CauScale让大规模因果发现更快更省空间，1000节点图上推理快万倍。
CauScale: Neural Causal Discovery at Scale
- 用压缩嵌入和共享注意力权重，解决大图因果推断的效率瓶颈。
- 在500节点图上训练成功，对分布内数据准确率达99.6%，分布外仍达84.4%。
- 适合需要高效处理大规模复杂因果关系的研究者与工业应用。
因果发现对科学人工智能与数据分析至关重要，但现有方法在扩展至大规模图时面临严重的时间与空间效率瓶颈。为此，我们提出 CauScale，一种可扩展至千节点图的神经架构。该方法通过压缩单元降低数据嵌入维度，并采用参数共享的注意力机制避免存储轴向注意力图，显著提升时空效率。为保持高准确性，CauScale采用双流设计：数据流从高维观测中提取关系证据，图流融合统计图先验并保留关键结构信号。在训练阶段，模型成功扩展至500节点图，而以往方法因内存限制无法实现。在不同规模和因果机制的数据测试中，模型在分布内数据上达到99.6% mAP，分布外数据上达84.4%，且推理速度相比前序方法提升4至13,000倍。项目主页见 https://github.com/OpenCausaLab/CauScale。
原文摘要 · Abstract (English)
Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500-node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data, while delivering 4-13,000 times inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale.
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。