[论文解读] Modality-free Graph In-context Alignment

Wei Zhuo, Siqiang Luo|arXiv (Cornell University)|Mar 13, 2026

Advanced Graph Neural Networks被引用 0

一句话总结

MF-GIA 通过在统一空间中对预编码图特征和领域特定标签进行对齐，利用梯度指纹和领域条件变换，实现跨异构领域的少样本、无需参数更新的图像-上下文学习。

ABSTRACT

In-context learning (ICL) converts static encoders into task-conditioned reasoners, enabling adaptation to new data from just a few examples without updating pretrained parameters. This capability is essential for graph foundation models (GFMs) to approach LLM-level generality. Yet current GFMs struggle with cross-domain alignment, typically relying on modality-specific encoders that fail when graphs are pre-vectorized or raw data is inaccessible. In this paper, we introduce Modality-Free Graph In-context Alignment (MF-GIA), a framework that makes a pretrained graph encoder promptable for few-shot prediction across heterogeneous domains without modality assumptions. MF-GIA captures domain characteristics through gradient fingerprints, which parameterize lightweight transformations that align pre-encoded features and indexed labels into unified semantic spaces. During pretraining, a dual prompt-aware attention mechanism with episodic objective learns to match queries against aligned support examples to establish prompt-based reasoning capabilities. At inference, MF-GIA performs parameter-update-free adaptation using only a few-shot support set to trigger cross-domain alignment and enable immediate prediction on unseen domains. Experiments demonstrate that MF-GIA achieves superior few-shot performance across diverse graph domains and strong generalization to unseen domains.

研究动机与目标

• 在不更新参数的情况下，提示一个预训练的图编码器在新图域上进行少样本预测。
• 在不需要模态特定编码器或原始数据访问的前提下实现跨域对齐。
• 引入基于梯度的领域指纹以驱动领域条件特征和标签对齐。
• 通过情节式预训练学习基于提示的推理，以便在未见领域上实现即时推断。

提出的方法

• 定义模态自由的对齐，将领域特定特征和标签ID映射到通过领域条件变换得到的统一空间。
• 使用梯度指纹（一次性更新）来推导参数化FiLM特征与标签对齐器的领域嵌入。
• 在情节式预训练中使用双提示感知注意力（DPAA）将查询与对齐的支持样本进行匹配。
• 以m路k-shot的情节式预训练来教会模型仅通过提示进行上下文推理。
• 在推断阶段，对未见图进行领域嵌入计算，应用对齐器，且不更新预训练参数。

Figure 1: Overview of MF-GIA. (Left) Modality-free Alignment: The pretraining graphs are mapped to a unified space via domain-conditioned transformations. Domain descriptors $e$ ensure similar domains occupy neighboring subspaces. (Middle) Episodic Pretraining: The model learns from $m$ -way $k$ -sh

实验结果

研究问题

• RQ1 一个图基础模型是否能够在没有模态假设的前提下，在异质图域之间实现真正的上下文学习？
• RQ2 梯度指纹与领域条件对齐是否能够实现对未见图的跨域、训练后无参数更新的推断？
• RQ3 使用DPAA的情节式预训练是否促进跨域节点和边分类的有效提示推理？

主要发现

• MF-GIA 在多样的图域上实现了卓越的少样本性能。
• 该方法能够在完全未见的域上泛化，无需额外训练。
• 它在边级任务上也能有效迁移，除了节点任务之外。
• 基于领域条件的FiLM特征与标签对齐在保持域内语义的同时实现跨域迁移。

Figure 2: Domain embedder.