发表机构
Mohamed bin Zayed University of Artificial Intelligence; Zhengzhou University; City University of Hong Kong（穆罕默德·本·扎耶德人工智能大学; 郑州大学; 香港城市大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对数据高效智能体图域自适应中源语义不可靠的问题，提出DEAG可靠性感知原型学习框架，通过可靠锚点与置信度对齐提升跨域适应性能。
AI 中文摘要
智能体学习系统通常需要在部署后通过观察新数据并在有限监督或反馈下重用先验知识来适应环境。对于图结构预测，图域自适应（GDA）通过在分布偏移下将知识从有标签的源图迁移到无标签的目标图，自然地实现了这一设置。然而，大多数GDA方法假设有充足的带标签源图，这在数据高效的智能体设置中变得受限，因为只能保留有限的源证据。在这种约束下，源语义变得不可靠，导致源锚定不稳定、目标关联不确定以及目标边缘校准脆弱。为解决这些挑战，我们提出了DEAG，一种用于数据高效智能体GDA的可靠性感知原型学习框架。DEAG从保留的源支持和嵌入紧凑性中估计类别可靠性，并通过混合经验原型与分类器方向来构建稳定可复用的源锚点。在这些锚点的引导下，DEAG执行原型感知的软目标关联，并将置信度加权的目标中心与源语义对齐。源先验正则化器进一步锐化目标预测，同时保持目标边缘与保留的源证据一致。在具有多样域偏移的图基准上的实验表明，在相同源数据预算下，DEAG相比竞争性GDA基线提高了平均适应性能。
英文摘要
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.
