Cover Image

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Li, Huang, Zhenhao, Zhang, Ming, Yu, Philip S.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry
by: Sun, Li, et al.
Published: (2025)

On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks
by: Chehreghani, Mostafa Haghir
Published: (2026)

Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models
by: Sun, Li, et al.
Published: (2026)

RiemannGL: Riemannian Geometry Changes Graph Deep Learning
by: Sun, Li, et al.
Published: (2026)

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
by: Errica, Federico, et al.
Published: (2023)

Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
by: Arnaiz-Rodriguez, Adrian, et al.
Published: (2025)

Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
by: Hossen, Md Sazzad, et al.
Published: (2026)

Spiking Graph Neural Network on Riemannian Manifolds
by: Sun, Li, et al.
Published: (2024)

Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence
by: Yu, Philip S., et al.
Published: (2026)

Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning
by: Sun, Li, et al.
Published: (2024)

Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks
by: Wenkel, Frederik, et al.
Published: (2022)

Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger
by: Sun, Li, et al.
Published: (2026)

Oversmoothing: A Nightmare for Graph Contrastive Learning?
by: Li, Jintang, et al.
Published: (2023)

Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks
by: Bose, Kushal, et al.
Published: (2025)

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
by: Gravina, Alessio, et al.
Published: (2024)

Short-Range Oversquashing
by: Mishayev, Yaaqov, et al.
Published: (2025)

Learning Graph Foundation Models on Riemannian Graph-of-Graphs
by: Liu, Haokun, et al.
Published: (2026)

Are We Measuring Oversmoothing in Graph Neural Networks Correctly?
by: Zhang, Kaicheng, et al.
Published: (2025)

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
by: Park, MoonJeong, et al.
Published: (2024)

Partially Trained Graph Convolutional Networks Resist Oversmoothing
by: Kelesis, Dimitrios, et al.
Published: (2024)

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
by: Sun, Li, et al.
Published: (2024)

Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
by: Southern, Joshua, et al.
Published: (2024)

A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs
by: Wang, Jiaqi, et al.
Published: (2025)

Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization
by: Yang, Guangrui, et al.
Published: (2024)

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing
by: Sun, Li, et al.
Published: (2024)

Graph Neural Networks Do Not Always Oversmooth
by: Epping, Bastian, et al.
Published: (2024)

Resolving Oversmoothing with Opinion Dissensus
by: Wang, Keqin, et al.
Published: (2025)

Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
by: Keriven, Nicolas
Published: (2025)

Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks
by: Kelesis, Dimitrios, et al.
Published: (2024)

ASIL: Augmented Structural Information Learning for Deep Graph Clustering in Hyperbolic Space
by: Sun, Li, et al.
Published: (2025)

Demystifying Oversmoothing in Attention-Based Graph Neural Networks
by: Wu, Xinyi, et al.
Published: (2023)

Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics
by: Sun, Li, et al.
Published: (2025)

RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation
by: Yuan, Haonan, et al.
Published: (2026)

DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
by: Liu, Jiaxu, et al.
Published: (2023)

Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
by: Kelesis, Dimitrios, et al.
Published: (2025)

Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
by: Nagar, Eden, et al.
Published: (2026)

Setting the Record Straight on Transformer Oversmoothing
by: Dovonon, Gbètondji J-S, et al.
Published: (2024)

Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction
by: Gao, Yisen, et al.
Published: (2025)

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
by: Yuan, Haonan, et al.
Published: (2025)

Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
by: Park, MoonJeong, et al.
Published: (2024)