Image de couverture de livre

Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Peng, Jie, Lei, Runlin, Wei, Zhewei
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
par: Lei, Runlin, et autres
Publié: (2024)

Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks
par: Qi, Binchuan
Publié: (2026)

Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
par: Lei, Runlin, et autres
Publié: (2025)

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer
par: Peng, Jie, et autres
Publié: (2025)

Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report
par: Ding, Haipeng, et autres
Publié: (2025)

Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
par: Lei, Runlin, et autres
Publié: (2025)

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
par: He, Mingguo, et autres
Publié: (2022)

Future Link Prediction Without Memory or Aggregation
par: Yi, Lu, et autres
Publié: (2025)

Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks
par: Choi, Yoonhyuk, et autres
Publié: (2024)

Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
par: Yi, Lu, et autres
Publié: (2024)

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
par: Horvath, Samuel, et autres
Publié: (2023)

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
par: Huang, Keke, et autres
Publié: (2024)

Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
par: Yan, Chengcheng, et autres
Publié: (2025)

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
par: Zhang, Yang, et autres
Publié: (2023)

Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels
par: Tian, Yong-Ming, et autres
Publié: (2025)

Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
par: He, Xin, et autres
Publié: (2025)

A Trainable Feature Extractor Module for Deep Neural Networks and Scanpath Classification
par: Fuhl, Wolfgang
Publié: (2024)

Deep Network Trainability via Persistent Subspace Orthogonality
par: Massucco, Alex, et autres
Publié: (2025)

PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer
par: Ma, Jiahong, et autres
Publié: (2024)

Trainable and Explainable Simplicial Map Neural Networks
par: Paluzo-Hidalgo, Eduardo, et autres
Publié: (2023)

From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
par: Nguyen, Tuan, et autres
Publié: (2023)

Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons
par: Huang, Wei, et autres
Publié: (2023)

Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
par: Faria, Arthur M., et autres
Publié: (2025)

Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks
par: Fracastoro, Giulia, et autres
Publié: (2025)

Over-squashing in Spatiotemporal Graph Neural Networks
par: Marisca, Ivan, et autres
Publié: (2025)

Beyond Leakage and Complexity: Towards Realistic and Efficient Information Cascade Prediction
par: Peng, Jie, et autres
Publié: (2025)

Trainability Beyond Linearity in Variational Quantum Objectives
par: Ma, Gordon, et autres
Publié: (2026)

Comment on "A Note on Over-Smoothing for Graph Neural Networks"
par: Hasson, Razi, et autres
Publié: (2025)

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
par: Zhang, Leyang, et autres
Publié: (2025)

Graph Neural Networks Uncover Geometric Neural Representations in Reinforcement-Based Motor Learning
par: Nardi, Federico, et autres
Publié: (2024)

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
par: Roth, Andreas, et autres
Publié: (2023)

Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem
par: Huang, Chen, et autres
Publié: (2024)

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
par: Yi, Lu, et autres
Publié: (2025)

Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
par: Karabulut, Tuğrul Hasan, et autres
Publié: (2025)

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
par: Liang, Langzhang, et autres
Publié: (2025)

Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
par: Fu, Guoji, et autres
Publié: (2023)

Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks
par: Liu, Zewen, et autres
Publié: (2025)

Weightless Neural Networks for Continuously Trainable Personalized Recommendation Systems
par: Latif, Rafayel, et autres
Publié: (2025)

APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks
par: Subramanian, Barathi, et autres
Publié: (2024)

LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
par: Sun, Li, et autres
Publié: (2024)