↓Skip to main content

Research

Currently, I am a member of the ADA group at King’s College London, where I research graph neural networks under the joint supervision of Dr. Frederik Mallmann-Trenn and Dr. David Watson.

Previously, I focused on the intersection of Federated Learning and competitive environments at the University of California, Davis. My work focused on developing mechanisms to optimize collaboration and competition in machine learning systems, particularly in cross-silo Federated Learning and SplitFed learning settings.

Publications #

  • Dachille, J., Rossi, A., Maurya, S. K., Mallmann-Trenn, F., Liu, X., Giroire, F., Murata, T., and Natale, E. (2025). BRAVA-GNN: Betweenness Ranking Approximation Via Degree Mass Inspired Graph Neural Network. arXiv preprint. [link] [paper]
  • Dachille, J., Huang, C., and Liu, X. (2025). The Impact of Cut Layer Selection in Split Federated Learning. AAAI FLUID Workshop ‘25. [link] [paper]
  • Huang, C., Dachille, J., and Liu, X. (2024). Coopetition in Heterogeneous Cross-Silo Federated Learning. ECAI ‘24. [link] [paper]
  • Huang, C., Dachille, J., and Liu, X. (2024). An Accuracy-Shaping Mechanism for Competitive Distributed Learning. ICANN ‘24. [link] [paper]
  • Huang, C., Dachille, J., and Liu, X. (2024). When Federated Learning Meets Oligopoly Competition: Stability and Model Differentiation. IEEE Internet of Things Journal. [link] [paper]