小模型也能推断图结构，轻量微调效果显著
TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference
- 用小型Transformer模型直接从图表示中推断结构参数
- 在多个图数据集上预测密度、聚类系数等指标表现良好
- 仅用LoRA微调即实现性能提升，适合资源受限场景
图是表示复杂关系系统的通用框架，推断其结构属性是图分析与推理的核心挑战。尽管大语言模型近期展现出符号与数值推理能力，但小型高效模型在此领域的潜力仍待探索。本文研究紧凑的Transformer语言模型是否能直接从图表示中推断图论参数。为系统评估，我们构建了TinyGraphEstimator数据集——一个由多种随机图模型生成的连通图集合，附带详尽的结构元数据标注。我们在多个小型开源模型上评估其对密度、聚类系数和色数等关键图参数的预测能力，并采用低秩适应（LoRA）进行轻量微调，结果在所有指标上均实现一致提升。实验表明，小型语言模型具备非平凡的图结构推理能力，通过高效参数调优可有效适配结构推断任务。
原文摘要 · Abstract (English)
Graphs provide a universal framework for representing complex relational systems, and inferring their structural properties is a core challenge in graph analysis and reasoning. While large language models have recently demonstrated emerging abilities to perform symbolic and numerical reasoning, the potential of smaller, resource-efficient models in this context remains largely unexplored. This paper investigates whether compact transformer-based language models can infer graph-theoretic parameters directly from graph representations. To enable systematic evaluation, we introduce the TinyGraphEstimator dataset - a balanced collection of connected graphs generated from multiple random graph models and annotated with detailed structural metadata. We evaluate several small open models on their ability to predict key graph parameters such as density, clustering, and chromatic number. Furthermore, we apply lightweight fine-tuning using the Low-Rank Adaptation (LoRA) technique, achieving consistent improvements across all evaluated metrics. The results demonstrate that small language models possess non-trivial reasoning capacity over graph-structured data and can be effectively adapted for structural inference tasks through efficient parameter tuning.
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。