聚合以适配：面向多源无源图领域自适应的节点中心聚合
Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation
AI总结：
本文针对多源无源无监督图领域自适应问题，提出节点级聚合模型 GraphATA，通过根据节点局部上下文动态聚合多个源预训练模型的权重矩阵，在无需访问源图数据的情况下实现图结构上的动态适配，并在多个数据集上超越现有方法。
摘要：
无监督图领域自适应（UGDA）专注于在领域差异下将知识从带标签的源图迁移到无标签的目标图。现有的大多数 UGDA 方法被设计用于从单一源领域适配信息，无法有效利用来自多个源领域的互补知识。此外，它们假设带标签的源图在整个训练过程中都可访问，但由于隐私、法规和存储方面的考虑，这一假设可能不切实际。在本文中，我们研究了多源无源无监督图领域自适应，即在不利用带标签的源图、仅依赖源预训练模型的情况下，将知识从多个源领域适配到无标签的目标领域。与以往在模型层面聚合预测的多源领域自适应方法不同，我们提出了一种名为 GraphATA 的新模型，它在节点粒度上进行适配。具体来说，我们通过根据每个节点的局部上下文自动聚合来自多个源模型的权重矩阵，为每个节点参数化其自身的图卷积矩阵，从而实现对图结构数据的动态适配。我们还展示了 GraphATA 泛化到以模型为中心和以层为中心的方法的能力。在多个公开数据集上的综合实验表明，我们的 GraphATA 能够以不同的增益持续超越近期最先进的基线方法。
英文摘要：
Unsupervised graph domain adaptation (UGDA) focuses on transferring knowledge from labeled source graph to unlabeled target graph under domain discrepancies. Most existing UGDA methods are designed to adapt information from a single source domain, which cannot effectively exploit the complementary knowledge from multiple source domains. Furthermore, their assumptions that the labeled source graphs are accessible throughout the training procedure might not be practical due to privacy, regulation, and storage concerns. In this paper, we investigate multi-source-free unsupervised graph domain adaptation, i.e., adapting knowledge from multiple source domains to an unlabeled target domain without utilizing labeled source graphs but relying solely on source pre-trained models. Unlike previous multi-source domain adaptation approaches that aggregate predictions at model level, we introduce a novel model named GraphATA which conducts adaptation at node granularity. Specifically, we parameterize each node with its own graph convolutional matrix by automatically aggregating weight matrices from multiple source models according to its local context, thus realizing dynamic adaptation over graph structured data. We also demonstrate the capability of GraphATA to generalize to both model-centric and layer-centric methods. Comprehensive experiments on various public datasets show that our GraphATA can consistently surpass recent state-of-the-art baselines with different gains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
