Message-passing graph neural networks (MPNNs) emerged as powerful tools for
processing graph-structured input. However, they operate on a fixed input graph structure …

Abstract Multimodal Recommender Systems (MRS) enhance the performance of
recommendations by utilizing different item information, such as text, images, and audio …

Graph neural networks (GNNs) have significantly advanced the processing of graph-
structured data, where objects exhibit complex relationships and interdependencies. The …

Predicting the mobility patterns of vehicles together with their interactions among
surrounding traffic objects is a critical task in autonomous driving systems. Existing graph …

Graph data are well suited to represent complex interactions and dependencies owing to its
inherent relational structure. Graph neural networks (GNNs) can effectively explore the …

This is a thesis of two halves. In the first, we address autonomous 3D reconstruction, the
process by which an agent constructs its own representations of a scene. In the second, we …