GegenbauerNet: Finding the Optimal Compromise in the GNN Flexibility-Stability Trade-off

• URL: http://arxiv.org/abs/2511.13730v1
• Date: Tue, 04 Nov 2025 19:39:29 GMT
• Title: GegenbauerNet: Finding the Optimal Compromise in the GNN Flexibility-Stability Trade-off
• Authors: Huseyin Goksu,
• Abstract summary: Spectral Graph Neural Networks (GNNs) operating in the canonical [-1, 1] domain face a fundamental Flexibility-Stability Trade-off.<n>We propose textbfGegenbauerNet, a novel GNN filter based on the Gegenbauers symmetry.<n>We demonstrate that GegenbauerNet achieves superior performance in the key local filtering regime.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spectral Graph Neural Networks (GNNs) operating in the canonical [-1, 1] domain (like ChebyNet and its adaptive generalization, L-JacobiNet) face a fundamental Flexibility-Stability Trade-off. Our previous work revealed a critical puzzle: the 2-parameter adaptive L-JacobiNet often suffered from high variance and was surprisingly outperformed by the 0-parameter, stabilized-static S-JacobiNet. This suggested that stabilization was more critical than adaptation in this domain. In this paper, we propose \textbf{GegenbauerNet}, a novel GNN filter based on the Gegenbauer polynomials, to find the Optimal Compromise in this trade-off. By enforcing symmetry (alpha=beta) but allowing a single shape parameter (lambda) to be learned, GegenbauerNet limits flexibility (variance) while escaping the fixed bias of S-JacobiNet. We demonstrate that GegenbauerNet (1-parameter) achieves superior performance in the key local filtering regime (K=2 on heterophilic graphs) where overfitting is minimal, validating the hypothesis that a controlled, symmetric degree of freedom is optimal. Furthermore, our comprehensive K-ablation study across homophilic and heterophilic graphs, using 7 diverse datasets, clarifies the domain's behavior: the fully adaptive L-JacobiNet maintains the highest performance on high-K filtering tasks, showing the value of maximum flexibility when regularization is managed. This study provides crucial design principles for GNN developers, showing that in the [-1, 1] spectral domain, the optimal filter depends critically on the target locality (K) and the acceptable level of design bias.

Related papers

• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• HybSpecNet: A Critical Analysis of Architectural Instability in Hybrid-Domain Spectral GNNs [0.0]
  Spectral Graph Neural Networks offer a principled approach to graph filtering.<n>They face a fundamental "Stability-vs.Adaptivity" trade-off.<n>We propose a hybrid-domain GNN, HybSpecNet, which combines a stable ChebyNet branch with an adaptive KrawtchoukNet branch.
  arXiv  Detail & Related papers  (2025-11-20T06:47:44Z)
• L-JacobiNet and S-JacobiNet: An Analysis of Adaptive Generalization, Stabilization, and Spectral Domain Trade-offs in GNNs [0.0]
  Spectral GNNs, like ChebyNet, are limited by heterophily and over-smoothing due to their static, low-pass filter design.<n>This work investigates the "Adaptive Orthogonal Polynomial Filter" (AOPF) class as a solution.<n>We introduce two models operating in the [-1, 1] domain: 1) L-JacobiNet, the adaptive generalization of ChebyNet with learnable alpha, beta shape parameters, and 2) S-JacobiNet, a novel baseline representing a LayerNorm-stabilized static ChebyNet
  arXiv  Detail & Related papers  (2025-11-20T06:17:02Z)
• KrawtchoukNet: A Unified GNN Solution for Heterophily and Over-smoothing with Adaptive Bounded Polynomials [0.0]
  Spectral Graph Networks (GNNs) based on filters, such as ChebyNet, suffer from two critical limitations.<n>We propose KrawtchoukNet, a GNN filter based on the discrete Krawtchouks.<n>We show this adaptive nature allows KrawtchoukNet to achieve SOTA performance on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-11-19T10:47:15Z)
• Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization [66.08522228989634]
  We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV)<n>This is achieved by adopting a lifted perspective through mean-field Langevin dynamics (MFLD)
  arXiv  Detail & Related papers  (2025-11-18T17:51:17Z)
• DualLaguerreNet: A Decoupled Spectral Filter GNN and the Uncovering of the Flexibility-Stability Trade-off [0.0]
  Graph Networks (GNNs) based on spectral filters, such as the Adaptive Orthogonal Polynomial Filter (AOPF) class (e.g., LaguerreNet) have shown promise in unifying the solutions for heterophily and over-smoothing.<n>These single-filter models suffer from a "compromise" problem, as their single adaptive parameter (e.g., alpha) must learn a suboptimal, averaged response across the entire graph spectrum.<n>We propose DualLaguerreNet, a novel GNN architecture that solves this by introducing "Decoupled Spectral Flexibility"
  arXiv  Detail & Related papers  (2025-11-04T19:33:29Z)
• Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach [49.1574468325115]
  Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. We propose a novel approach to DNN regularization by framing the training process as a constrained optimization problem. We employ the Augmented Lagrangian (SAL) method to achieve a more flexible and efficient regularization mechanism.
  arXiv  Detail & Related papers  (2023-10-25T13:55:35Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Provably tuning the ElasticNet across instances [53.0518090093538]
  We consider the problem of tuning the regularization parameters of Ridge regression, LASSO, and the ElasticNet across multiple problem instances. Our results are the first general learning-theoretic guarantees for this important class of problems.
  arXiv  Detail & Related papers  (2022-07-20T21:22:40Z)
• Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians [5.33024001730262]
  Self-Tuning Networks (STNs) have recently gained traction due to their ability to amortize the optimization of the inner objective. We propose the $Delta$-STN, an improved hypernetwork architecture which stabilizes training.
  arXiv  Detail & Related papers  (2020-10-26T12:12:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.