Towards Multi-Label Graph Foundation Models: from Single-Vector Representation Learning to Multi-Semantic Basis Learning

面向多标签图基础模型：从单向量表征学习到多语义基学习

Abstract: Multi-label node classification is an important yet challenging task in graph learning, where nodes exhibit multiple semantics simultaneously. Existing methods for multi-label node classification can effectively model multiple labels, while only considering in-domain scenarios where the model needs to be trained and tested within the same graph domain, resulting in limited cross-domain generalization.

摘要： 多标签节点分类是图学习中一项重要且具有挑战性的任务，其中节点同时表现出多种语义。现有的多标签节点分类方法虽然能有效建模多个标签，但仅考虑了域内场景，即模型需要在同一个图域内进行训练和测试，这导致其跨域泛化能力有限。

Recently, Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable graph representations across diverse graph domains and downstream tasks. However, existing GFMs are built upon single-label assumption, where all nodes are arbitrarily regarded as containing only one class of semantic and embedded into a single representation. For multi-label nodes, such a representation essentially approximates multiple semantics with a single point in the representation space, inevitably leading to semantic entanglement and making simultaneous discrimination of multiple labels difficult.

近年来，图基础模型（GFMs）作为一种新兴范式，在跨不同图域和下游任务学习可迁移图表征方面展现出巨大潜力。然而，现有的图基础模型大多建立在单标签假设之上，即所有节点被武断地视为仅包含一类语义，并被嵌入到一个单一的表征中。对于多标签节点而言，这种表征本质上是用表征空间中的一个点来近似多种语义，不可避免地导致了语义纠缠，使得同时区分多个标签变得困难。

To address these limitations, we propose a Multi-Semantic Basis Graph Foundation Model (MSB-GFM), a framework for cross-domain multi-label node classification. Specifically, we introduce a multi-semantic basis representation learning paradigm that models each multi-label node as an adaptive composition of semantic bases, thereby enabling flexible representational capacity for modeling multiple semantics. Furthermore, we develop a semantic-structure dual-channel architecture with domain adversarial training for effective cross-domain knowledge transfer. Extensive experiments demonstrate the effectiveness of our model.

为了解决这些局限性，我们提出了多语义基图基础模型（MSB-GFM），这是一个用于跨域多标签节点分类的框架。具体而言，我们引入了一种多语义基表征学习范式，将每个多标签节点建模为语义基的自适应组合，从而为建模多种语义提供了灵活的表征能力。此外，我们开发了一种结合域对抗训练的语义-结构双通道架构，以实现有效的跨域知识迁移。大量实验证明了我们模型的有效性。