On the Prediction Instability of Graph Neural Networks

• URL: http://arxiv.org/abs/2205.10070v1
• Date: Fri, 20 May 2022 10:32:59 GMT
• Title: On the Prediction Instability of Graph Neural Networks
• Authors: Max Klabunde, Florian Lemmerich
• Abstract summary: Instability of trained models can affect reliability, reliability, and trust in machine learning systems. We systematically assess the prediction instability of node classification with state-of-the-art Graph Neural Networks (GNNs) We find that up to one third of the incorrectly classified nodes differ across algorithm runs.
• Score: 2.3605348648054463
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instability of trained models, i.e., the dependence of individual node predictions on random factors, can affect reproducibility, reliability, and trust in machine learning systems. In this paper, we systematically assess the prediction instability of node classification with state-of-the-art Graph Neural Networks (GNNs). With our experiments, we establish that multiple instantiations of popular GNN models trained on the same data with the same model hyperparameters result in almost identical aggregated performance but display substantial disagreement in the predictions for individual nodes. We find that up to one third of the incorrectly classified nodes differ across algorithm runs. We identify correlations between hyperparameters, node properties, and the size of the training set with the stability of predictions. In general, maximizing model performance implicitly also reduces model instability.

Related papers

• Generalization of Graph Neural Networks is Robust to Model Mismatch [84.01980526069075]
  Graph neural networks (GNNs) have demonstrated their effectiveness in various tasks supported by their generalization capabilities. In this paper, we examine GNNs that operate on geometric graphs generated from manifold models. Our analysis reveals the robustness of the GNN generalization in the presence of such model mismatch.
  arXiv  Detail & Related papers  (2024-08-25T16:00:44Z)
• Conditional Shift-Robust Conformal Prediction for Graph Neural Network [0.0]
  Graph Neural Networks (GNNs) have emerged as potent tools for predicting outcomes in graph-structured data. Despite their efficacy, GNNs have limited ability to provide robust uncertainty estimates. We propose Conditional Shift Robust (CondSR) conformal prediction for GNNs.
  arXiv  Detail & Related papers  (2024-05-20T11:47:31Z)
• Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks [4.213427823201119]
  Models with similar performances exhibit significant disagreement in the predictions of individual samples, referred to as prediction churn. We propose a novel metric called Influence Difference (ID) to quantify the variation in reasons used by nodes across models. We also consider the differences between nodes with a stable and an unstable prediction, positing that both equally utilize different reasons. As an efficient approximation, we introduce DropDistillation (DD) that matches the output for a graph perturbed by edge deletions.
  arXiv  Detail & Related papers  (2023-10-02T07:37:28Z)
• Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks [5.8490454659691355]
  We propose a new measure of closeness between classification models based on the output of the network before thresholding. Our measure is based on a robust hypothesis-testing framework and can be adapted to other quantities derived from trained models.
  arXiv  Detail & Related papers  (2023-10-01T01:44:35Z)
• Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction [51.82628081279621]
  Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
  arXiv  Detail & Related papers  (2023-09-02T01:27:53Z)
• Satellite Anomaly Detection Using Variance Based Genetic Ensemble of Neural Networks [7.848121055546167]
  We use an efficient ensemble of the predictions from multiple Recurrent Neural Networks (RNNs) For prediction, each RNN is guided by a Genetic Algorithm (GA) which constructs the optimal structure for each RNN model. This paper uses the Monte Carlo (MC) dropout as an approximation version of BNNs.
  arXiv  Detail & Related papers  (2023-02-10T22:09:00Z)
• How to Combine Variational Bayesian Networks in Federated Learning [0.0]
  Federated learning enables multiple data centers to train a central model collaboratively without exposing any confidential data. deterministic models are capable of performing high prediction accuracy, their lack of calibration and capability to quantify uncertainty is problematic for safety-critical applications. We study the effects of various aggregation schemes for variational Bayesian neural networks.
  arXiv  Detail & Related papers  (2022-06-22T07:53:12Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Discovering Invariant Rationales for Graph Neural Networks [104.61908788639052]
  Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features. We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
  arXiv  Detail & Related papers  (2022-01-30T16:43:40Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.