arXiv cs.AI· Giovanni Briglia, Marco Lippi, Stefano Mariani, Franco Zambonelli·· 3 天前AI 评分27
Neural Bayesian Networks：面向不确定性下模块化可扩展决策的神经贝叶斯网络
Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty
AI 导读
研究者提出 Neural Bayesian Networks（NBNs），将贝叶斯网络中的每个条件分布替换为可微分的张量机制，同时保持图结构与分解方式不变，从而可表示任意可学习的条件分布并原生运行在 GPU 上。团队同时发布基于 PyTorch 的 NBN 库及公开基准，在大规模网络和大批量查询上借助 GPU 并行实现两个数量级的加速。
正文 · 原文
Abstract:Bayesian Networks (BNs) are established tools for letting agents reason under uncertainty in sequential decision-making. They split a joint distribution into local conditional mechanisms arranged on a directed acyclic graph, which makes them modular, interpretable, and ready to perform probabilistic inference. Their classical formulation, however, has limitations in both expressiveness and scale: each conditional is usually stored as a table or a linear-Gaussian form, and inference evaluates the graph one node and one query at a time.
In this paper we introduce Neural Bayesian Networks (NBNs), in which each conditional is a differentiable, tensor-valued mechanism, while the graph and its factorization are unchanged. NBNs retain the modularity and local mechanisms of BNs, can represent any learnable conditional distribution, and run natively on GPUs. We also release NBN, a PyTorch-based library for learning and inference in NBNs, together with a public benchmark. Our evaluation shows gains in both expressiveness and scale: NBNs fit distributions that classical BN libraries struggle to represent, and on large networks and large batches of queries they run two orders of magnitude faster thanks to GPU parallelization. NBN is available at this https URL.
| Comments: | Main text 10 pages, extra is supplementary. ACM CCS: Computing methodologies~Artificial intelligence~Knowledge representation and reasoning~Probabilistic reasoning. Computing methodologies~Machine learning~Machine learning approaches~Neural networks. Computing methodologies~Machine learning~Machine learning approaches~Learning in probabilistic graphical models~Bayesian network models |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| ACM classes: | I.2.6; I.2.11 |
| Cite as: | arXiv:2610.16902 [cs.AI] |
| (or arXiv:2610.16902v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16902 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Stefano Mariani [view email]
[v1]
Mon, 12 Oct 2026 14:54:35 UTC (3,270 KB)
来源：arXiv cs.AI · arxiv.org