Geometric Deep Learning is an emerging paradigm to process graph-structured data with end-to-end trainable models, Graph Neural Networks (GNNs), with the ability to leverage prior knowledge about the data domain while offering large expressive power. Such attractive tradeoff has resulted in state-of-the-art performance over diverse domains, ranging from social networks, biology, knowledge bases, or finance. In this talk, I will present recent advances in our group covering both theory and applications. On the theory side, we quantify both the approximation power of GNN architectures and their stability to graph perturbations, resulting in a principled architecture design. We will illustrate these theoretical advances with applications in semi-supervised learning and forecasting in dynamic graphs modeling Social Network data, and discuss broader applications to recommender systems and fraud detection.... Read More إقرأ المزيد | Share it now!

Artificial Intelligence (AI) provides many opportunities to improve private and public life, and it has enjoyed significant investment. Indeed, discovering patterns and structures in large troves of data in an automated manner is a core component of data science. Machine learning currently drives applications in computational biology, natural language processing and robotics. However, such a highly positive impact is coupled with a significant challenge: when can we convincingly deploy these methods in our workplace? For example, can we provide prior knowledge and suggestions to the learning modules? Can we learn interpretable symbolic structures from data? In this talk, we look at the fundamental problem of unifying reasoning and learning, and how this enables a systematic way to integrate human knowledge and data-driven learning methods. We will then briefly consider how that unification may help us take steps towards a commonsensical, transparent and responsible AI.... Read More إقرأ المزيد | Share it now!