Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Neuman, A. Martina, Wang, Rongrong, Xie, Yuying
Format:	Preprint
Published:	2022
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning from one graph: transductive learning guarantees via the geometry of small random worlds
by: Detering, Nils, et al.
Published: (2025)

Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning
by: Xie, Rongrong, et al.
Published: (2025)

Theoretical guarantees for neural estimators in parametric statistics
by: Rödder, Almut, et al.
Published: (2025)

An Information-Theoretic Analysis of Temporal GNNs
by: Farzaneh, Amirmohammad
Published: (2024)

Consistency of augmentation graph and network approximability in contrastive learning
by: Li, Chenghui, et al.
Published: (2025)

Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
by: Shirzadi, Mohammad, et al.
Published: (2025)

Theoretical guarantees in KL for Diffusion Flow Matching
by: Silveri, Marta Gentiloni, et al.
Published: (2024)

Transferability of Graph Neural Networks using Graphon and Sampling Theories
by: Neuman, A. Martina, et al.
Published: (2023)

How does over-squashing affect the power of GNNs?
by: Di Giovanni, Francesco, et al.
Published: (2023)

Theoretical guarantees on the best-of-n alignment policy
by: Beirami, Ahmad, et al.
Published: (2024)

FlexiDrop: Theoretical Insights and Practical Advances in Random Dropout Method on GNNs
by: Zhou, Zhiheng, et al.
Published: (2024)

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

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

Theoretical guarantees for change localization using conformal p-values
by: Bhattacharyya, Swapnaneel, et al.
Published: (2025)

ResQuNNs: Towards Enabling Deep Learning in Quantum Convolution Neural Networks
by: Kashif, Muhammad, et al.
Published: (2024)

Universal generalization guarantees for Wasserstein distributionally robust models
by: Le, Tam, et al.
Published: (2024)

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
by: Luo, Yuankai, et al.
Published: (2024)

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

Benchmarking Positional Encodings for GNNs and Graph Transformers
by: Grötschla, Florian, et al.
Published: (2024)

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
by: Kratsios, Anastasis, et al.
Published: (2026)

Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
by: Neuman, A. Martina, et al.
Published: (2024)

Balanced Multimodal Learning via Mutual Information
by: Xie, Rongrong, et al.
Published: (2025)

Theoretical guarantees for neural control variates in MCMC
by: Belomestny, Denis, et al.
Published: (2023)

Warped geometric information on the optimisation of Euclidean functions
by: Hartmann, Marcelo, et al.
Published: (2023)

Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy
by: Seo, Hyunjin, et al.
Published: (2024)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
by: Zhou, Junru, et al.
Published: (2025)

Universally Invariant Learning in Equivariant GNNs
by: Cen, Jiacheng, et al.
Published: (2025)

Generalizing GNNs with Tokenized Mixture of Experts
by: Guo, Xiaoguang, et al.
Published: (2026)

Polybasic Speculative Decoding Through a Theoretical Perspective
by: Wang, Ruilin, et al.
Published: (2025)

On the Scalability of GNNs for Molecular Graphs
by: Sypetkowski, Maciej, et al.
Published: (2024)

Weighted Euclidean Distance Matrices over Mixed Continuous and Categorical Inputs for Gaussian Process Models
by: Pu, Mingyu, et al.
Published: (2025)

A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
by: Xie, Shuo, et al.
Published: (2025)

A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs
by: Wang, Jiaqi, et al.
Published: (2025)

Simple GNNs with Low Rank Non-parametric Aggregators
by: Vinas, Luciano, et al.
Published: (2023)

Rethinking the Expressive Power of GNNs via Graph Biconnectivity
by: Zhang, Bohang, et al.
Published: (2023)

Prospects for quantum advantage in machine learning from the representability of functions
by: Masot-Llima, Sergi, et al.
Published: (2025)

Locality-Aware Graph-Rewiring in GNNs
by: Barbero, Federico, et al.
Published: (2023)

Are GNNs doomed by the topology of their input graph?
by: Aboussalah, Amine Mohamed, et al.
Published: (2025)

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

Chordless Structure: A Pathway to Simple and Expressive GNNs
by: Pan, Hongxu, et al.
Published: (2025)