Davide Bacciu

Full Professor@University of Pisa·意大利·OpenReview

研究方向

deep learning for graphs · graph neural networks · learning with structured data · tree structured data · hidden markov models · recursive models · deep learning · RNNs · continual learning · dynamic memory

Davide Bacciu

Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation

Credal Graph Neural Networks for Robust Uncertainty Quantification

ComPhy: Composing Physical Models with end-to-end Alignment

A Sensitivity Analysis of State-Space Models on Graphs

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks

Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

Graph Adaptive Autoregressive Moving Average Models

SONAR: Long-Range Graph Propagation Through Information Waves

Graph Diffusion that can Insert and Delete

GRAMA: Adaptive Graph Autoregressive Moving Average Models

Derivatives Are All You Need For Learning Physical Models