paper-with-me

홈 › Papers

Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study

2025-10-21 · Gangda Deng, Yuxin Yang, Ömer Faruk Akgül, Hanqing Zeng, Yinglong Xia, Rajgopal Kannan, Viktor Prasanna arxiv

Graph Neural Networks (GNNs) have become essential tools for learning on relational data, yet the performance of a single GNN is often limited by the heterogeneity present in real-world graphs. Recent advances in Mixture-of-Experts (MoE) frameworks demonstrate that assembling multiple, explicitly diverse GNNs with distinct generalization patterns can significantly improve performance. In this work, we present the first systematic empirical study of expert-level diversification techniques for GNN ensembles. Evaluating 20 diversification strategies -- including random re-initialization, hyperparameter tuning, architectural variation, directionality modeling, and training data partitioning -- across 14 node classification benchmarks, we construct and analyze over 200 ensemble variants. Our comprehensive evaluation examines each technique in terms of expert diversity, complementarity, and ensemble performance. We also uncovers mechanistic insights into training maximally diverse experts. These findings provide actionable guidance for expert training and the design of effective MoE frameworks on graph data. Our code is available at https://github.com/Hydrapse/bench-gnn-diversification.

📄 PDF Abstract BibTeX arXiv:2510.18370

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification

Similar Papers 제목 키워드 기반

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

2026-03-12 · Yulu Gan, Phillip Isola arxiv

Pretraining produces a learned parameter vector that is typically treated as a starting point for further iterative adaptation. In this work, we instead view the outcome of pretraining as a distribution over parameter ve…

SnapE -- Training Snapshot Ensembles of Link Prediction Models

2024-08-05 · Ali Shaban, Heiko Paulheim

Snapshot ensembles have been widely used in various fields of prediction. They allow for training an ensemble of prediction models at the cost of training a single one. They are known to yield more robust predictions by …

Knowledge GraphsLink PredictionPrediction

GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

2024-10-12 · Dingyi Zhuang, Chonghe Jiang, Yunhan Zheng, Shenhao Wang 외

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications w…

Mixture-of-Experts

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling

2023-09-21 · NeurIPS 2023 11

Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges of varying types. To bolster the genera…

Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization

2025-10-24 · Yunlong Chu, Minglai Shao, Zengyi Wo, Bing Hao 외 arxiv

Graph Neural Networks (GNNs) face a fundamental adaptability challenge: their fixed message-passing architectures struggle with the immense diversity of real-world graphs, where optimal computational strategies vary by l…

Node ClassificationFew-Shot Learning