Semi-supervised Node Importance Estimation with Informative Distribution Modeling for Uncertainty Regularization

2025-03-26

AI Summary

Addressing the challenge of sparse node importance annotations in real-world heterogeneous graphs, this paper proposes the first semi-supervised learning framework for node importance estimation. Our method jointly models node importance and its predictive uncertainty via a learnable importance distribution; introduces an uncertainty-aware heteroscedastic regularization mechanism to mitigate bias from low-quality unlabeled data; and integrates a deep encoder-decoder architecture, distributional representation learning, and a pseudo-labeling strategy to achieve robust semi-supervised heteroscedastic regression. Extensive experiments on three real-world heterogeneous graph datasets demonstrate that our approach significantly outperforms both fully supervised and weakly supervised baselines. The source code is publicly available.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Reasoning under Uncertainty: Graphical Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Node importance estimation, a classical problem in network analysis, underpins various web applications. Previous methods either exploit intrinsic topological characteristics, e.g., graph centrality, or leverage additional information, e.g., data heterogeneity, for node feature enhancement. However, these methods follow the supervised learning setting, overlooking the fact that ground-truth node-importance data are usually partially labeled in practice. In this work, we propose the first semi-supervised node importance estimation framework, i.e., EASING, to improve learning quality for unlabeled data in heterogeneous graphs. Different from previous approaches, EASING explicitly captures uncertainty to reflect the confidence of model predictions. To jointly estimate the importance values and uncertainties, EASING incorporates DJE, a deep encoder-decoder neural architecture. DJE introduces distribution modeling for graph nodes, where the distribution representations derive both importance and uncertainty estimates. Additionally, DJE facilitates effective pseudo-label generation for the unlabeled data to enrich the training samples. Based on labeled and pseudo-labeled data, EASING develops effective semi-supervised heteroscedastic learning with varying node uncertainty regularization. Extensive experiments on three real-world datasets highlight the superior performance of EASING compared to competing methods. Codes are available via https://github.com/yankai-chen/EASING.

Problem

• Estimates node importance in partially labeled networks
• Models uncertainty to improve prediction confidence
• Enhances learning with pseudo-labels for unlabeled data

Innovation

• Semi-supervised framework for node importance estimation
• Uncertainty regularization via distribution modeling
• Deep encoder-decoder architecture for joint estimation