Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Xin, Song, Dongjin, Wen, Qingsong, Du, Bo, Pan, Shirui
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2403.09953
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929278044602368
author Zheng, Xin
Song, Dongjin
Wen, Qingsong
Du, Bo
Pan, Shirui
author_facet Zheng, Xin
Song, Dongjin
Wen, Qingsong
Du, Bo
Pan, Shirui
contents Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution shifts, conventional model evaluation encounters limitations in calculating performance metrics (e.g., test error) and measuring graph data-level discrepancies, particularly when the training graph used for developing GNNs remains unobserved during test time. In this paper, we study a new research problem, online GNN evaluation, which aims to provide valuable insights into the well-trained GNNs's ability to effectively generalize to real-world unlabeled graphs under the test-time graph distribution shifts. Concretely, we develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models. Through a novel GNN re-training strategy with a parameter-free optimality criterion, the proposed LeBeD comprehensively integrates learning behavior discrepancies from both node prediction and structure reconstruction perspectives. This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation. Extensive experiments on real-world test graphs under diverse graph distribution shifts could verify the effectiveness of the proposed method, revealing its strong correlation with ground-truth test errors on various well-trained GNN models.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online GNN Evaluation Under Test-time Graph Distribution Shifts
Zheng, Xin
Song, Dongjin
Wen, Qingsong
Du, Bo
Pan, Shirui
Machine Learning
Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution shifts, conventional model evaluation encounters limitations in calculating performance metrics (e.g., test error) and measuring graph data-level discrepancies, particularly when the training graph used for developing GNNs remains unobserved during test time. In this paper, we study a new research problem, online GNN evaluation, which aims to provide valuable insights into the well-trained GNNs's ability to effectively generalize to real-world unlabeled graphs under the test-time graph distribution shifts. Concretely, we develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models. Through a novel GNN re-training strategy with a parameter-free optimality criterion, the proposed LeBeD comprehensively integrates learning behavior discrepancies from both node prediction and structure reconstruction perspectives. This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation. Extensive experiments on real-world test graphs under diverse graph distribution shifts could verify the effectiveness of the proposed method, revealing its strong correlation with ground-truth test errors on various well-trained GNN models.
title Online GNN Evaluation Under Test-time Graph Distribution Shifts
topic Machine Learning
url https://arxiv.org/abs/2403.09953