发表机构
University of Ulm; University of Essex（乌尔姆大学; 埃塞克斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Chimaera提出图专家混合架构，整合多种图基础模型与线性GNN，扩展至多任务，实验证明其跨任务和数据集迁移的有效性。
AI 中文摘要
为图设计基础模型因图的不规则结构以及嵌入的不同规模和特性而具有挑战性。Chimaera将专家混合与图基础模型（GFM）相结合。它整合了不同的GFM架构，如图提示和线性GNN模型。使用大型语言模型生成嵌入，专家可以按照不同策略、GFM、嵌入等进行训练和组合。此外，Chimaera扩展了现有的线性GNN，除节点级任务外，还支持链接级和图级任务。使用六个基准文本属性图数据集，对节点、链接和图分类任务进行了同任务和跨任务实验的实证分析。实验证明了Chimaera的有效性及其跨任务和数据集迁移的能力。进一步的见解包括：需要使用大型和小型语言模型为专家生成嵌入，简单但有效的线性GNN具有强大的跨任务可迁移性，并且仅使用少量样本即可提供强结果。
英文摘要
Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embeddings. Chimaera integrates mixture-of-experts with graph foundation models (GFM). It integrates different GFM architectures, such as graph prompts and linear GNN models. Large language models are used to generate embeddings, and experts can be trained and combined following different strategies, GFMs, embeddings, etc. Furthermore, Chimaera extends existing linear GNNs to support link-level and graph-level tasks in addition to node-level tasks. Empirical analyses are performed on same-task and cross-task experiments with node, link, and graph classification tasks using six benchmark text-attributed graph datasets. The experiments demonstrate the effectiveness of Chimaera and its capabilities for transfer across tasks and datasets. Further insights include the need to use both large and small language models to generate embeddings for the experts, a strong cross-task transferability of simple but effective linear GNNs, and using few samples only to provide strong results.
CommentsAccepted at WI-IAT 2026
