SPLASH 2020
Sun 15 - Sat 21 November 2020 Online Conference
Thu 19 Nov 2020 15:20 - 15:40 at OOPSLA/ECOOP - R-5
Fri 20 Nov 2020 03:20 - 03:40 at OOPSLA/ECOOP - R-5

Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools and techniques for certifying fairness of these models or describing their biased behavior is, therefore, critical. In this paper, we propose a perfectly parallel static analysis for certifying causal fairness of feed-forward neural networks used for classification of tabular data. When certification succeeds, our approach provides definite guarantees, otherwise, it describes and quantifies the biased behavior. We design the analysis to be sound, in practice also exact, and configurable in terms of scalability and precision, thereby enabling pay-as-you-go certification. We implement our approach in an open-source tool and demonstrate its effectiveness on models trained with popular datasets.

Thu 19 Nov
Times are displayed in time zone: Central Time (US & Canada) change

15:00 - 16:20: R-5OOPSLA at OOPSLA/ECOOP +12h
15:00 - 15:20
Talk
OOPSLA
Sifis LagouvardosUniversity of Athens, Greece, Neville GrechUniversity of Athens, Greece, Ilias TsatirisUniversity of Athens, Yannis SmaragdakisUniversity of Athens, Greece
15:20 - 15:40
Talk
OOPSLA
Caterina UrbanINRIA & École Normale Supérieure, Maria ChristakisMPI-SWS, Germany, Valentin WüstholzConsenSys, Germany, Fuyuan ZhangMPI-SWS
15:40 - 16:00
Talk
OOPSLA
Elvira AlbertComplutense University of Madrid, Shelly GrossmanTel Aviv University, Noam RinetzkyTel Aviv University, Israel, Clara RodríguezComplutense University of Madrid, Albert RubioComplutense University of Madrid, Mooly SagivTel Aviv University
16:00 - 16:20
Talk
OOPSLA
Shengjian GuoBaidu X-Lab, Yueqi ChenThe Pennsylvania State University, Jiyong YuUniversity of Illinois at Urbana-Champaign, Meng WuAnt Financial, Zhiqiang ZuoNanjing University, China, Peng LiBaidu X-Lab, Yueqiang ChengBaidu Security

Fri 20 Nov
Times are displayed in time zone: Central Time (US & Canada) change

03:00 - 04:20: R-5OOPSLA at OOPSLA/ECOOP
03:00 - 03:20
Talk
OOPSLA
Sifis LagouvardosUniversity of Athens, Greece, Neville GrechUniversity of Athens, Greece, Ilias TsatirisUniversity of Athens, Yannis SmaragdakisUniversity of Athens, Greece
03:20 - 03:40
Talk
OOPSLA
Caterina UrbanINRIA & École Normale Supérieure, Maria ChristakisMPI-SWS, Germany, Valentin WüstholzConsenSys, Germany, Fuyuan ZhangMPI-SWS
03:40 - 04:00
Talk
OOPSLA
Elvira AlbertComplutense University of Madrid, Shelly GrossmanTel Aviv University, Noam RinetzkyTel Aviv University, Israel, Clara RodríguezComplutense University of Madrid, Albert RubioComplutense University of Madrid, Mooly SagivTel Aviv University
04:00 - 04:20
Talk
OOPSLA
Shengjian GuoBaidu X-Lab, Yueqi ChenThe Pennsylvania State University, Jiyong YuUniversity of Illinois at Urbana-Champaign, Meng WuAnt Financial, Zhiqiang ZuoNanjing University, China, Peng LiBaidu X-Lab, Yueqiang ChengBaidu Security