Foundation models have revolutionized the landscape of Deep Learning (DL), serving as a versatile platform which can be adapted to a wide range of downstream tasks. Despite their adaptability, applications of foundation models to downstream graph-based tasks have been limited, and there remains no convenient way to leverage large-scale non-graph pretrained models in graph-structured settings. In this work, we present a new framework which we term Foundation-Informed Message Passing (FIMP) to bridge the fields of foundational models and GNNs through a simple concept: constructing message-passing operators from pretrained foundation model weights. We show that this approach results in improved performance for graph-based tasks in a number of data domains, allowing graph neural networks to leverage the knowledge of foundation models.

翻译：基础模型已彻底改变了深度学习领域，成为可适用于广泛下游任务的多功能平台。尽管适应性强，但基础模型在下游图任务中的应用仍十分有限，且尚无便捷的方式在图结构化场景中利用大规模非图预训练模型。本文提出一种新框架——基础模型引导的消息传递（FIMP），通过一个简单概念架起基础模型与图神经网络之间的桥梁：从预训练基础模型权重构建消息传递算子。实验表明，该方法在多个数据域的图任务中提升了性能，使图神经网络能够有效利用基础模型的知识。