5 papers
The Expressive Power of Random-Feature MPNNs Across Graph Sizes
Robert R. Nerem, Mitchell Black, Antonis Vasileiou +2
Continuous random node features increase the expressivity of message-passing neural networks (MPNNs), but existing theoretical analyses are not fine-grained enough to capture their…
Algorithmically Aligned Neural Agglomerative Tree Construction
Robert R Nerem, Pranav Singh, Cheyenne Ward +1
Linkage algorithms for hierarchical clustering (HC) are a powerful and efficient framework for constructing clustering trees, yet it is often unclear which merge rule best suits a…
Which Algorithms Can Graph Neural Networks Learn?
Solveig Wittig, Antonis Vasileiou, Robert R. Nerem +4
In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural…
Graph neural networks extrapolate out-of-distribution for shortest paths
Robert R. Nerem, Samantha Chen, Sanjoy Dasgupta +1
Neural networks (NNs), despite their success and wide adoption, still struggle to extrapolate out-of-distribution (OOD), i.e., to inputs that are not well-represented by their trai…
Differentiable Extensions with Rounding Guarantees for Combinatorial Optimization over Permutations
Robert R. Nerem, Zhishang Luo, Akbar Rafiey +1
Continuously extending combinatorial optimization objectives is a powerful technique commonly applied to the optimization of set functions. However, few such methods exist for exte…