Imagen de Portada

Homophily modulates double descent generalization in graph convolution networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Cheng, Pan, Liming, Hu, Hong, Dokmanić, Ivan
Formato:	Preprint
Publicado:	2022
Materias:	Machine Learning Disordered Systems and Neural Networks
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Spring-block theory of feature learning in deep neural networks
por: Shi, Cheng, et al.
Publicado: (2024)

Asymptotic generalization error of a single-layer graph convolutional network
por: Duranthon, O., et al.
Publicado: (2024)

Injectivity of ReLU networks: perspectives from statistical physics
por: Maillard, Antoine, et al.
Publicado: (2023)

Training neural networks with structured noise improves classification and generalization
por: Benedetti, Marco, et al.
Publicado: (2023)

Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model
por: Duranthon, O., et al.
Publicado: (2025)

What can we learn from quantum convolutional neural networks?
por: Umeano, Chukwudubem, et al.
Publicado: (2023)

Pruning-induced phases in fully-connected neural networks: the eumentia, the dementia, and the amentia
por: Pan, Haining, et al.
Publicado: (2026)

Emergent weight morphologies in deep neural networks
por: de Jong, Pascal, et al.
Publicado: (2025)

High-dimensional learning of narrow neural networks
por: Cui, Hugo
Publicado: (2024)

A universal approximation theorem for nonlinear resistive networks
por: Scellier, Benjamin, et al.
Publicado: (2023)

Supervised and Unsupervised protocols for hetero-associative neural networks
por: Alessandrelli, Andrea, et al.
Publicado: (2025)

Deep neural networks from the perspective of ergodic theory
por: Zhang, Fan
Publicado: (2023)

Computing frustration and near-monotonicity in deep neural networks
por: Wendin, Joel, et al.
Publicado: (2025)

Finite-time Lyapunov exponents of deep neural networks
por: Storm, L., et al.
Publicado: (2023)

To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets
por: Doshi, Darshil, et al.
Publicado: (2023)

Self-attention as an attractor network: transient memories without backpropagation
por: D'Amico, Francesco, et al.
Publicado: (2024)

How does training shape the Riemannian geometry of neural network representations?
por: Zavatone-Veth, Jacob A., et al.
Publicado: (2023)

Boundary between noise and information applied to filtering neural network weight matrices
por: Staats, Max, et al.
Publicado: (2022)

Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks
por: Park, Chanju, et al.
Publicado: (2025)

Asymptotics of feature learning in two-layer networks after one gradient-step
por: Cui, Hugo, et al.
Publicado: (2024)

Adaptive kernel predictors from feature-learning infinite limits of neural networks
por: Lauditi, Clarissa, et al.
Publicado: (2025)

Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
por: Agliari, Elena, et al.
Publicado: (2023)

Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval
por: Maillard, Antoine, et al.
Publicado: (2026)

Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
por: Baldassi, Carlo, et al.
Publicado: (2019)

Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
por: D'Amico, Francesco, et al.
Publicado: (2025)

Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions
por: Nishiyama, Sota, et al.
Publicado: (2024)

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
por: Huang, Jie, et al.
Publicado: (2026)

Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds
por: Troiani, Emanuele, et al.
Publicado: (2025)

Autoregressive model path dependence near Ising criticality
por: Teoh, Yi Hong, et al.
Publicado: (2024)

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization
por: Mendes, Vicente Conde, et al.
Publicado: (2026)

Representing Born effective charges with equivariant graph convolutional neural networks
por: Kutana, Alex, et al.
Publicado: (2024)

Random Features Hopfield Networks generalize retrieval to previously unseen examples
por: Kalaj, Silvio, et al.
Publicado: (2024)

How noise affects memory in linear recurrent networks
por: Guan, JingChuan, et al.
Publicado: (2024)

Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks
por: Annesi, Brandon L., et al.
Publicado: (2024)

Bias-inducing geometries: an exactly solvable data model with fairness implications
por: Mannelli, Stefano Sarao, et al.
Publicado: (2022)

Dataset-Free Weight-Initialization on Restricted Boltzmann Machine
por: Yasuda, Muneki, et al.
Publicado: (2024)

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
por: Xu, Yizhou, et al.
Publicado: (2025)

Specialization of softmax attention heads: insights from the high-dimensional single-location model
por: Sagitova, M., et al.
Publicado: (2026)

Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
por: Wang, Shanshan, et al.
Publicado: (2025)

No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
por: Ruben, Benjamin S., et al.
Publicado: (2024)