3 papers
cs.LG2026
Graph Hierarchical Recurrence for Long-Range Generalization
Stefano Carotti, Marco Pacini, Alessio Gravina +3
Graph Neural Networks and Graph Transformers have become central to graph learning, combining expressive representation learning with sample-efficient inductive biases. Yet they re…
cs.CL2024
Self-generated Replay Memories for Continual Neural Machine Translation
Michele Resta, Davide Bacciu
Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, s…
cs.LG2024
Multi-Relational Graph Neural Network for Out-of-Domain Link Prediction
Asma Sattar, Georgios Deligiorgis, Marco Trincavelli +1
Dynamic multi-relational graphs are an expressive relational representation for data enclosing entities and relations of different types, and where relationships are allowed to var…