← All work
published2023 – 2025

C3E — GNN Capacity Estimation

Estimating hidden width and propagation depth from a channel-capacity view of graph representation learning.

  • Graph neural networks
  • Architecture search
  • Information theory

Problem

GNN width and depth are often chosen heuristically even though both control information compression and over-squashing.

Approach

Model spectral GNN propagation as a communication channel and estimate capacity-constrained architecture settings through nonlinear optimization.

Role

First author and lead implementation author

C3E connects graph structure, propagation, hidden dimension, and depth through an information-capacity formulation. The result is an auditable architecture-selection mechanism rather than a broad brute-force search.