SMNC：用多尺度归一化闭包改进连续 DAG 结构学习
Structurally Separated DAG Learning with Multi-Scale Normalized Closure
做因果发现、结构学习的开发者可以看这篇：作者在 DAGMA 之上加了一层矩阵式多跳路径证据，多尺度归一化后长环梯度不再指数衰减。论文带线性+非线性 ER 基准对比，稠密图上明显超过 DAGMA，代码思路也写得清楚。
arXiv 论文提出 SMNC（scale-normalized multi-scale closure），在 DAGMA 式连续 DAG 学习基础上引入矩阵形式的 closure logits，为每个有序节点对显式表示多跳路径证据，而非将环路信息压缩为标量聚合量。
方法通过对结构门控做 log 空间反复平方来构建多尺度得分，并按路径长度预算归一化，抵消长环路上的乘积式衰减；对角元素用于节点级环路监督，非对角元素提供可选的成对可达性线索。
理论方面，线性模型给出有界的结构-幅值分解，对足够强的环路，归一化 logits 存在与长度无关的下界；在唯一活跃环路假设下，硬最终尺度读出将梯度因子从指数衰减改为多项式级 log-gate 因子。
实验在无先验线索、未标准化的高斯线性和非线性 ER 基准上进行，使用默认超参数，SMNC 在较稠密图上优于 DAGMA 且计算预算更低，在稀疏图上接近 DAGMA。
Structurally Separated DAG Learning with Multi-Scale Normalized Closure
Continuous DAG learning commonly enforces acyclicity through scalar functions of a weighted adjacency that aggregate evidence from weighted closed walks. We add a complementary layer: matrix-valued closure logits---explicit multi-hop structural relation scores for each ordered pair---supervised alongside data fit, sparsity, and a DAGMA-style barrier on the weighted adjacency. The distinction is not scalarization of the overall objective but how path evidence is represented and exposed before aggregation. SMNC (scale-normalized multi-scale closure) builds these scores on a structural gate by repeated squaring in log space and divides each scale by its path-length budget, counteracting product-style attenuation along long cycles; diagonal entries support node-wise cycle supervision and off-diagonals optional pairwise reachability cues. In the linear model, a bounded structure--magnitude factorization ties strong effective edges to strong gates; a nonlinear induced gate offers another construction with the same intent. For sufficiently strong cycles, normalized logits admit a length-independent lower bound; under a unique-active-cycle assumption, the hard final-scale readout yields a polynomial log-gate gradient factor rather than exponential product-style decay. On cue-free, unstandardized Gaussian linear and nonlinear ER benchmarks, these models improve over DAGMA, run with default hyperparameters at a reduced budget, on denser graphs and are close to it on sparse ones.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DAGMA, DAG, 因果发现, 结构学习.
Source attribution: curated from arXiv cs.LG (@Shuai Feng, Hao Yan).
