arXiv Machine Learning June 2, 2026 By Zichao Yue, Zhiru Zhang

Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs

Read the original on arXiv Machine Learning →

arXiv:2606. 01660v1 Announce Type: new Abstract: Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop features, which makes them highly scalable.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 15

Generalizing GNNs with Tokenized Mixture of Experts

arXiv:2602. 09258v2 Announce Type: replace Abstract: Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations.

By Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel, Qi Yang, Kaize Ding, Jundong Li, Chuxu Zhang

efficiency benchmarks

arXiv Machine Learning

Jul 21

Node4All: Learning Node Representation Beyond Datasets

arXiv:2607. 17272v1 Announce Type: new Abstract: Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning.

By Dooho Lee, Jaemin Yoo

llms benchmarks

arXiv Machine Learning

1d ago

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

arXiv:2603. 06952v2 Announce Type: replace Abstract: As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods.

By Yuhang Song, Naima Abrar Shami, Romaric Duvignau, Vasiliki Kalavri

arXiv Machine Learning

Aug 11

HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models

arXiv:2608. 09031v1 Announce Type: new Abstract: Graph neural networks typically propagate information through repeated message-passing layers, coupling the distance over which information travels with the number of nonlinear transformations applied.

By Isuru Herath, Arin Gopakumar, Sharan Sahu

benchmarks

arXiv AI

Jul 16

EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting

arXiv:2607. 13241v1 Announce Type: cross Abstract: Traffic forecasting is highly challenging due to complex and nonlinear spatial and temporal dependencies.

By Mingxing Xu, Rakesh Chowdary Machineni, Ke Liu, Xi Cheng, Chengqi Lu, Xin Hu, Lyuhao Chen, Xiangyu Li, Junwei You, Oliver Gao

benchmarks

arXiv AI

Aug 11

LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN

arXiv:2608. 09596v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long-range information is compressed through limited message-passing channels.

By Killian Cressant, Pedro B. Velloso

rag

Related stories

Generalizing GNNs with Tokenized Mixture of Experts

Node4All: Learning Node Representation Beyond Datasets

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models

EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting

LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN