arXiv Machine Learning September 23, 2026 By Zhicong Cai, Yinglong Zhang, Xiaoying Hong, Xuewen Xia, Xing Xu

PreGS: A Parameter-Transfer-Based Multi-Expert Graph Neural Network for Node Classification

Read the original on arXiv Machine Learning →

PreGS is a multi-expert graph neural network that uses parameter transfer from a pre‑trained multi‑head GAT to freeze GraphSAGE experts, creating complementary structural branches. The model fuses raw node features, GAT head outputs, and expert representations through an MLP, then combines the result with pretrained GAT logits. An extended version, PreGSv2, adds source‑level weighting and a structural gating mechanism for adaptive feature integration, and both variants outperform several baseline GNNs on eight public datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Sep 10

Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning

arXiv:2609.08709v1 Announce Type: new Abstract: Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embedding...

By Jonathan Frank, David Richerby, Ansgar Scherp

llms rag benchmarks

arXiv Machine Learning

1d ago

NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era

arXiv:2609.39673v1 Announce Type: new Abstract: Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality a...

By Jinmo Lee, Dooho Lee, Minho Jeong, Jaemin Yoo

benchmarks

arXiv Machine Learning

3d ago

Message Passing Does More with Less for In-Context Learning on Graphs

arXiv:2609.37057v1 Announce Type: new Abstract: Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeat...

By Dooho Lee, Jinmo Lee, Minho Jeong, Kijung Shin, Jaemin Yoo

llms

arXiv AI

Jun 17

Handling Feature Heterogeneity with Learnable Graph Patches

arXiv:2606. 17667v1 Announce Type: cross Abstract: In recent years, the rapid development of foundation models and graph pre-training technologies has spurred increasing interest in constructing a universal pre-trained graph model or Graph Foundation Model (GFM).

By Yifei Sun, Yang Yang, Xiao Feng, Zijun Wang, Haoyang Zhong, Chunping Wang, Lei Chen

rag

arXiv Machine Learning

Jun 2

OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

arXiv:2605. 15511v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning.

By Louisa Cornelis, Johan Mathe, Louis Van Langendonck, Guillermo Bern\'ardez, Nina Miolane

benchmarks

arXiv Machine Learning

Aug 28

Plain Transformers Can be Powerful Graph Learners

The paper shows that a plain Transformer can serve as an effective graph learner by adding three lightweight modifications: simplified L₂ attention, adaptive RMS normalization, and an MLP-based positional encoding stem. These changes preserve token magnitude and enable the model to achieve high expressivity on graph benchmarks, outperforming more complex graph transformer variants. The results suggest that plain Transformers can act as a unified backbone for multimodal learning across language, vision, and graph domains.

By Liheng Ma, Soumyasundar Pal, Yingxue Zhang, Philip H. S. Torr, Mark Coates

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning

NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era

Message Passing Does More with Less for In-Context Learning on Graphs

Handling Feature Heterogeneity with Learnable Graph Patches

OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

Plain Transformers Can be Powerful Graph Learners