Information, Inference and Machine Learning Group at University College London

Afroditi Papadaki

Previous PhD Student

Contact

Where to Find Me

Room 7.05
Malet Place Engineering Building
Torrington Place
London WC1E 7JE
United Kingdom

Our Feed

Tweets by IIML-UCL

Research Interests

Responsible AI, Optimization, Federated Learning

About

Afroditi Papadaki holds a PhD in Electronic and Electrical Engineering and a postgraduate degree in Internet Engineering from University College London.

Publications

@misc{bertran2018learning,
                          title={Learning to Collaborate for User-Controlled Privacy},
                          author={Martin Bertran and Natalia Martinez and Afroditi Papadaki and Qiang Qiu and Miguel Rodrigues and Guillermo Sapiro},
                          year={2018},
                          eprint={1805.07410},
                          archivePrefix={arXiv},
                          primaryClass={stat.ML},
                          url={https://arxiv.org/abs/1805.07410}
                    }

@misc{
                    bertran2019learning,
                    title={Learning data-derived privacy preserving representations from information metrics},
                    author={Martin Bertran and Natalia Martinez and Afroditi Papadaki and Qiang Qiu and Miguel Rodrigues and Guillermo Sapiro},
                    year={2019},
                    url={https://openreview.net/forum?id=SJe2so0qF7},
                    }

@inproceedings{martinezbpf,
                      title={Blind Pareto Fairness and Subgroup Robustness},
                      author={Martinez, Natalia and Bertran, Martin and Papadaki, Afroditi and Rodrigues, Miguel and Sapiro, Guillermo},
                      booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML 2021)},
                      year = {2021}
                  }
                @inproceedings{neurips2021papadaki,
                author = {Papadaki, Afroditi and Martinez, Natalia and Bertran, Martin and Sapiro, Guillermo and Rodrigues, Miguel},
                title = {Federating for Learning Group Fair Models},
                year = {2021},
                address = {Virtual},
                booktitle = {New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)},
                                }

@inproceedings{papadaki2022,
                author = {Papadaki, Afroditi and Martinez, Natalia and Bertran, Martin and Sapiro, Guillermo and Rodrigues, Miguel},
                title = {Minimax Demographic Group Fairness in Federated Learning},
                year = {2022},
                isbn = {9781450393522},
                publisher = {Association for Computing Machinery},
                address = {New York, NY, USA},
                url = {https://doi.org/10.1145/3531146.3533081},
                doi = {10.1145/3531146.3533081},
                abstract = {Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how our proposed group fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm – FedMinMax – for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or superior performance.},
                booktitle = {2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2022)},
                pages = {142–159},
                numpages = {18},
                keywords = {Minimax Group Fairness, Algorithmic Fairness, Federated Learning},
                location = {Seoul, Republic of Korea},

}

@inproceedings{
                papadaki2022federated,
                title={Federated Fairness without Access to Demographics},
                author={Afroditi Papadaki and Natalia Martinez and Martin Andres Bertran and Guillermo Sapiro and Miguel R. D. Rodrigues},
                booktitle={Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)},
                year={2022},
                url={https://openreview.net/forum?id=CmmxQQE6U60A}
                  }

@inproceedings{martinezrobustness,
                      title={Pareto Robustness for Fairness Beyond Demographics},
                      author={Martinez, Natalia and Bertran, Martin and Papadaki, Afroditi and Rodrigues, Miguel and Sapiro, Guillermo},
                      booktitle={Fair AI in Finance at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)},
                      year = {2020}
                  }

@inproceedings{pmlr-v97-bertran19a,
                      title = {Adversarially Learned Representations for Information Obfuscation and Inference},
                      author = {Bertran, Martin and Martinez, Natalia and Papadaki, Afroditi and Qiu, Qiang and Rodrigues, Miguel and Reeves, Galen and Sapiro, Guillermo},
                      booktitle = {Proceedings of the 36th International Conference on Machine Learning (ICML 2019)},
                      pages = {614--623},
                      year = {2019},
                      editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov},
                      volume = {97},
                      series = {Proceedings of Machine Learning Research},
                      month = {09--15 Jun}, publisher = {PMLR},
                      pdf = {http://proceedings.mlr.press/v97/bertran19a/bertran19a.pdf},
                      url = { http://proceedings.mlr.press/v97/bertran19a.html },
                      code={https://github.com/MartinBertran/AIOI}}

@inproceedings{bertranlearning,
                      title={Learning Representations for Utility and Privacy: An Information-Theoretic Based Approach},
                      author={Bertran, Martin and Martinez, Natalia and Papadaki, Afroditi and Qiu, Qiang and Rodrigues, Miguel and Sapiro, Guillermo},
                      booktitle={Privacy in Machine Learning and Artificial Intelligence at the 35th International Conference on Machine Learning (ICML 2018)},
                      year = {2018}
                  }

• [view online ] ,[view code ]

, ,

, Media Coverage