Towards Integrating Formal Methods into ML-Based Systems for Networking

Fengchen Gong, Divya Raghunathan, Aarti Gupta, Maria Apostolaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Owing to its adaptability and scalability, Machine Learning (ML) has gained significant momentum in the networking community. Yet, ML models can still produce outputs that contradict knowledge, i.e., established networking rules and principles. On the other hand, Formal Methods (FM) use rigorous mathematical reasoning based on knowledge, but suffer from the lack of scalability. To capitalize on the complementary strengths of both approaches, we advocate for the integration of knowledge-based FM into ML-based systems for networking problems. Through a case study, we demonstrate the benefits and limitations of using ML models or FM alone. We find that incorporating FM in the training and inference of an ML model yields not only more reliable results but also better performance in various downstream tasks. We hope that our paper inspires a tighter integration of FM-based and ML-based approaches in networking, facilitating the development of more robust and dependable systems.

Original languageEnglish (US)
Title of host publicationHotNets 2023 - Proceedings of the 22nd ACM Workshop on Hot Topics in Networks
PublisherAssociation for Computing Machinery, Inc
Pages48-55
Number of pages8
ISBN (Electronic)9798400704154
DOIs
StatePublished - Nov 28 2023
Event22nd ACM Workshop on Hot Topics in Networks, HotNets 2023 - Cambridge, United States
Duration: Nov 28 2023Nov 29 2023

Publication series

NameHotNets 2023 - Proceedings of the 22nd ACM Workshop on Hot Topics in Networks

Conference

Conference22nd ACM Workshop on Hot Topics in Networks, HotNets 2023
Country/TerritoryUnited States
CityCambridge
Period11/28/2311/29/23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Keywords

  • Formal Methods
  • Imputation
  • Telemetry
  • Transformer

Fingerprint

Dive into the research topics of 'Towards Integrating Formal Methods into ML-Based Systems for Networking'. Together they form a unique fingerprint.

Cite this