Data is at the heart of digital transformations. However, between data and the business cases of companies there is still a big entry barrier :
Through our research projects, Euranova wants to develop a cutting-edge service offering providing competitive advantages to European entrepreneurs and businesses.
With BISHOP, the goal is to remove technological barriers related to the complexity of data and ensure data confidentiality and trust in AI models.
BISHOP’s research project was able to see the day due to the co-financing of the Walloon Region. Through its two research tracks, it addresses the following challenges :
Tackling data complexity ( Dilithium )
Building responsible AI ( Brainiac )
DILITHIUM aims at addressing the challenges of time-dependent graphs. Graphs have seen widespread adoption recently, driven by the abundance of complex data of various types and the transition from single-source analysis to deeply heterogeneous, multi-source systems. However, data is not static. To facilitate the adoption of graph models that evolve over time and thus better meet the needs of the market in the medium/long term, we develop methods for evolving graph embedding, based on state-of-the-art work and related disciplines. Finally, as explainability has become the central ingredient in trustworthy AI, we also explore state-of-the-art methods designed for explaining node, link or graph level predictions.
BRAINIAC aims at addressing the challenges of responsible artificial intelligence by developing data generative methods that allow the generation of realistic synthetic data. Those data are very close to the original data and represent the data (including minorities) in a complete way while being robust to known or future privacy attacks. Such agnosticity with respect to patterns and attacks requires attention to a way of quantifying the level of privacy using very general notions.