Generative ML models are increasingly popular in networking for tasks such as telemetry imputation, prediction, and synthetic trace generation. Despite their capabilities, they suffer from two shortcomings: (i) their output is often visibly violating well-known networking rules, which undermines their trustworthiness; and (ii) they are difficult to control, frequently requiring retraining even for minor changes. To address these limitations and unlock the benefits of generative models for networking, we propose a new paradigm for integrating explicit network knowledge in the form of first-order logic rules into ML models used for networking tasks. Rules capture well-known relationships among used signals, e.g., that increased latency precedes packet loss. While the idea is conceptually straightforward, its realization is challenging: networking knowledge is rarely formalized into rules, and naively injecting them into ML models often hampers ML's effectiveness. This paper introduces NetNomos a multi-stage framework that (1) learns rules directly from data (e.g., measurements); (2) filters them to distinguish semantically meaningful ones; and (3) enforces them through a collaborative generation between an ML model and an SMT solver.

翻译：生成式机器学习模型在网络领域日益流行，用于遥测数据插补、预测和合成轨迹生成等任务。尽管功能强大，它们仍存在两个缺陷：(i) 其输出常明显违反已知网络规则，损害了可信度；(ii) 模型难以控制，即使进行微小调整也常需重新训练。为克服这些限制并释放生成式模型在网络领域的潜力，我们提出一种新范式，将一阶逻辑规则形式的显式网络知识集成到用于网络任务的机器学习模型中。规则捕获了所用信号间的已知关系，例如延迟增加先于丢包发生。虽然这一概念在理论上直接，但其实现具有挑战性：网络知识很少被形式化为规则，且将其简单注入机器学习模型常会损害模型效能。本文介绍NetNomos——一个多阶段框架，它能够(1)直接从数据（如测量值）中学习规则；(2)通过过滤区分具有语义意义的规则；(3)通过机器学习模型与SMT求解器的协同生成来强制执行这些规则。