Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

readme: rm papers #819

Merged
merged 2 commits into from
Nov 19, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 13 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -28,24 +28,29 @@ ___

___
:question: **DISCO TECHNOLOGY**
- DISCO supports arbitrary deep learning tasks and model architectures in your browser via [TF.js](https://www.tensorflow.org/js)
- DISCO runs arbitrary deep learning tasks and model architectures in your browser, via [TF.js](https://www.tensorflow.org/js)
- Decentralized learning :sparkles: relies on [peer2peer](https://github.com/feross/simple-peer) communication
- Have a look at how DISCO ensures privacy and confidentiality [HERE](docs/PRIVACY.md)

___

:test_tube: **RESEARCH-BASED DESIGN**
:test_tube: **RESEARCH-BASED DESIGN**

DISCO leverages latest research advances, enabling open-access and easy-use distributed training which is
- :tornado: efficient ([R1](https://github.com/epfml/powergossip), [R2](https://github.com/epfml/ChocoSGD))
- :lock: privacy-preserving ([R3](https://eprint.iacr.org/2017/281.pdf), [R4](https://arxiv.org/abs/2006.04747))
- :hammer_and_wrench: fault-tolerant and dynamic over time ([R5](https://arxiv.org/abs/2106.06639), [R6](https://arxiv.org/abs/2206.08307))
- :ninja: robust to malicious actors and data poisoning ([R7](https://arxiv.org/abs/2012.10333), [R8](https://arxiv.org/abs/2006.09365))

- :lock: privacy-preserving ([R1](https://eprint.iacr.org/2017/281.pdf))
- :hammer_and_wrench: dynamic and asynchronous over time ([R2](https://arxiv.org/abs/2106.06639), [R7](https://arxiv.org/abs/2206.08307))
- :ninja: robust to malicious actors ([R3](https://arxiv.org/abs/2012.10333) (partially))

And more on the roadmap

- :tornado: efficient ([R4](https://github.com/epfml/powergossip), [R5](https://github.com/epfml/ChocoSGD))
- :lock: privacy-preserving while Byzantine robust ([R6](https://arxiv.org/abs/2006.04747))
- :ninja: resistant to data poisoning ([R8](https://arxiv.org/abs/2006.09365))
- :apple: :banana: interpretable in imperfectly interoperable data distributions ([R9](https://arxiv.org/abs/2107.06580))
- :mirror: personalizable ([R10](https://arxiv.org/abs/2103.00710))
- :mirror: personalizable ([R10](https://arxiv.org/abs/2103.00710))
- :carrot: fairly incentivizing participation


___


Expand Down