用大模型生成图结构，提升因果发现的效率与精度。
Guide: Generalized-Prior and Data Encoders for DAG Estimation
- 结合大模型生成邻接矩阵与观测数据，双编码器架构优化推理。
- 在70节点以上场景下，运行时间减少42%，准确率提升117%。
- 适合需要处理混合数据类型、大规模因果推断的研究者使用。
现代因果发现方法在可扩展性、计算效率和混合数据类型适应性方面存在显著局限，体现在节点规模（30、≤50、≥70节点）、计算能耗以及连续/非连续数据处理能力上。传统算法如PC、GES和ICA-LiNGAM在高阶节点下能耗过高，且在超过70节点时表现不佳。我们提出GUIDE框架，通过双编码器架构将大语言模型（LLM）生成的邻接矩阵与观测数据融合。训练中，强化学习代理动态平衡奖励最大化（准确性）与惩罚规避（DAG约束），实现跨混合数据类型的鲁棒性能，并支持≥70节点的可扩展性——这是基线方法失效的场景。相比RL-BIC和KCRL方法，平均运行时间减少约42%；相比NOTEARS和GraN-DAG，平均准确率提升约117%。
原文摘要 · Abstract (English)
Modern causal discovery methods face critical limitations in scalability, computational efficiency, and adaptability to mixed data types, as evidenced by benchmarks on node scalability (30, $\le 50$, $\ge 70$ nodes), computational energy demands, and continuous/non-continuous data handling. While traditional algorithms like PC, GES, and ICA-LiNGAM struggle with these challenges, exhibiting prohibitive energy costs for higher-order nodes and poor scalability beyond 70 nodes, we propose \textbf{GUIDE}, a framework that integrates Large Language Model (LLM)-generated adjacency matrices with observational data through a dual-encoder architecture. GUIDE uniquely optimizes computational efficiency, reducing runtime on average by $\approx 42%$ compared to RL-BIC and KCRL methods, while achieving an average $\approx 117%$ improvement in accuracy over both NOTEARS and GraN-DAG individually. During training, GUIDE's reinforcement learning agent dynamically balances reward maximization (accuracy) and penalty avoidance (DAG constraints), enabling robust performance across mixed data types and scalability to $\ge 70$ nodes -- a setting where baseline methods fail.
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。