Neuron Alignment | Biagio (Mattia) La Rosa

This page provides a summary sheet that includes the general goal, reference papers (both mine and external) for an overview of the topic, as well as the domains explored so far. We are also interested in extending the applications of these techniques beyond their traditional domains. If you have expertise in other areas (e.g., neuroscience, gaming, or audio/speech modeling), we would be happy to explore potential extensions into those fields.

Goal: The goal of this research area is to understand what deep neural networks learn during the training process. My research focuses on capturing the alignment between neurons activations and human-defined knowledge (e.g., concepts). These methods typically combine tools from classical AI (e.g., heuristic search and clustering), statistical analysis, and recent advancements in AI.

Domains: NLP, Vision.

Reference Papers:

Compositional Explanations: [Seminal Paper]
Clustered Compositional Explanations: [(La Rosa et al., 2023)]
Open Vocabulary Compoisitional Explanations: [(La Rosa & Gilpin, 2025)]
Optimal Compositional Explanations: [(La Rosa & Gilpin, 2025)]
Metrics : [(Makinwa et al., 2022)]

References

2025

Pre-Print

Open Vocabulary Compositional Explanations for Neuron Alignment

Biagio La Rosa, and Leilani H. Gilpin

2025

Bib DOI Official PDF

@article{LaRosa2025open,
  author = {{La Rosa}, Biagio and Gilpin, Leilani H.},
  title = {Open Vocabulary Compositional Explanations for Neuron Alignment},
  year = {2025},
  archiveprefix = {arXiv},
  doi = {10.48550/ARXIV.2511.20931},
  eprint = {2511.20931},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), FOS: Computer and information sciences},
  primaryclass = {cs.CV},
  publisher = {arXiv},
}

Pre-Print

Guaranteed Optimal Compositional Explanations for Neurons

Biagio La Rosa, and Leilani H. Gilpin

2025

Bib DOI Official PDF

@article{LaRosa2025optimal,
  author = {{La Rosa}, Biagio and Gilpin, Leilani H.},
  title = {Guaranteed Optimal Compositional Explanations for Neurons},
  year = {2025},
  archiveprefix = {arXiv},
  doi = {10.48550/ARXIV.2511.20934},
  eprint = {2511.20934},
  keywords = {Artificial Intelligence (cs.AI), Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences},
  primaryclass = {cs.AI},
  publisher = {arXiv},
}

2023

Conference

Towards a fuller understanding of neurons with Clustered Compositional Explanations

Biagio La Rosa, Leilani H. Gilpin, and Roberto Capobianco

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

Bib Official PDF Code

@inproceedings{LaRosa2023Towards,
  title = {Towards a fuller understanding of neurons with Clustered Compositional Explanations},
  author = {{La Rosa}, Biagio and Gilpin, Leilani H. and Capobianco, Roberto},
  booktitle = {Thirty-seventh Conference on Neural Information Processing Systems},
  year = {2023},
  url = {https://openreview.net/forum?id=51PLYhMFWz},
}

2022

Conference

Detection Accuracy for Evaluating Compositional Explanations of Units

Sayo M. Makinwa, Biagio La Rosa, and Roberto Capobianco

In AIxIA 2021 - Advances in Artificial Intelligence, 2022

Bib DOI Official PDF Code

@incollection{Makinwa2022,
  author = {Makinwa, Sayo M. and {La Rosa}, Biagio and Capobianco, Roberto},
  booktitle = {AIxIA 2021 - Advances in Artificial Intelligence},
  publisher = {Springer International Publishing},
  title = {Detection Accuracy for~Evaluating Compositional Explanations of~Units},
  year = {2022},
  pages = {550--563},
  doi = {10.1007/978-3-031-08421-8_38},
}