Bishop
Data is at the heart of digital transformations. However, between data and the business cases of companies there is still a big entry barrier :
the technology
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
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
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.
Internships 2024
This document presents internships supervised by our consulting department or by our research & development department. Each project is an opportunity to feel both empowered and responsible for your own professional development and for your contribution to the company.
Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings
In this paper, we study graph representation learning and show that data augmentation that preserves semantics can be learned and used to produce interpretations. Our framework, which we named INGENIOUS, creates inherently interpretable embeddings and eliminates the need for costly additional post-hoc analysis.
SANGEA: Scalable and Attributed Network Generation
In this paper, we present SANGEA, a sizeable synthetic graph generation framework that extends the applicability of any SGG to large graphs.
By first splitting the large graph into communities, SANGEA trains one SGG per community, then links the community graphs back together to create a synthetic large graph.
Internships 2023
This document presents internships supervised by our software engineering department or by our research & development department. Each project is an opportunity to feel both empowered and responsible for your own professional development and for your contribution to the company.
We Collaborate on the TAUDoS Project
We started a new collaboration with Aix-Marseille University, Montreal University, Nantes University, and St-Etienne on a four-year project called TAUDoS, which focuses on Trustful AI.
DEBS 2022
In June 2022, our research director Sabri Skhiri and the head of the data science department Madalina Ciortan travelled to Copenhagen to attend DEBS 2022, the leading conference focusing on distributed and event-based systems.