Conference item
Planter: seeding trees within switches
- Abstract:
- Data classification within the network brings significant benefits in reaction time, servers offload and power efficiency. Still, only very simple models were mapped to the network. In-network classification will not be useful unless we manage to map complex machine learning models to network devices. We present Planter, an algorithm that maps a variety of ensemble models, such as XGBoost and Random Forest, to programmable switches. By overlapping trees within coded tables, Planter manages to map ensemble models to switches with high accuracy and low resource overhead.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 979.9KB, Terms of use)
-
- Publisher copy:
- 10.1145/3472716.3472846
Authors
- Publisher:
- Association for Computing Machinery
- Host title:
- Proceedings of the SIGCOMM '21 Poster and Demo Sessions
- Pages:
- 12-14
- Publication date:
- 2021-08-23
- Acceptance date:
- 2021-06-21
- Event title:
- SIGCOMM ’21 Demos and Posters
- Event location:
- Virtual Event, USA
- Event website:
- https://conferences.sigcomm.org/sigcomm/2021/cf-posters.html
- Event start date:
- 2021-08-23
- Event end date:
- 2021-08-27
- DOI:
- ISBN:
- 9781450386296
- Language:
-
English
- Keywords:
- Pubs id:
-
1184434
- Local pid:
-
pubs:1184434
- Deposit date:
-
2021-09-03
- ARK identifier:
Terms of use
- Copyright holder:
- Zheng and Zilberman
- Copyright date:
- 2021
- Rights statement:
- © 2021 Copyright held by the owner/author(s).
- Notes:
- This paper was presented at SIGCOMM ’21 Demos and Posters, 23–27 August 2021, Virtual Event, USA. This is the accepted manuscript version of the paper. The final version is available online from the Association for Computing Machinery at: https://doi.org/10.1145/3472716.3472846
If you are the owner of this record, you can report an update to it here: Report update to this record