6 papers
Scaling Weisfeiler-Leman Expressiveness Analysis to Massive Graphs with GPUs
Filippo Biondi, Mirco Tribastone, Max Tschaikowski
The stable coloring of the Weisfeiler-Leman (1-WL) test is a cornerstone of Graph Neural Networks because it provides an upper bound to the expressive power of message-passing arch…
Neural Network Compression by Approximate Differential Equivalence
Ravi Dhiman, Andrea Passarella, Mirco Tribastone +1
Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.g., magnitude-based pruning. We propose a complementary approach that comp…
RAwR: Role-Aware Rewiring via Approximate Equitable Partition
Riccardo Porcedda, Giuseppe Squillace, Bastian Epping +4
While Graph Neural Networks (GNNs) have demonstrated significant efficacy in node classification tasks, where predictions rely on local neighborhood information, the performance of…
DeGAS: Gradient-Based Optimization of Probabilistic Programs without Sampling
Francesca Randone, Romina Doz, Mirco Tribastone +1
We present DeGAS, a differentiable Gaussian approximate semantics for loopless probabilistic programs that enables sample-free, gradient-based optimization in models with both cont…
Certified Inductive Synthesis for Online Mixed-Integer Optimization
Marco Zamponi, Emilio Incerto, Daniele Masti +1
In fields such as autonomous and safety-critical systems, online optimization plays a crucial role in control and decision-making processes, often requiring the integration of cont…
Efficient Network Embedding by Approximate Equitable Partitions
Giuseppe Squillace, Mirco Tribastone, Max Tschaikowski +1
Structural network embedding is a crucial step in enabling effective downstream tasks for complex systems that aims to project a network into a lower-dimensional space while preser…