The Quest for the GRAph Level autoEncoder (GRALE)
Krzakala, P., Melo, G., Laclau, C., d'Alché-Buc, F., & Flamary, R. (2025). The Quest for the GRAph Level autoEncoder (GRALE). arXiv preprint arXiv:2505.22109.
CV
Education
- (2023-2026) PhD at Institut Polytechnique
- (2022-2023) Master MVA
- (2019-2023) ENS Paris-Saclay
- (2017-2019) Classe préparatoire Stanilas
Publications
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
Krzakala, P., Yang, J., Flamary, R., d'Alché-Buc, F., Laclau, C., & Labeau, M. (2024). Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss. Advances in Neural Information Processing Systems, 37, 101552-101588.
Irregular layout for a satellite’s interferometric array
Krzakala, Paul and Assouel, Amine, et al. (2021). Irregular layout for a satellite’s interferometric array. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 9408-9423..
Talks
Training Neural Networks to Predict Graphs. Who is afraid of the big bad NP-hardness ?
Talk at EPFL, Lausanne, Switzerland
Any2Graph, A framework for deep Supervised Graph Prediction
Talk at Neurips in Paris, Paris, France
Adversarial Examples, an overview.
Talk at Télécom Paris, Paris, France
An introduction to Machine Learning.
Invited talk at Institut Fourier, Grenoble, France