Cover Image

How Graph Neural Networks Learn: Lessons from Training Dynamics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Chenxiao, Wu, Qitian, Wipf, David, Sun, Ruoyu, Yan, Junchi
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transformers from Diffusion: A Unified Framework for Neural Message Passing
by: Wu, Qitian, et al.
Published: (2024)

Learning Divergence Fields for Shift-Robust Graph Representations
by: Wu, Qitian, et al.
Published: (2024)

Handling Distribution Shifts on Graphs: An Invariance Perspective
by: Wu, Qitian, et al.
Published: (2022)

SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
by: Wu, Qitian, et al.
Published: (2024)

Graph Out-of-Distribution Generalization via Causal Intervention
by: Wu, Qitian, et al.
Published: (2024)

GeoMix: Towards Geometry-Aware Data Augmentation
by: Zhao, Wentao, et al.
Published: (2024)

Supercharging Graph Transformers with Advective Diffusion
by: Wu, Qitian, et al.
Published: (2023)

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
by: Wu, Qitian, et al.
Published: (2023)

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
by: Yang, Chenxiao, et al.
Published: (2025)

New Evidence of the Two-Phase Learning Dynamics of Neural Networks
by: Zhou, Zhanpeng, et al.
Published: (2025)

EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
by: Chen, Chao, et al.
Published: (2023)

Implicit vs Unfolded Graph Neural Networks
by: Yang, Yongyi, et al.
Published: (2021)

Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach
by: Ai, Xing, et al.
Published: (2022)

Robust Angular Synchronization via Directed Graph Neural Networks
by: He, Yixuan, et al.
Published: (2023)

Feature Learning Dynamics in Infinite-Depth Neural Networks
by: Yao, Zihan, et al.
Published: (2025)

Graph Attention Specialized Expert Fusion Model for Node Classification: Based on Cora and Pubmed Datasets
by: Ma, Zihang, et al.
Published: (2025)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
by: Huang, Kezhao, et al.
Published: (2023)

Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks
by: Wang, Runzhong, et al.
Published: (2024)

Molecule Generation for Drug Design: a Graph Learning Perspective
by: Yang, Nianzu, et al.
Published: (2022)

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective
by: Wang, Senmiao, et al.
Published: (2025)

On the Cone Effect in the Learning Dynamics
by: Zhou, Zhanpeng, et al.
Published: (2025)

PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling
by: Yang, Kai, et al.
Published: (2025)

Deep Neural Network Training as Random Effects: An Optimization-Inference Duality
by: Yao, Minhao, et al.
Published: (2026)

Refined Edge Usage of Graph Neural Networks for Edge Prediction
by: Jin, Jiarui, et al.
Published: (2022)

BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization
by: Zheng, Amber Yijia, et al.
Published: (2024)

How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks
by: Sharon, Yuval, et al.
Published: (2024)

Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing
by: Fesser, Lukas, et al.
Published: (2025)

GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention
by: Yan, Junchi, et al.
Published: (2024)

Rule Based Learning with Dynamic (Graph) Neural Networks
by: Seiffarth, Florian
Published: (2024)

Stealing Training Graphs from Graph Neural Networks
by: Lin, Minhua, et al.
Published: (2024)

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
by: Qin, Xiaohan, et al.
Published: (2025)

Towards Quantifying the Hessian Structure of Neural Networks
by: Dong, Zhaorui, et al.
Published: (2025)

Graph Neural Networks for Learning Equivariant Representations of Neural Networks
by: Kofinas, Miltiadis, et al.
Published: (2024)

Robust Graph Neural Networks for Stability Analysis in Dynamic Networks
by: Zhang, Xin, et al.
Published: (2024)

How Interpretable Are Interpretable Graph Neural Networks?
by: Chen, Yongqiang, et al.
Published: (2024)

On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
by: Su, Junwei, et al.
Published: (2025)

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
by: Huang, Zheng, et al.
Published: (2024)

Efficient and Effective Implicit Dynamic Graph Neural Network
by: Zhong, Yongjian, et al.
Published: (2024)

Learning Dynamics from Multicellular Graphs with Deep Neural Networks
by: Yang, Haiqian, et al.
Published: (2024)

DiffPuter: Empowering Diffusion Models for Missing Data Imputation
by: Zhang, Hengrui, et al.
Published: (2024)