Cover Image

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Jiawei, Li, Hongkang, Wang, Meng
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

Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks
by: He, Yuntian, et al.
Published: (2024)

Spectral Neural Graph Sparsification
by: Liguori, Angelica, et al.
Published: (2025)

Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
by: Xie, Beini, et al.
Published: (2024)

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
by: Li, Hongkang, et al.
Published: (2025)

Layer-wise Linear Mode Connectivity
by: Adilova, Linara, et al.
Published: (2023)

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
by: Li, Hongkang, et al.
Published: (2024)

SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks
by: Das, Siddhartha Shankar, et al.
Published: (2025)

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

Graph Sparsification via Mixture of Graphs
by: Zhang, Guibin, et al.
Published: (2024)

A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models
by: Shandirasegaran, Mugunthan, et al.
Published: (2026)

Less Is More -- On the Importance of Sparsification for Transformers and Graph Neural Networks for TSP
by: Lischka, Attila, et al.
Published: (2024)

Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
by: Krishnagopal, Sanjukta
Published: (2026)

Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report
by: Ding, Haipeng, et al.
Published: (2025)

Layer-wise Weight Selection for Power-Efficient Neural Network Acceleration
by: Fang, Jiaxun, et al.
Published: (2025)

Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification
by: Alsmeier, Hendrik, et al.
Published: (2025)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
by: Li, Hongkang, et al.
Published: (2024)

Layer-wise Derivative Controlled Networks
by: Martnishn, Rowan, et al.
Published: (2026)

Learning-Based Sparsification of Dynamic Graphs in Robotic Exploration Algorithms
by: Sastry, Adithya V., et al.
Published: (2026)

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
by: Vessio, Gennaro
Published: (2025)

Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
by: Han, Haoyu, et al.
Published: (2024)

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines
by: Song, Yuhang, et al.
Published: (2026)

Online Sparsification of Bipartite-Like Clusters in Graphs
by: Das, Joyentanuj, et al.
Published: (2025)

How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
by: Li, Hongkang, et al.
Published: (2024)

Empirical Error Estimates for Graph Sparsification
by: Wang, Siyao, et al.
Published: (2025)

Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition
by: Lyu, Shuyan, et al.
Published: (2025)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
by: Huang, Weizhong, et al.
Published: (2025)

Unveiling Mode Connectivity in Graph Neural Networks
by: Li, Bingheng, et al.
Published: (2025)

Element-wise Modulation of Random Matrices for Efficient Neural Layers
by: Szorc, Maksymilian
Published: (2025)

Machine Learning for Two-Stage Graph Sparsification for the Travelling Salesman Problem
by: Lin, Bo-Cheng, et al.
Published: (2026)

Layer-diverse Negative Sampling for Graph Neural Networks
by: Duan, Wei, et al.
Published: (2024)

Layer-wise dynamic rank for compressing large language models
by: Mi, Zhendong, et al.
Published: (2025)

Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
by: Roy, Dip, et al.
Published: (2026)

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
by: Luo, Yuankai, et al.
Published: (2024)

Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
by: Li, Hongkang, et al.
Published: (2024)

AMOSL: Adaptive Modality-wise Structure Learning in Multi-view Graph Neural Networks For Enhanced Unified Representation
by: Liang, Peiyu, et al.
Published: (2024)

Robust Network Learning via Inverse Scale Variational Sparsification
by: Zhou, Zhiling, et al.
Published: (2024)

Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
by: Huang, Jinshu, et al.
Published: (2025)

Jump Diffusion-Informed Neural Networks with Transfer Learning for Accurate American Option Pricing under Data Scarcity
by: Sun, Qiguo, et al.
Published: (2024)

Personalized Layer Selection for Graph Neural Networks
by: Sharma, Kartik, et al.
Published: (2025)

Financial Fraud Detection using Jump-Attentive Graph Neural Networks
by: Kadam, Prashank
Published: (2024)