# Making Logic a First-Class Citizen in Generative ML for Networking

arXiv: https://arxiv.org/abs/2506.23964 · HTML: https://mlsanity.com/paper/2506.23964/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 91 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Charformer: Fast Character Transformers via Gradient-based Subword Tokenization](https://mlsanity.com/paper/2106.12672/) (2021)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers](https://mlsanity.com/paper/2302.02041/) (2023)
- [Limitations of Language Models in Arithmetic and Symbolic Induction](https://mlsanity.com/paper/2208.05051/) (2022)
- [NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation](https://mlsanity.com/paper/2310.08543/) (2023)
- [Flow-based Network Traffic Generation using Generative Adversarial Networks](https://mlsanity.com/paper/1810.07795/) (2018)
- [netFound: Principled Design for Network Foundation Models](https://mlsanity.com/paper/2310.17025/) (2023)
- [Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions](https://mlsanity.com/paper/1909.13403/) (2019)
- [Robustifying ML-powered Network Classifiers with PANTS](https://mlsanity.com/paper/2409.04691/) (2024)
- [CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers](https://mlsanity.com/paper/2501.10013/) (2025)
- [NetSSM: Multi-Flow and State-Aware Network Trace Generation using State Space Models](https://mlsanity.com/paper/2503.22663/) (2025)
- [A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning](https://mlsanity.com/paper/2507.01976/) (2025)

## Built on by (most cited first, 2 of 2)

- [Invariant Discovery for Networked Systems](https://mlsanity.com/paper/2607.22944/) (2026)
- [Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures](https://mlsanity.com/paper/2610.08090/) (2026)

## Abstract (arXiv)

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 observed 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 rules into ML models often hampers their effectiveness. This paper introduces NetNomos, a multi-stage framework that (i) learns rules directly from data (e.g., measurements); (ii) filters them to select semantically meaningful ones; and (iii) enforces them through collaborative generation between an ML model and a Satisfiability Modulo Theories (SMT) solver. %We evaluate NetNomos both component-wise and end-to-end across four diverse network datasets. We show that NetNomos learns diverse, meaningful rules from four real-world datasets and is 1.6--6.5× more scalable than DuoAI, a state-of-the-art (SOTA) rule-learning method. By enforcing these rules on a generic GPT-2 model, NetNomos achieves performance on par with or even surpassing specialized SOTA systems such as Zoom2Net and NetShare across three networking tasks: telemetry imputation, traffic forecasting, and synthetic data generation.