用扩散语言模型统一处理图文图结构，无需微调即可跨任务通用。
TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning
- 将局部图结构转为令牌序列，通过拓扑注意力实现图文联合推理。
- 在三个标签图数据集上超越基线3.9个百分点，支持节点分类与链接预测。
- 只需改提示词就能适应不同任务，无需针对目标调整模型。
文本属性图（TAGs）中每个节点带有自然语言描述，需同时理解文本与图结构。现有方法常分开处理：图神经网络使用浅层文本特征，而大模型与图的混合架构仅将语言模型当作文本编码器，结构学习仍依赖独立图模块。本文提出一种统一的掩码扩散语言模型，融合文本理解与图消息传递。对每个图实例，将采样的局部邻域线性化为令牌序列，并通过拓扑注意力掩码注入图结构信息，实现图上的消息传递。由于该模型兼具文本解释与生成能力，仅通过修改提示词即可适配不同任务，无需特定任务微调，支持节点分类、链接预测及跨数据集迁移。实验表明，在三个TAG基准数据集上，该方法在两项任务中均优于图神经网络、图变压器及基于大模型的基线，性能提升最高达3.9点。
原文摘要 · Abstract (English)
Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual reasoning and graph message passing within a masked diffusion language model, a language model with bidirectional attention and generative decoding. For each graph instance, method linearises a sampled local neighbourhood into a token sequence and injects graph structure through a topology attention mask, which realises message passing over the graph. Because the diffusion language model can both interpret and generate text, the method adapts to different tasks simply by changing the prompt, supporting node classification, link prediction, and cross-dataset transfer with no target-specific fine-tuning. Experiments show that method outperforms graph neural networks, graph transformers, and LLM-based baselines on all three TAG benchmarks across two tasks, improving over the strongest baseline by up to 3.9 points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。