Riccardo Porcedda

Biography

Riccardo Porcedda is a PhD student in Artificial Intelligence at the University of Pisa and Scuola Superiore Sant’Anna. His research focuses mostly on graph neural networks and synthetic network generation, with a recent focus on role discovery. He holds a background in Physics and Data Science and has been a visiting researcher at the Complexity Science Hub in Vienna and RWTH Aachen University. He also had experiences in startups working in the field of xAI, and liquidity optimization in financial networks (entering also the Fintech Milano Hub of Banca d'Italia for the project "B2Bridge" while being Chief Data Officer of Liqex Srl). In December 2025 he founded Little-g.AI, a startup focused on the development of efficient foundational models alternatives to LLMs, focusing on applications on the academic publishing processes.

Workshop contributions

RAwR: Role-Aware Rewiring via Approximate Equitable Partition

Graph neural networks (GNNs) are effective for node classification when labels can leverage information from local neighborhoods. However, they can struggle when prediction depends on long-range interactions, due to well-known problems such as oversquashing. To address this issue, prior work has proposed rewiring the graph topology to improve signal propagation. In this work, we introduce RAwR, a novel and efficient rewiring method that creates a quotient graph from an equitable partition and connects it to the input graph. This enables faster communication between nodes with the same structural role -- i.e., the same Weisfeiler-Leman graph coloring -- and reduces the total effective resistance. Furthermore, an approximate definition of the equitable partition allows for controllable shrinking of the quotient graph until it collapses to a single node, thereby recovering the well-known Master Node rewiring technique. Across a broad evaluation benchmark, including standard homophilic and heterophilic datasets as well as synthetic graphs specifically designed for long-range interactions, RAwR achieves state-of-the-art results. We also analytically investigate the improvements that RAwR can achieve in an idealized teacher-student model of linear GNNs, explaining when and why role-based rewiring helps. This theoretical insight leads to the definition of Spectral Role Lift (SRL), a measure useful for identifying the approximate equitable partition that leads to the best performance.