Are we measuring oversmoothing in graph neural networks correctly?

Kaicheng Zhang, Piero Deidda, Desmond J. Higham, Francesco Tudisco
International Conference on Learning Representations (ICLR), (2026)
arxiv doi

dEBORA: Efficient Bilevel Optimization-based low-Rank Adaptation

Emanuele Zangrando, Sara Venturini, Francesco Rinaldi, Francesco Tudisco
In: International Conference on Learning Representations (ICLR), (2025)
doi

GeoLoRA: Geometric integration for parameter efficient fine-tuning

Steffen Schotthöfer, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco, Jonas Kusch
In "International Conference on Learning Representations (ICLR)", (2025)
arxiv doi

Low-Rank Adversarial PGD Attack

Dayana Savostianova, Emanuele Zangrando, Francesco Tudisco
preprint, (2024)
arxiv

Geometry-aware training of factorized layers in tensor Tucker format

Emanuele Zangrando, Steffen Schotthöfer, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
Advances in Neural Information Processing Systems (NeurIPS), (2024)
arxiv doi

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks

Emanuele Zangrando, Piero Deidda, Simone Brugiapaglia, Nicola Guglielmi, Francesco Tudisco
preprint, (2024)
arxiv

Robust low-rank training via approximate orthonormal constraints

Dayana Savostianova, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco
Advances in Neural Information Processing Systems (NeurIPS), (2023)
arxiv doi code

Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations

Steffen Schotthöfer, Emanuele Zangrando, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
Advances in Neural Information Processing Systems (NeurIPS), (2022)
arxiv doi code