Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints
Simulate Federated Multi-Task Learning via the Clustered Federated Learning method as described in
Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints
When clustering all clients into multiple clusters (>3), the indexes in cluster_indices seem to be incomprehensible.
Should this line cluster_indices_new += [c1, c2]
be cluster_indices_new += [idc[c1],idc[ c2]]
?
Hello,
I am not sure if this an error, but it seems you are not weighting the clients when averaging reduce_add_average
. Moreover, in the paper you use Local SGD with same number of steps at each client, while in the code you fit a fixed number of epochs, thus the number of steps is not constant across clients, and depends on the local data size.
I am not sure if what I highlight here is relevant, can you please clarify this if possible.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.