Graph Representation Learning via Adaptive Expectile Aggregation
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 aggregation framework that introduces a learnable expectile level to capture neighborhood information beyond the mean. The proposed operator continuously adjusts aggregation between minimum- and maximum-type behaviors, with mean aggregation as a special case. A differentiable approximation based on sigmoid smoothing and fixed-point iterations enables end-to-end optimization. Theoretically, we establish stability properties and transductive generalization guarantees for ExpectileGCN. We further investigate its classification risk under heterophilic neighborhood models. For informative neighborhoods, we show that expectile aggregation can exploit class-dependent scale differences to achieve a classification advantage over mean aggregation. Under a local asymptotic regime with diminishing per-neighbor label informativeness, we establish that this advantage can persist in terms of limiting classification risk. Experiments on homophilic and heterophilic benchmark graphs demonstrate strong predictive performance and improved robustness under feature corruption and structural perturbations.
Related
- Hyperbolic Graph Representation Learning: Embed in One Metric, Optimize with Another
- Adaptive Task Offloading Under Dynamic Topology via Graph Attention-Enhanced Reinforcement Learning for Layered UAV-Enabled Digital Twin Channel Modeling
- Conditional Aggregation in Context-Aware Fuzzy Systems: A Fibered Representation Theory
- Invertible Graph Aggregation Can Increase ReLU Readout Width
- Combining Weather Forecast Aggregation and State-Space Models for Adaptive Probabilistic Electricity Load Forecasting
BibTeX
@misc{zhu2026graph,
title = {{Graph Representation Learning via Adaptive Expectile Aggregation}},
author = {Tianyi Zhu and Wei Lan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37450},
eprint = {2610.37450},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37450},
}
RIS
TY - UNPB
TI - Graph Representation Learning via Adaptive Expectile Aggregation
AU - Tianyi Zhu
AU - Wei Lan
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.37450
UR - https://arxiv.org/abs/2610.37450
AB - 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 aggregation framework that introduces a learnable expectile level to capture neighborhood information beyond the mean. The proposed operator continuously adjusts aggregation between minimum- and maximum-type behaviors, with mean aggregation as a special case. A differentiable approximation based on sigmoid smoothing and fixed-point iterations enables end-to-end optimization. Theoretically, we establish stability properties and transductive generalization guarantees for ExpectileGCN. We further investigate its classification risk under heterophilic neighborhood models. For informative neighborhoods, we show that expectile aggregation can exploit class-dependent scale differences to achieve a classification advantage over mean aggregation. Under a local asymptotic regime with diminishing per-neighbor label informativeness, we establish that this advantage can persist in terms of limiting classification risk. Experiments on homophilic and heterophilic benchmark graphs demonstrate strong predictive performance and improved robustness under feature corruption and structural perturbations.
ER -