Image de couverture de livre

Theoretical guarantees for the advantage of GNNs over NNs in generalizing bandlimited functions on Euclidean cubes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Neuman, A. Martina, Wang, Rongrong, Xie, Yuying
Format:	Preprint
Publié:	2022
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

Learning from one graph: transductive learning guarantees via the geometry of small random worlds
par: Detering, Nils, et autres
Publié: (2025)

Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning
par: Xie, Rongrong, et autres
Publié: (2025)

Theoretical guarantees for neural estimators in parametric statistics
par: Rödder, Almut, et autres
Publié: (2025)

An Information-Theoretic Analysis of Temporal GNNs
par: Farzaneh, Amirmohammad
Publié: (2024)

Consistency of augmentation graph and network approximability in contrastive learning
par: Li, Chenghui, et autres
Publié: (2025)

Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
par: Shirzadi, Mohammad, et autres
Publié: (2025)

Theoretical guarantees in KL for Diffusion Flow Matching
par: Silveri, Marta Gentiloni, et autres
Publié: (2024)

Transferability of Graph Neural Networks using Graphon and Sampling Theories
par: Neuman, A. Martina, et autres
Publié: (2023)

How does over-squashing affect the power of GNNs?
par: Di Giovanni, Francesco, et autres
Publié: (2023)

Theoretical guarantees on the best-of-n alignment policy
par: Beirami, Ahmad, et autres
Publié: (2024)

FlexiDrop: Theoretical Insights and Practical Advances in Random Dropout Method on GNNs
par: Zhou, Zhiheng, et autres
Publié: (2024)

v-PuNNs: van der Put Neural Networks for Transparent Ultrametric Representation Learning
par: N'guessan, Gnankan Landry Regis
Publié: (2025)

A Boolean Function-Theoretic Framework for Expressivity in GNNs with Applications to Fair Graph Mining
par: Pal, Manjish
Publié: (2026)

Theoretical guarantees for change localization using conformal p-values
par: Bhattacharyya, Swapnaneel, et autres
Publié: (2025)

ResQuNNs: Towards Enabling Deep Learning in Quantum Convolution Neural Networks
par: Kashif, Muhammad, et autres
Publié: (2024)

Universal generalization guarantees for Wasserstein distributionally robust models
par: Le, Tam, et autres
Publié: (2024)

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
par: Luo, Yuankai, et autres
Publié: (2024)

Reconstruction of frequency-localized functions from pointwise samples via least squares and deep learning
par: Neuman, A. Martina, et autres
Publié: (2025)

Benchmarking Positional Encodings for GNNs and Graph Transformers
par: Grötschla, Florian, et autres
Publié: (2024)

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
par: Kratsios, Anastasis, et autres
Publié: (2026)

Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
par: Neuman, A. Martina, et autres
Publié: (2024)

Balanced Multimodal Learning via Mutual Information
par: Xie, Rongrong, et autres
Publié: (2025)

Theoretical guarantees for neural control variates in MCMC
par: Belomestny, Denis, et autres
Publié: (2023)

Warped geometric information on the optimisation of Euclidean functions
par: Hartmann, Marcelo, et autres
Publié: (2023)

Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy
par: Seo, Hyunjin, et autres
Publié: (2024)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
par: Zhou, Junru, et autres
Publié: (2025)

Universally Invariant Learning in Equivariant GNNs
par: Cen, Jiacheng, et autres
Publié: (2025)

Generalizing GNNs with Tokenized Mixture of Experts
par: Guo, Xiaoguang, et autres
Publié: (2026)

Polybasic Speculative Decoding Through a Theoretical Perspective
par: Wang, Ruilin, et autres
Publié: (2025)

On the Scalability of GNNs for Molecular Graphs
par: Sypetkowski, Maciej, et autres
Publié: (2024)

Weighted Euclidean Distance Matrices over Mixed Continuous and Categorical Inputs for Gaussian Process Models
par: Pu, Mingyu, et autres
Publié: (2025)

A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
par: Xie, Shuo, et autres
Publié: (2025)

A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs
par: Wang, Jiaqi, et autres
Publié: (2025)

Simple GNNs with Low Rank Non-parametric Aggregators
par: Vinas, Luciano, et autres
Publié: (2023)

Rethinking the Expressive Power of GNNs via Graph Biconnectivity
par: Zhang, Bohang, et autres
Publié: (2023)

Prospects for quantum advantage in machine learning from the representability of functions
par: Masot-Llima, Sergi, et autres
Publié: (2025)

Locality-Aware Graph-Rewiring in GNNs
par: Barbero, Federico, et autres
Publié: (2023)

Are GNNs doomed by the topology of their input graph?
par: Aboussalah, Amine Mohamed, et autres
Publié: (2025)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
par: Huang, Weizhong, et autres
Publié: (2025)

Chordless Structure: A Pathway to Simple and Expressive GNNs
par: Pan, Hongxu, et autres
Publié: (2025)