Transfer Learning on Edge Connecting Probability Estimation under Graphon Model

2025-10-06

AI Summary

To address inaccurate connection probability estimation in Graphon models for small-scale networks, this paper proposes GTRANS—a transfer learning framework that leverages structural information from large-scale source graphs to improve estimation accuracy on target small graphs. GTRANS innovatively integrates neighborhood smoothing with Gromov–Wasserstein optimal transport to achieve cross-graph structural alignment and incorporates an adaptive debiasing mechanism to mitigate negative transfer, thereby ensuring estimation stability. Unlike conventional graph-based modeling approaches, GTRANS explicitly captures inter-graph heterogeneity and structural bias while preserving residual smoothing capability. Extensive experiments on synthetic data and multiple real-world network datasets demonstrate that GTRANS significantly outperforms baseline methods in link prediction and graph classification tasks, validating its effectiveness and generalizability for downstream applications.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Graphon models provide a flexible nonparametric framework for estimating latent connectivity probabilities in networks, enabling a range of downstream applications such as link prediction and data augmentation. However, accurate graphon estimation typically requires a large graph, whereas in practice, one often only observes a small-sized network. One approach to addressing this issue is to adopt a transfer learning framework, which aims to improve estimation in a small target graph by leveraging structural information from a larger, related source graph. In this paper, we propose a novel method, namely GTRANS, a transfer learning framework that integrates neighborhood smoothing and Gromov-Wasserstein optimal transport to align and transfer structural patterns between graphs. To prevent negative transfer, GTRANS includes an adaptive debiasing mechanism that identifies and corrects for target-specific deviations via residual smoothing. We provide theoretical guarantees on the stability of the estimated alignment matrix and demonstrate the effectiveness of GTRANS in improving the accuracy of target graph estimation through extensive synthetic and real data experiments. These improvements translate directly to enhanced performance in downstream applications, such as the graph classification task and the link prediction task.

Problem

• Estimating connectivity probabilities in small networks using transfer learning
• Aligning structural patterns between graphs via optimal transport
• Preventing negative transfer with adaptive debiasing mechanisms

Innovation

• Transfer learning framework for small graph estimation
• Neighborhood smoothing with Gromov-Wasserstein optimal transport
• Adaptive debiasing mechanism prevents negative transfer