# Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts

arXiv: https://arxiv.org/abs/2601.05537 · HTML: https://mlsanity.com/paper/2601.05537/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- Mixture-of-experts / [MoE for time series and graphs](https://mlsanity.com/moe/moe-for-time-series-and-graphs/)

## Builds on (most cited first, 25 of 25)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models](https://mlsanity.com/paper/2501.11873/) (2025)
- [Scalable Graph Neural Networks for Heterogeneous Graphs](https://mlsanity.com/paper/2011.09679/) (2020)
- [Heterogeneous Graph Representation Learning with Relation Awareness](https://mlsanity.com/paper/2105.11122/) (2021)
- [GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts](https://mlsanity.com/paper/2412.11085/) (2024)
- [LocMoE: A Low-Overhead MoE for Large Language Model Training](https://mlsanity.com/paper/2401.13920/) (2024)
- [ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization](https://mlsanity.com/paper/2206.08181/) (2022)
- [DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts](https://mlsanity.com/paper/2411.03025/) (2024)
- [R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph](https://mlsanity.com/paper/2103.07877/) (2021)
- [MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts](https://mlsanity.com/paper/2509.09337/) (2025)

## Abstract (arXiv)

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.