Imagen de Portada

Visualization and Analysis of the Loss Landscape in Graph Neural Networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Moustafa, Samir, Kummer, Lorenz, Fetzel, Simon, Kriege, Nils M., Gansterer, Wilfried N.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
por: Kummer, Lorenz, et al.
Publicado: (2025)

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
por: Kummer, Lorenz, et al.
Publicado: (2023)

On the Relationship Between Robustness and Expressivity of Graph Neural Networks
por: Kummer, Lorenz, et al.
Publicado: (2025)

Efficient Mixed Precision Quantization in Graph Neural Networks
por: Moustafa, Samir, et al.
Publicado: (2025)

On the Two Sides of Redundancy in Graph Neural Networks
por: Bause, Franka, et al.
Publicado: (2023)

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
por: Kummer, Lorenz, et al.
Publicado: (2025)

XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction
por: Ehrlich, Anatol, et al.
Publicado: (2026)

Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints
por: Azizi, Niloofar, et al.
Publicado: (2024)

Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph
por: Roth, Andreas, et al.
Publicado: (2024)

Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
por: Xu, Yichu, et al.
Publicado: (2024)

Accelerating Graph Neural Networks with a Novel Matrix Compression Format
por: Alves, João N. F., et al.
Publicado: (2024)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
por: Bai, Zhiwei, et al.
Publicado: (2022)

Sensitivity Analysis On Loss Landscape
por: Faroz, Salman
Publicado: (2024)

A Unified Theory of Quantum Neural Network Loss Landscapes
por: Anschuetz, Eric R.
Publicado: (2024)

Loss Landscape Characterization of Neural Networks without Over-Parametrization
por: Islamov, Rustem, et al.
Publicado: (2024)

Paths and Ambient Spaces in Neural Loss Landscapes
por: Dold, Daniel, et al.
Publicado: (2025)

LossLens: Diagnostics for Machine Learning through Loss Landscape Visual Analytics
por: Xie, Tiankai, et al.
Publicado: (2024)

Visualizing Loss Functions as Topological Landscape Profiles
por: Geniesse, Caleb, et al.
Publicado: (2024)

Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
por: Wu, Frank Zhengqing, et al.
Publicado: (2024)

A Quasi-Wasserstein Loss for Learning Graph Neural Networks
por: Cheng, Minjie, et al.
Publicado: (2023)

Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks
por: Wong, Zhen Hao, et al.
Publicado: (2024)

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
por: Chen, Jiaqing, et al.
Publicado: (2026)

Graph Neural Networks for Source Detection: A Review and Benchmark Study
por: Sterchi, Martin, et al.
Publicado: (2025)

Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization
por: Abbas, Khushnood, et al.
Publicado: (2025)

Flat Channels to Infinity in Neural Loss Landscapes
por: Martinelli, Flavio, et al.
Publicado: (2025)

Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
por: Wang, Zhiyang, et al.
Publicado: (2024)

Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing
por: Baldi, Tommaso, et al.
Publicado: (2025)

Loss Patterns of Neural Networks
por: Skorokhodov, Ivan, et al.
Publicado: (2019)

Heterogeneous Graph Neural Networks with Loss-decrease-aware Curriculum Learning
por: Wang, Yili
Publicado: (2024)

Probabilistic Demand Forecasting with Graph Neural Networks
por: Kozodoi, Nikita, et al.
Publicado: (2024)

Finite Volume-Informed Neural Network Framework for 2D Shallow Water Equations: Rugged Loss Landscapes and the Importance of Data Guidance
por: Liu, Xiaofeng
Publicado: (2026)

Loss Spike in Training Neural Networks
por: Li, Xiaolong, et al.
Publicado: (2023)

There is a Singularity in the Loss Landscape
por: Lowell, Mark
Publicado: (2022)

Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks
por: Kim, Bum Jun, et al.
Publicado: (2026)

Hybrid-Quantum Neural Architecture Search for The Proximal Policy Optimization Algorithm
por: Zada, Moustafa
Publicado: (2025)

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
por: Bushnaq, Lucius, et al.
Publicado: (2024)

Spatio-Spectral Graph Neural Networks
por: Geisler, Simon, et al.
Publicado: (2024)

Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape
por: Karhadkar, Kedar, et al.
Publicado: (2023)

NeuralSurv: Deep Survival Analysis with Bayesian Uncertainty Quantification
por: Monod, Mélodie, et al.
Publicado: (2025)

Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
por: Liu, Jingyi, et al.
Publicado: (2026)