Learning to Configure Computer Networks with Neural Algorithmic Reasoning

Abstract

We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that satisfies a given specification into an approximate objective amenable to learning-based techniques. Based on this idea, we train a neural algorithmic model which learns to generate configurations likely to (fully or partially) satisfy a given specification under existing routing protocols. By relaxing the rigid satisfaction guarantees, our approach (i) enables greater flexibility: it is protocol-agnostic, enables cross-protocol reasoning, and does not depend on hardcoded rules; and (ii) finds configurations for much larger computer networks than previously possible. Our learned synthesizer is up to 490x faster than state-of-the-art SMT-based methods, while producing configurations which on average satisfy more than 93% of the provided requirements.

Research Area: Verification and Synthesis

People

Prof. Laurent Vanbever

Group Leader

BibTex

@inproceedings{beurer-kellner2022learning,
  author    = {Beurer-Kellner, Luca and Vechev, Martin and Vanbever, Laurent and Veli{\v{c}}kovi{\'{c}}, Petar},
  title     = {{Learning to Configure Computer Networks with Neural Algorithmic Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems 35},
  address   = {New Orleans, LA, USA},
  year      = 2022,
  month     = nov,
  publisher = {Curran},
  url       = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/04cc90ec6868b97b7423dc38ced1e35c-Abstract-Conference.html}
}

Research Collection: 20.500.11850/589728