Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Wei, Huang, Hong, Shi, Ruize, Liu, Bang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911362978938880
author Zhou, Wei
Huang, Hong
Shi, Ruize
Liu, Bang
author_facet Zhou, Wei
Huang, Hong
Shi, Ruize
Liu, Bang
contents Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts make a global head miss fine semantics, overfit hub nodes, and underserve tail nodes. While Mixture-of-Experts(MoE) could help, naively applying it clashes with structural imbalance and risks expert collapse. We propose a Heterogeneous-aware Orthogonal Prototype Experts framework named HOPE, a plug-and-play replacement for the standard prediction head. HOPE uses learnable prototype-based routing to assign instances to experts by similarity, letting expert usage follow the natural long-tail distribution, and adds expert orthogonalization to encourage diversity and prevent collapse. Experiments on four real datasets show consistent gains across SOTA HGNN backbones with minimal overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05537
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts
Zhou, Wei
Huang, Hong
Shi, Ruize
Liu, Bang
Machine Learning
Artificial Intelligence
Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts make a global head miss fine semantics, overfit hub nodes, and underserve tail nodes. While Mixture-of-Experts(MoE) could help, naively applying it clashes with structural imbalance and risks expert collapse. We propose a Heterogeneous-aware Orthogonal Prototype Experts framework named HOPE, a plug-and-play replacement for the standard prediction head. HOPE uses learnable prototype-based routing to assign instances to experts by similarity, letting expert usage follow the natural long-tail distribution, and adds expert orthogonalization to encourage diversity and prevent collapse. Experiments on four real datasets show consistent gains across SOTA HGNN backbones with minimal overhead.
title Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.05537