Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Francesco Locatello

Enforcing and Discovering Structure in Machine Learning


Nov 26, 2021
Francesco Locatello

* Updated version of my PhD thesis, with fixed typos. Will keep updated as new typos are discovered 

  Access Paper or Ask Questions

Unsupervised Object Learning via Common Fate


Oct 13, 2021
Matthias Tangemann, Steffen Schneider, Julius von K├╝gelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias K├╝mmerer, Matthias Bethge, Bernhard Sch├Âlkopf


  Access Paper or Ask Questions

Dynamic Inference with Neural Interpreters


Oct 12, 2021
Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, Bernhard Sch├Âlkopf

* NeurIPS 2021 

  Access Paper or Ask Questions

You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction


Oct 11, 2021
Osama Makansi, Julius von K├╝gelgen, Francesco Locatello, Peter Gehler, Dominik Janzing, Thomas Brox, Bernhard Sch├Âlkopf


  Access Paper or Ask Questions

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain


Jul 23, 2021
Lukas Schott, Julius von K├╝gelgen, Frederik Tr├Ąuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Sch├Âlkopf, Francesco Locatello, Wieland Brendel


  Access Paper or Ask Questions

Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning


Jul 12, 2021
Andrea Dittadi, Frederik Tr├Ąuble, Manuel W├╝thrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Sch├Âlkopf, Stefan Bauer


  Access Paper or Ask Questions

Backward-Compatible Prediction Updates: A Probabilistic Approach


Jul 02, 2021
Frederik Tr├Ąuble, Julius von K├╝gelgen, Matth├Ąus Kleindessner, Francesco Locatello, Bernhard Sch├Âlkopf, Peter Gehler


  Access Paper or Ask Questions

Generalization and Robustness Implications in Object-Centric Learning


Jul 01, 2021
Andrea Dittadi, Samuele Papa, Michele De Vita, Bernhard Sch├Âlkopf, Ole Winther, Francesco Locatello


  Access Paper or Ask Questions

Neighborhood Contrastive Learning Applied to Online Patient Monitoring


Jun 09, 2021
Hugo Y├Ęche, Gideon Dresdner, Francesco Locatello, Matthias H├╝ser, Gunnar R├Ątsch

* ICML 2021 

  Access Paper or Ask Questions

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style


Jun 08, 2021
Julius von K├╝gelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Sch├Âlkopf, Michel Besserve, Francesco Locatello


  Access Paper or Ask Questions

Boosting Variational Inference With Locally Adaptive Step-Sizes


May 19, 2021
Gideon Dresdner, Saurav Shekhar, Fabian Pedregosa, Francesco Locatello, Gunnar R├Ątsch


  Access Paper or Ask Questions

Towards Causal Representation Learning


Feb 22, 2021
Bernhard Sch├Âlkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio

* Special Issue of Proceedings of the IEEE - Advances in Machine Learning and Deep Neural Networks 

  Access Paper or Ask Questions

On the Transfer of Disentangled Representations in Realistic Settings


Oct 27, 2020
Andrea Dittadi, Frederik Tr├Ąuble, Francesco Locatello, Manuel W├╝thrich, Vaibhav Agrawal, Ole Winther, Stefan Bauer, Bernhard Sch├Âlkopf


  Access Paper or Ask Questions

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation


Oct 27, 2020
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar R├Ątsch, Sylvain Gelly, Bernhard Sch├Âlkopf, Olivier Bachem

* Journal of Machine Learning Research 2020, Volume 21, Number 209 
* arXiv admin note: substantial text overlap with arXiv:1811.12359 

  Access Paper or Ask Questions

A Commentary on the Unsupervised Learning of Disentangled Representations


Jul 28, 2020
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar R├Ątsch, Sylvain Gelly, Bernhard Sch├Âlkopf, Olivier Bachem

* The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 (AAAI-20) 

  Access Paper or Ask Questions

Object-Centric Learning with Slot Attention


Jun 26, 2020
Francesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran, Georg Heigold, Jakob Uszkoreit, Alexey Dosovitskiy, Thomas Kipf


  Access Paper or Ask Questions

Is Independence all you need? On the Generalization of Representations Learned from Correlated Data


Jun 14, 2020
Frederik Tr├Ąuble, Elliot Creager, Niki Kilbertus, Anirudh Goyal, Francesco Locatello, Bernhard Sch├Âlkopf, Stefan Bauer

* 33 pages, 33 figures 

  Access Paper or Ask Questions

Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization


Feb 29, 2020
Geoffrey N├ęgiar, Gideon Dresdner, Alicia Tsai, Laurent El Ghaoui, Francesco Locatello, Fabian Pedregosa


  Access Paper or Ask Questions

Weakly-Supervised Disentanglement Without Compromises


Feb 07, 2020
Francesco Locatello, Ben Poole, Gunnar R├Ątsch, Bernhard Sch├Âlkopf, Olivier Bachem, Michael Tschannen


  Access Paper or Ask Questions

On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset


Jun 07, 2019
Muhammad Waleed Gondal, Manuel W├╝thrich, ─Éor─Ĺe Miladinovi─ç, Francesco Locatello, Martin Breidt, Valentin Volchkov, Joel Akpo, Olivier Bachem, Bernhard Sch├Âlkopf, Stefan Bauer


  Access Paper or Ask Questions

On the Fairness of Disentangled Representations


May 31, 2019
Francesco Locatello, Gabriele Abbati, Tom Rainforth, Stefan Bauer, Bernhard Sch├Âlkopf, Olivier Bachem


  Access Paper or Ask Questions

Are Disentangled Representations Helpful for Abstract Visual Reasoning?


May 29, 2019
Sjoerd van Steenkiste, Francesco Locatello, J├╝rgen Schmidhuber, Olivier Bachem

* This is a preliminary pre-print 

  Access Paper or Ask Questions

The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA


May 16, 2019
Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou, Francesco Locatello, Bernhard Sch├Âlkopf


  Access Paper or Ask Questions

Disentangling Factors of Variation Using Few Labels


May 03, 2019
Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar R├Ątsch, Bernhard Sch├Âlkopf, Olivier Bachem


  Access Paper or Ask Questions

Stochastic Conditional Gradient Method for Composite Convex Minimization


Jan 29, 2019
Francesco Locatello, Alp Yurtsever, Olivier Fercoq, Volkan Cevher


  Access Paper or Ask Questions

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations


Dec 02, 2018
Francesco Locatello, Stefan Bauer, Mario Lucic, Sylvain Gelly, Bernhard Sch├Âlkopf, Olivier Bachem

* This is a preliminary preprint based on our initial experimental results 

  Access Paper or Ask Questions

Boosting Black Box Variational Inference


Nov 01, 2018
Francesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar R├Ątsch


  Access Paper or Ask Questions

Deep Self-Organization: Interpretable Discrete Representation Learning on Time Series


Oct 05, 2018
Vincent Fortuin, Matthias H├╝ser, Francesco Locatello, Heiko Strathmann, Gunnar R├Ątsch


  Access Paper or Ask Questions