Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learning

2026-09-12

AI Summary

为了解决图域适应中数据效率低下的问题，本文提出DEAG框架，通过可靠性感知原型学习方法提高目标图的预测准确性。

Abstract

Agentic learning systems are often required to adapt after deployment by observing new data and reusing prior knowledge under limited supervision or feedback. For graph-structured prediction, Graph Domain Adaptation (GDA) naturally instantiates this setting by transferring knowledge from labeled source graphs to unlabeled target graphs under distribution shifts. However, most GDA methods assume sufficient labeled source graphs, which becomes restrictive in data-efficient agentic settings where only limited source evidence can be retained. Under such constraints, source semantics become unreliable, leading to unstable source anchoring, uncertain target association, and fragile targetmarginal calibration. To address these challenges, we propose DEAG, a reliability-aware prototype learning framework for data-efficient agentic GDA. DEAG estimates class reliability from retained source support and embedding compactness, and constructs stable reusable source anchors by blending empirical prototypes with classifier directions. Guided by these anchors, DEAG performs prototype-aware soft target association and aligns confidence-weighted target centers with source semantics. A source-prior regularizer further sharpens target predictions while keeping the target marginal consistent with retained source evidence. Experiments on graph benchmarks with diverse domain shifts show that DEAG improves average adaptation performance over competitive GDA baselines under the same source-data budget.

Problem

• Graph Domain Adaptation
• data-efficient
• reliability
• prototype learning
• domain shifts

Innovation

• reliability-aware prototype learning
• data-efficient agentic GDA
• stable reusable source anchors
• prototype-aware soft target association
• source-prior regularizer