Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
D
D-Cliques
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
SaCS
Distributed Machine Learning
D-Cliques
Commits
41b67b3b
Commit
41b67b3b
authored
2 years ago
by
aurelien.bellet
Browse files
Options
Downloads
Patches
Plain Diff
cosmit
parent
e1189631
No related branches found
Branches containing commit
No related tags found
Tags containing commit
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
srds22/d-cliques.tex
+2
-2
2 additions, 2 deletions
srds22/d-cliques.tex
with
2 additions
and
2 deletions
srds22/d-cliques.tex
+
2
−
2
View file @
41b67b3b
...
...
@@ -224,8 +224,8 @@ until the topology stabilizes.
\begin{remark}
[Privacy]
Constructing cliques with Greedy-Swap only requires nodes to reveal their
local label proportions (i.e., a histogram with
$
L
$
bins), which is
aggregated
information. In rare
local label proportions (i.e., a histogram with
$
L
$
bins), which is
compact
aggregated
information. In rare
use-cases where this information may be considered sensitive, techniques
from differential privacy
\cite
{
dwork2013Algorithmic
}
can be readily used to
control the amount of leakage about the local dataset by adding
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment