Learn Beneficial Noise as Graph Augmentation

• URL: http://arxiv.org/abs/2505.19024v1
• Date: Sun, 25 May 2025 08:20:34 GMT
• Title: Learn Beneficial Noise as Graph Augmentation
• Authors: Siqi Huang, Yanchen Xu, Hongyuan Zhang, Xuelong Li,
• Abstract summary: We propose PiNGDA, where positive-incentive noise (pi-noise) scientifically analyzes the beneficial effect of noise under the information theory.<n>We prove that the standard GCL with pre-defined augmentations is equivalent to estimate the beneficial noise via the point estimation.<n>Since the generator learns how to produce beneficial perturbations on graph topology and node attributes, PiNGDA is more reliable compared with the existing methods.
• Score: 54.44813218411879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although graph contrastive learning (GCL) has been widely investigated, it is still a challenge to generate effective and stable graph augmentations. Existing methods often apply heuristic augmentation like random edge dropping, which may disrupt important graph structures and result in unstable GCL performance. In this paper, we propose Positive-incentive Noise driven Graph Data Augmentation (PiNGDA), where positive-incentive noise (pi-noise) scientifically analyzes the beneficial effect of noise under the information theory. To bridge the standard GCL and pi-noise framework, we design a Gaussian auxiliary variable to convert the loss function to information entropy. We prove that the standard GCL with pre-defined augmentations is equivalent to estimate the beneficial noise via the point estimation. Following our analysis, PiNGDA is derived from learning the beneficial noise on both topology and attributes through a trainable noise generator for graph augmentations, instead of the simple estimation. Since the generator learns how to produce beneficial perturbations on graph topology and node attributes, PiNGDA is more reliable compared with the existing methods. Extensive experimental results validate the effectiveness and stability of PiNGDA.

Related papers

• Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark [25.40550479788717]
  Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data.<n>We introduce BeGIN, a new benchmark that provides realistic graph datasets with various noise types.<n>By comprehensively evaluating noise-handling strategies, BeGIN provides insights into their effectiveness, efficiency, and key performance factors.
  arXiv  Detail & Related papers  (2025-06-14T12:14:15Z)
• Training Robust Graph Neural Networks by Modeling Noise Dependencies [28.1151026795484]
  In real-world applications, node features in graphs often contain noise from various sources, leading to significant performance degradation.<n>We introduce a more realistic noise scenario, dependency-aware noise on graphs (DANG), where noise in node features create a chain of noise dependencies that propagates to the graph structure and node labels.<n>We propose a novel robust GNN, DA-GNN, which captures the causal relationships among variables in the data generating process (DGP) of DANG using variational inference.
  arXiv  Detail & Related papers  (2025-02-27T01:30:13Z)
• SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples [44.315865532262876]
  Graph Contrastive Learning (GCL) excels at managing noise and fluctuations in input data, making it popular in various fields. Most existing GCL methods focus mainly on the time domain (low-frequency information) for node feature representations. We propose a novel spectral GCL framework without positive samples, named SpeGCL.
  arXiv  Detail & Related papers  (2024-10-14T10:39:38Z)
• RobGC: Towards Robust Graph Condensation [61.259453496191696]
  Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning.<n>However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands.<n>We propose graph condensation (GC) to generate an informative compact graph that enables efficient training of GNNs while retaining performance.
  arXiv  Detail & Related papers  (2024-06-19T04:14:57Z)
• Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning [71.9954600831939]
  Positive-Unlabeled (PU) learning is vital in many real-world scenarios, but its application to graph data remains under-explored. We unveil that a critical challenge for PU learning on graph lies on the edge heterophily, which directly violates the irreducibility assumption for Class-Prior Estimation. In response to this challenge, we introduce a new method, named Graph PU Learning with Label Propagation Loss (GPL)
  arXiv  Detail & Related papers  (2024-05-30T10:30:44Z)
• Combating Bilateral Edge Noise for Robust Link Prediction [56.43882298843564]
  We propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse. Two instantiations, RGIB-SSL and RGIB-REP, are explored to leverage the merits of different methodologies. Experiments on six datasets and three GNNs with diverse noisy scenarios verify the effectiveness of our RGIB instantiations.
  arXiv  Detail & Related papers  (2023-11-02T12:47:49Z)
• Per-Example Gradient Regularization Improves Learning Signals from Noisy Data [25.646054298195434]
  Empirical evidence suggests that gradient regularization technique can significantly enhance the robustness of deep learning models against noisy perturbations. We present a theoretical analysis that demonstrates its effectiveness in improving both test error and robustness against noise perturbations. Our analysis reveals that PEGR penalizes the variance of pattern learning, thus effectively suppressing the memorization of noises from the training data.
  arXiv  Detail & Related papers  (2023-03-31T10:08:23Z)
• Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution [112.3443939502313]
  We propose a unified graph signal sampling framework which enjoys the benefits of graph signal analysis and processing. The key idea is to transform each user's ratings on the items to a function (signal) on the vertices of an item-item graph. For the online setting, we develop a Bayesian extension, i.e., BGS-IMC which considers continuous random Gaussian noise in the graph Fourier domain.
  arXiv  Detail & Related papers  (2023-02-08T08:17:43Z)
• How Powerful is Implicit Denoising in Graph Neural Networks [33.01155523195073]
  We conduct a comprehensive theoretical study and analyze when and why the implicit denoising happens in GNNs. Our theoretical analysis suggests that the implicit denoising largely depends on the connectivity, the graph size, and GNN architectures. We derive a robust graph convolution, where the smoothness of the node representations and the implicit denoising effect can be enhanced.
  arXiv  Detail & Related papers  (2022-09-29T02:19:39Z)
• Oversquashing in GNNs through the lens of information contraction and graph expansion [6.8222473597904845]
  We present a framework for analyzing oversquashing based on information contraction. We propose a graph rewiring algorithm aimed at alleviating oversquashing.
  arXiv  Detail & Related papers  (2022-08-06T08:44:39Z)
• Shape Matters: Understanding the Implicit Bias of the Noise Covariance [76.54300276636982]
  Noise in gradient descent provides a crucial implicit regularization effect for training over parameterized models. We show that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not.
  arXiv  Detail & Related papers  (2020-06-15T18:31:02Z)

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.