Publications and Preprints

• Membership Inference Attacks against Large Vision-Language Models (NeurIPS 2024)
  Zhan Li, Yongtao Wu, Yihang Chen, Francesco Tonin, Elias Abad Rocamora, Volkan Cevher   [paper]

• HeNCler: Node Clustering in Heterophilous Graphs through Learned Asymmetric Similarity (preprint)
  Sonny Achten, Francesco Tonin, Volkan Cevher, Johan A. K. Suykens   [paper]

• Quantum-PEFT: Ultra parameter-efficient fine-tuning (ICML 2024 Workshop)
  Toshiaki Koike-Akino*, Francesco Tonin*, Yongtao Wu, Leyla Naz Candogan, Volkan Cevher   [paper]

• Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method (ICML 2024)
  Qinghua Tao*°, Francesco Tonin*°, Alex Lambert, Yingyi Chen, Panagiotis Patrinos, Johan A. K. Suykens   [paper, poster]

• Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes (ICML 2024)
  Yingyi Chen, Qinghua Tao, Francesco Tonin, Johan A. K. Suykens   [paper]

• Tensor-based Multi-view Spectral Clustering via Shared Latent Space (Information Fusion, 2024)
  Qinghua Tao°, Francesco Tonin°, Panagiotis Patrinos, Johan A. K. Suykens   [paper, code]

• Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification (AAAI 2024)
  Sonny Achten, Francesco Tonin, Panagiotis Patrinos, Johan A. K. Suykens   [paper]

• Deep Kernel Principal Component Analysis for Multi-level Feature Learning (Neural Networks, 2024)
  Francesco Tonin, Qinghua Tao, Panagiotis Patrinos, Johan A. K. Suykens   [paper, code]

• Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation (NeurIPS 2023)
  Yingyi Chen, Qinghua Tao, Francesco Tonin, Johan A. K. Suykens   [paper]

• Nonlinear SVD with Asymmetric Kernels: feature learning and asymmetric Nyström method (preprint)
  Qinghua Tao*°, Francesco Tonin*°, Panagiotis Patrinos, Johan A. K. Suykens   [paper]

• Combining Primal and Dual Representations in Deep Restricted Kernel Machines Classifiers (ECML 2023 Workshop)
  Francesco Tonin, Panagiotis Patrinos, Johan A. K. Suykens   [paper]

• Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms (ICML 2023)
  Francesco Tonin*°, Alex Lambert*, Panagiotis Patrinos, Johan A. K. Suykens   [paper, code, poster, project page]

• Unsupervised Learning of Disentangled Representations in Deep Restricted Kernel Machines with Orthogonality Constraints (Neural Networks, 2021)
  Francesco Tonin, Panagiotis Patrinos, Johan A. K. Suykens   [paper, code]

• Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine (IJCNN 2021)
  Francesco Tonin, Arun Pandey, Panagiotis Patrinos, Johan A. K. Suykens   [paper, slides, code]

* indicates equal contribution, ° indicates corresponding author.