = {2023},
   }

2022

1. LoG

   Metric Based Few-Shot Graph Classification

   Donato Crisostomi, Simone Antonelli, Valentino Maiorca, Luca Moschella, Riccardo Marin, and Emanuele Rodolà

   In Learning on Graphs Conference, Jul 2022

   Bib Code

   @inproceedings{crisostomi2022metric,
     title = {Metric Based Few-Shot Graph Classification},
     author = {Crisostomi, Donato and Antonelli, Simone and Maiorca, Valentino and Moschella, Luca and Marin, Riccardo and Rodol{\`a}, Emanuele},
     booktitle = {Learning on Graphs Conference},
     pages = {33--1},
     year = {2022},
     organization = {PMLR},
   }

2021

1. EMNLP

   WikiNEuRal: Combined neural and knowledge-based silver data creation for multilingual NER

   Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, and Roberto Navigli

   In Findings of the Association for Computational Linguistics: EMNLP 2021, Jul 2021

   Bib

   @inproceedings{tedeschi2021wikineural,
     title = {WikiNEuRal: Combined neural and knowledge-based silver data creation for multilingual NER},
     author = {Tedeschi, Simone and Maiorca, Valentino and Campolungo, Niccol{\`o} and Cecconi, Francesco and Navigli, Roberto},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
     pages = {2521--2533},
     year = {2021},
   }