消息传递在图上的上下文学习中以更少资源实现更强性能

中文摘要 AI 辅助

使用图神经网络（GNN）实现强性能通常需要对每个数据集进行训练和超参数调优，导致重复的成本和精力消耗。图上下文学习（ICL）通过使用单个预训练模型直接从带标签的上下文节点预测未知节点标签，避免了这一问题。然而，现有方法依赖节点间的密集注意力，随着图规模增大，推理成本日益昂贵。在本工作中，我们提出Ephris，一种基于稀疏消息传递的新型图上下文学习器，其复杂度随节点特征条目数和图边数线性增长。Ephris完全在由结构因果模型生成的合成图上预训练，这些图具有多样的图结构和关系动态，使模型暴露于拓扑、特征和标签之间的多种依赖关系。我们在51个节点分类数据集上，针对15个经过广泛调优的GNN和现有图ICL方法，在高标签和低标签的训练/验证/测试划分下进行评估。在两种设置下，Ephris在所有四个聚合指标（Elo、可改进性、平均排名和准确率）上均排名第一。其推理成本与一次性训练单个GNN相当，同时比之前的图ICL模型快10倍以上。这些结果共同推进了性能-运行时的帕累托前沿，表明强大的图ICL不需要密集注意力。代码和模型权重可在该https URL获取。

英文摘要

Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in-context learning (ICL) avoids this by using a single pretrained model to predict unknown node labels directly from labeled context nodes. Existing approaches, however, rely on dense attention across nodes, making inference increasingly expensive as graphs grow. In this work, we present Ephris, a new graph in-context learner built on sparse message passing, scaling linearly with the number of node-feature entries and graph edges. Ephris is pretrained entirely on synthetic graphs generated from structural causal models with diverse graph structures and relational dynamics, exposing the model to varied dependencies among topology, features, and labels. We evaluate Ephris on 51 node-classification datasets against 15 extensively tuned GNNs and existing graph ICL methods under both high- and low-label train/validation/test splits. Across both settings, Ephris ranks first on all four aggregate measures: Elo, improvability, average rank, and accuracy. Its inference cost remains comparable to training a single GNN once, while being over 10 times faster than previous graph ICL models. Together, these results advance the performance-runtime Pareto frontier, demonstrating that strong graph ICL does not require dense attention. Code and model weights are available at https://github.com/nums-ai/ephris.

发表机构

• Nums AI
• KAIST（韩国科学技术院）
• Seoul National University（首尔国立大学）

机构由 AI 辅助整理，请以论文原文为准。