Selective transfer boosts graph learning by judging data trustworthiness
SUCRe: Selective Uncertainty-Aware Contrastive Representation for Graph Transfer Learning
Graphics
Summary
Sometimes, computers learn from connected data called graphs, but when using one graph to help with another, some parts might not fit well and cause mistakes. The authors created a method that guesses which parts of the data are more reliable to share between graphs. Their technique combines checking data uncertainty and structure to decide what to transfer. They also pick better examples to compare during learning, making the process faster and more accurate.
What this means in practice
- •For data engineers: Improve machine learning on connected data with few labels by selectively transferring reliable knowledge between graphs to reduce errors and speed up training.
- •For network analysts: Enhance analysis of complex network data by adapting graph models selectively based on structural reliability to better identify important patterns.
Authors
Mingcan Wang, Junchang Xin, Zhongming Yao, Bing Tian Dai, Kaifu Long, Zhiqiong Wang
Abstract
Graph transfer learning (GTL) provides a promising paradigm for adapting knowledge from source graphs with sufficient labels to label-scarce target graphs. However, existing approaches often assume that transferred knowledge is uniformly reliable, ignoring the different transferability of samples caused by structural and distribution shifts across graphs. This limitation leads to negative transfer and unnecessary computational overhead. In this work, we propose SUCRe, a selective uncertainty-aware contrastive representation method for GTL. The key idea is to selectively adapt and transfer graph knowledge according to its estimated reliability. Specifically, we introduce structure-aware entropy-based matching discrepancy, which jointly models feature uncertainty and structural coherence to ensure accurate feature adaptation between graphs. Moreover, we develop a domain-aware semi-hard negative sampling strategy that constructs informative contrastive sets by filtering unreliable cross-domain relationships, reducing computational redundancy while enhancing representation discrimination. Extensive experiments on graph transfer benchmarks demonstrate that SUCRe achieves competitive performance with improved efficiency.