Paper Accepted at INFOCOM 2021: shadow banning practices in Twitter

Our paper, in collaboration with IRIT/ENSHEEIT and LAAS/CNRS, has been accepted to the 2021 IEEE International Conference on Computer Communications (INFOCOM), one of the flagship conferences in networking. It is entitled “Setting the Record Straighter on Shadow Banning”, and deals with the user-side observation of the (black-box) moderation algorithm of…

Continue reading

The Coronasurvey Team were finalists in the FB Symptom Data Challenge

The Coronasurveys team (https://coronasurveys.org/) led by Antonio Fernandez from IMDEA, and involving Davide Frey from the WIDE team, were finalists in the Facebook Symptom Data Challenge (https://www.symptomchallenge.org/). They developed forecasting methods for the number of COVID-19 cases based on the signals collected by the FB Symptom  Survey and by coronasurveys.org.…

Continue reading

Best Paper Award at Middleware 2020

The paper Online Federated Learning via Staleness Awareness and Performance Prediction. Georgios Damaskinos, Rachid Guerraoui, Anne-Marie Kermarrec, Vlad Nitu, Rhicheek Patra, François Taïani ⟨10.1145/3423211.3425685⟩. ⟨hal-03043237⟩ has been awarded the Best Paper Award at the 2020 ACM/IFP International Conference on Middleware, the premier event for the discussion of innovations and recent scientific…

Continue reading

3 papers accepted at Middleware 2020

The WIDE team proudly presented three papers at Middleware 2020, the ACM/IFIP International Conference on Middleware. Congratulations to Erwan, Georgios and Loïck, and for their respective successes! Georgios Damaskinos, Rachid Guerraoui, Anne-Marie Kermarrec, Vlad Nitu, Rhicheek Patra, François Taïani. FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction. ⟨10.1145/3423211.3425685⟩.…

Continue reading

Paper on AI Explainability published by Nature

Congratulations to Erwan Le Merrer (WIDE) and Gilles Trédan (LAAS), whose paper “Remote explainability faces the bouncer problem” has recently been published by Nature! The paper considers the concept of explainability of machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so…

Continue reading