Cover Image

Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ayday, Nil, Sabanayagam, Mahalakshmi, Ghoshdastidar, Debarghya
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks
by: Ayday, Nil, et al.
Published: (2026)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
by: Sabanayagam, Mahalakshmi, et al.
Published: (2024)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
by: Gosch, Lukas, et al.
Published: (2024)

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
by: Mohgaonkar, Ajinkya, et al.
Published: (2026)

Robustness Certificates for Neural Networks against Adversarial Attacks
by: Taheri, Sara, et al.
Published: (2025)

Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
by: Ayday, Nil, et al.
Published: (2026)

Robust Feature Inference: A Test-time Defense Strategy using Spectral Projections
by: Singh, Anurag, et al.
Published: (2023)

Generalization Certificates for Adversarially Robust Bayesian Linear Regression
by: Sabanayagam, Mahalakshmi, et al.
Published: (2025)

Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations
by: Crăciun, Alexandru, et al.
Published: (2025)

Infinite Width Limits of Self Supervised Neural Networks
by: Fleissner, Maximilian, et al.
Published: (2024)

Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters
by: Han, Yaomengxi, et al.
Published: (2025)

On the Convergence of Gradient Descent for Large Learning Rates
by: Crăciun, Alexandru, et al.
Published: (2024)

Tight PAC-Bayesian Risk Certificates for Contrastive Learning
by: Van Elst, Anna, et al.
Published: (2024)

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
by: Anil, Gautham Govind, et al.
Published: (2024)

Cluster Specific Representation Learning
by: Sabanayagam, Mahalakshmi, et al.
Published: (2024)

Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders
by: Ham, Jonghyun, et al.
Published: (2025)

Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization
by: Esser, Pascal, et al.
Published: (2025)

A Probabilistic Model for Non-Contrastive Learning
by: Fleissner, Maximilian, et al.
Published: (2025)

Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit
by: Eppert, Martin, et al.
Published: (2025)

Explainable Clustering Beyond Worst-Case Guarantees
by: Fleissner, Maximilian, et al.
Published: (2024)

A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
by: Feigin, Shlomo Libo, et al.
Published: (2024)

Explaining Kernel Clustering via Decision Trees
by: Fleissner, Maximilian, et al.
Published: (2024)

Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
by: Zarvandi, Maedeh, et al.
Published: (2025)

Nonparametric Kernel Clustering with Bandit Feedback
by: Thuot, Victor, et al.
Published: (2026)

The Quantization Benefits of Residual-Free Transformers
by: Ji, Yiping, et al.
Published: (2026)

Less is More: Benchmarking LLM Based Recommendation Agents
by: Chauhan, Kargi, et al.
Published: (2026)

Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
by: Qharabagh, Muhammad Fetrat, et al.
Published: (2026)

Skew-Probabilistic Neural Networks for Learning from Imbalanced Data
by: Naik, Shraddha M., et al.
Published: (2023)

Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients
by: Berger, Armin, et al.
Published: (2025)

Cross-Attention Graph Neural Networks for Inferring Gene Regulatory Networks with Skewed Degree Distribution
by: Xiong, Jiaqi, et al.
Published: (2024)

Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
by: Lee, Hunjae
Published: (2025)

Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
by: Yuan, Hanyang, et al.
Published: (2024)

Generalisable Agents for Neural Network Optimisation
by: Tessera, Kale-ab, et al.
Published: (2023)

Power Failure Cascade Prediction using Graph Neural Networks
by: Chadaga, Sathwik, et al.
Published: (2024)

Privacy-Preserving Optimal Parameter Selection for Collaborative Clustering
by: Ghasemian, Maryam, et al.
Published: (2024)

Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model
by: Wang, Xinjue, et al.
Published: (2022)

Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
by: Muschalik, Maximilian, et al.
Published: (2025)

On Rank-Dependent Generalisation Error Bounds for Transformers
by: Truong, Lan V.
Published: (2024)

Graph Neural Networks for Heart Failure Prediction on an EHR-Based Patient Similarity Graph
by: Boll, Heloisa Oss, et al.
Published: (2024)

Generalization Error of Graph Neural Networks in the Mean-field Regime
by: Aminian, Gholamali, et al.
Published: (2024)