arXiv Machine Learning October 8, 2026 By Zhewei Chen, Hao Zhu, Jiaojiao Jiang, Ahad N. Zehmakan

Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs

Read the original on arXiv Machine Learning →

The paper introduces G^2MLP, a graph‑free MLP trained via distillation from a GNN teacher while preserving the teacher’s graph‑induced geometry. It identifies two spectral failure modes—underfit on sparse graphs and overfit on dense graphs—caused by neglecting geometry during distillation. By using Ollivier‑Ricci curvature to guide supervision between prediction‑level and representation‑level alignment, G^2MLP improves node‑classification performance and reduces the teacher‑student rank gap across benchmarks.

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.

arXiv Machine Learning

Oct 2

Model-to-Data Distillation for Graph Neural Networks

The paper introduces Model-to-Data (M2D) distillation, a method that transfers properties learned by a complex graph neural network (GNN) teacher into the graph data itself. By jointly learning augmented node features and graph structure, M2D encodes the teacher’s behavior, allowing simpler GNNs to recover high predictive performance, fairness, and robustness. The resulting graph can be reused with various downstream models, enabling them to approximate sophisticated teachers such as fairness-aware GNNs, Graph Attention Networks, and Graph Transformers.

By Debolina Halder Lina, Arlei Silva

llms efficiency safety

arXiv AI

Jul 21

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

arXiv:2604. 10882v2 Announce Type: replace-cross Abstract: Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data.

By Yang Yan, Yunxuan Li, Qiuyan Wang, Tianjin Huang, Qiudong Yu

fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 30

The Universal Classifier for Graph Learning

arXiv:2609.36302v1 Announce Type: new Abstract: While foundation models have revolutionized natural language processing and computer vision by leveraging universal vocabularies, Graph Machine Learnin...

By Ben Finkelshtein, Andr\'{e} Linhares, Petar Veli\v{c}kovi\'{c}, Bryan Perozzi, Mikhail Galkin

diffusion computer-vision nlp

arXiv AI

Aug 6

NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

arXiv:2608. 04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space.

By Tinghe Zhang, Jian Xu, Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Qiang Wang

rag diffusion fine-tuning benchmarks

arXiv Machine Learning

Jun 5

The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning

arXiv:2606. 06397v1 Announce Type: new Abstract: Current evaluation practices in relational learning rely heavily on flat leaderboards that average performance across heterogeneous datasets, implicitly assuming a uniform underlying structure.

By Shuo Wang, Xiangyu Wang, Quanxin Wang, Bailin Wu, Bokui Wang, Shunyang Huang, Boyan Deng, Haonan Liu, Ruiyi Fang, Zhenxiang Xu, Boyu Wang, Zhao Kang

benchmarks safety

Hugging Face Trending Papers

Jul 13

Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment

Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains. Recent advancements in GFMs have been largely dominated by two paradigms: Graph Neural Network and Large Language Model (LLM) based methods.

llms diffusion benchmarks safety

One email a morning, machine-written

Related stories

Model-to-Data Distillation for Graph Neural Networks

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

The Universal Classifier for Graph Learning

NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning

Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment