神经因果发现方法在小样本下难以区分真实与虚假因果关系。
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
- 用神经网络检测因果结构，但无法可靠判断关系是否存在
- 即使小图和大样本，仍无法准确恢复真实因果图
- 现有方法受忠实性假设限制，需根本性范式变革
神经因果发现方法在可扩展性和计算效率上已取得进展，但系统评估显示其在揭示因果结构时仍存在显著误差。我们发现根本性局限：在有限样本下，神经网络无法可靠区分真实与不存在的因果关系。实验表明，当前方法即使面对小规模图和相对大样本，也缺乏恢复真实图的精度。此外，忠实性假设是关键瓶颈：（i）在合理数据集规模范围内极可能被违反，（ii）其违反直接损害神经发现方法性能。结论是，当前范式下的进步存在根本限制，亟需领域范式转变。
原文摘要 · Abstract (English)
Neural causal discovery methods have recently improved in terms of scalability and computational efficiency. However, our systematic evaluation highlights significant room for improvement in their accuracy when uncovering causal structures. We identify a fundamental limitation: neural networks cannot reliably distinguish between existing and non-existing causal relationships in the finite sample regime. Our experiments reveal that neural networks, as used in contemporary causal discovery approaches, lack the precision needed to recover ground-truth graphs, even for small graphs and relatively large sample sizes. Furthermore, we identify the faithfulness property as a critical bottleneck: (i) it is likely to be violated across any reasonable dataset size range, and (ii) its violation directly undermines the performance of neural discovery methods. These findings lead us to conclude that progress within the current paradigm is fundamentally constrained, necessitating a paradigm shift in this domain.
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。