Net2Text: Query-Guided Summarization of Network Forwarding Behaviors
Event details
| Date | 17.05.2018 |
| Hour | 13:30 › 14:30 |
| Location | |
| Category | Conferences - Seminars |
By Dana Drachsler Cohen
Abstract
Today network operators spend a significant amount of time struggling to understand how their network forwards traffic. Even simple questions such as "How is my network handling Google traffic?" often require operators to manually bridge large semantic gaps between lowlevel forwarding rules distributed across many routers and the corresponding high-level insights.
In this talk, I will introduce Net2Text, a system which assists network operators in reasoning about network-wide forwarding behaviors. Out of the raw forwarding state and a query expressed in natural language, Net2Text automatically produces succinct summaries, also in natural language, which efficiently capture network-wide semantics. The key insight is to pose the problem of summarizing the network forwarding state as an optimization problem that aims to balance coverage, by describing as many paths as possible, and explainability, by maximizing the information provided. As this problem is NP-hard, I will show an approximation algorithm which generates summaries based on a sample of the forwarding state, with marginal loss of quality. I will experimentally show that Net2Text generates high-quality interpretable summaries of the entire forwarding state of hundreds of routers with full routing tables, in few seconds only.
Joint work with Rüdiger Birkner, Laurent Vanbever, and Martin Vechev.
Bio
Dana is an ETH Postdoctoral Fellow in the department of Computer Science at ETH Zurich.
Her research focuses on applying programming languages techniques to bring rigor to other areas including deep learning models, blockchains, and computer networks.
She obtained her PhD from the Computer Science Department at the Technion in 2017.
More information
Abstract
Today network operators spend a significant amount of time struggling to understand how their network forwards traffic. Even simple questions such as "How is my network handling Google traffic?" often require operators to manually bridge large semantic gaps between lowlevel forwarding rules distributed across many routers and the corresponding high-level insights.
In this talk, I will introduce Net2Text, a system which assists network operators in reasoning about network-wide forwarding behaviors. Out of the raw forwarding state and a query expressed in natural language, Net2Text automatically produces succinct summaries, also in natural language, which efficiently capture network-wide semantics. The key insight is to pose the problem of summarizing the network forwarding state as an optimization problem that aims to balance coverage, by describing as many paths as possible, and explainability, by maximizing the information provided. As this problem is NP-hard, I will show an approximation algorithm which generates summaries based on a sample of the forwarding state, with marginal loss of quality. I will experimentally show that Net2Text generates high-quality interpretable summaries of the entire forwarding state of hundreds of routers with full routing tables, in few seconds only.
Joint work with Rüdiger Birkner, Laurent Vanbever, and Martin Vechev.
Bio
Dana is an ETH Postdoctoral Fellow in the department of Computer Science at ETH Zurich.
Her research focuses on applying programming languages techniques to bring rigor to other areas including deep learning models, blockchains, and computer networks.
She obtained her PhD from the Computer Science Department at the Technion in 2017.
More information
Practical information
- General public
- Free
Contact
- Host: Laboratory for Automated Reasoning and Analysis, http://lara.epfl.ch