Copertina

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Arroyo, Álvaro, Gravina, Alessio, Gutteridge, Benjamin, Barbero, Federico, Gallicchio, Claudio, Dong, Xiaowen, Bronstein, Michael, Vandergheynst, Pierre
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can Graph Foundation Models Generalize Over Architecture?
di: Gutteridge, Benjamin, et al.
Pubblicazione: (2026)

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
di: Blayney, Hugh, et al.
Pubblicazione: (2025)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
di: Attali, Hugo, et al.
Pubblicazione: (2024)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
di: Attali, Hugo, et al.
Pubblicazione: (2026)

Position: Don't be Afraid of Over-Smoothing And Over-Squashing
di: Kormann, Niklas, et al.
Pubblicazione: (2026)

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
di: Jamadandi, Adarsh, et al.
Pubblicazione: (2024)

Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
di: Saber, Danial, et al.
Pubblicazione: (2025)

Limiting Over-Smoothing and Over-Squashing of Graph Message Passing by Deep Scattering Transforms
di: Jiang, Yuanhong, et al.
Pubblicazione: (2024)

Locality-Aware Graph-Rewiring in GNNs
di: Barbero, Federico, et al.
Pubblicazione: (2023)

On Measuring Long-Range Interactions in Graph Neural Networks
di: Bamberger, Jacob, et al.
Pubblicazione: (2025)

Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations
di: Seo, Sangwoo, et al.
Pubblicazione: (2025)

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
di: Fesser, Lukas, et al.
Pubblicazione: (2023)

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
di: Hariri, Ali, et al.
Pubblicazione: (2025)

Long Range Propagation on Continuous-Time Dynamic Graphs
di: Gravina, Alessio, et al.
Pubblicazione: (2024)

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
di: Heilig, Simon, et al.
Pubblicazione: (2024)

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
di: Gravina, Alessio, et al.
Pubblicazione: (2025)

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

Bundle Neural Networks for message diffusion on graphs
di: Bamberger, Jacob, et al.
Pubblicazione: (2024)

How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
di: You, Zinuo, et al.
Pubblicazione: (2025)

Enhancing Recommendation Systems with GNNs and Addressing Over-Smoothing
di: Liu, Wenyi, et al.
Pubblicazione: (2024)

Over-Squashing in Graph Neural Networks: A Comprehensive survey
di: Akansha, Singh
Pubblicazione: (2023)

GRAMA: Adaptive Graph Autoregressive Moving Average Models
di: Eliasof, Moshe, et al.
Pubblicazione: (2025)

Geometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs
di: Zosso, Mia, et al.
Pubblicazione: (2026)

Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
di: Karabulut, Tuğrul Hasan, et al.
Pubblicazione: (2025)

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
di: Liang, Langzhang, et al.
Pubblicazione: (2025)

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
di: Ceni, Andrea, et al.
Pubblicazione: (2025)

Information propagation dynamics in Deep Graph Networks
di: Gravina, Alessio
Pubblicazione: (2024)

Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks
di: Yang, Guangrui, et al.
Pubblicazione: (2024)

Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification
di: Tjandra, Benedict Aaron, et al.
Pubblicazione: (2024)

Over-squashing in Spatiotemporal Graph Neural Networks
di: Marisca, Ivan, et al.
Pubblicazione: (2025)

Functional correspondence by matrix completion
di: Kovnatsky, Artiom, et al.
Pubblicazione: (2014)

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
di: Queipo-de-Llano, Enrique, et al.
Pubblicazione: (2025)

On the Impact of Downstream Tasks on Sampling and Reconstructing Noisy Graph Signals
di: Sripathmanathan, Baskaran, et al.
Pubblicazione: (2025)

On the Impact of Sample Size in Reconstructing Noisy Graph Signals: A Theoretical Characterisation
di: Sripathmanathan, Baskaran, et al.
Pubblicazione: (2024)

A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting
di: Banf, Michael, et al.
Pubblicazione: (2025)

Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription
di: Gutteridge, Benjamin, et al.
Pubblicazione: (2025)

Improving Spatio-Temporal Residual Error Propagation by Mitigating Over-Squashing
di: Moghadas, Seyed Mohamad, et al.
Pubblicazione: (2026)

Effective Resistance Rewiring: A Simple Topological Correction for Over-Squashing
di: Miquel-Oliver, Bertran, et al.
Pubblicazione: (2026)

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
di: Roth, Andreas, et al.
Pubblicazione: (2023)

Graph Hierarchical Recurrence for Long-Range Generalization
di: Carotti, Stefano, et al.
Pubblicazione: (2026)