Graph Representation Learning via Adaptive Expectile Aggregation
arXiv:2610.37450v1 Announce Type: new Abstract: Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic graphs. We propose ExpectileGCN, an adaptive graph…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-28 04:00 · arXiv stat.ML
Graph Representation Learning via Adaptive Expectile Aggregation