graph-neural-networks-54600fa4·2 events·first seen Aliases: Graph Neural Networks
A new arXiv preprint introduces a theoretical framework for understanding how ML models trained on small inputs generalize to larger, unseen input sizes — covering sequences, graphs, point clouds, and tensors. The approach uses random sampling maps (generalizing sampling with replacement, random binning, and species sampling) to compare inputs of different sizes and derive explicit generalization and sketching rates. The framework applies to transformers, graph neural networks, and moment polynomials, among other architectures. This is a foundational theoretical contribution addressing out-of-distribution generalization across input dimensionality.
This paper introduces FROG, a framework that treats relational database schema graph construction as a learnable optimization problem rather than a fixed design choice. The method formulates table role modeling as a learnable component, allowing tables to dynamically serve as nodes or edges in message passing, with functional dependency constraints ensuring semantic consistency. Experiments show FROG outperforms existing relational deep learning approaches and provides insights into how table roles affect downstream prediction tasks.