From f40782ad067d0382d678e3aa7073af9977ca0b30 Mon Sep 17 00:00:00 2001
From: Tsing <2719584131@qq.com>
Date: Wed, 18 Dec 2024 11:48:07 +0800
Subject: [PATCH] fix typos
---
README.md | 8 ++++----
docs/about.html | 2 +-
docs/benchmark.html | 4 ++--
docs/docs.html | 4 ++--
docs/extend.html | 2 +-
docs/index.html | 2 +-
6 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/README.md b/README.md
index a461c646..e3f4eee0 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
# PFLlib: Personalized Federated Learning Library
-🎯***We create a beginner-friendly algorithm library and evaluation platform for those new to federated learning. Join us in expanding the FL community by contributing your algorithms, datasets, and metrics to this project.***
+🎯***We create a beginner-friendly algorithm library and benchmark platform for those new to federated learning. Join us in expanding the FL community by contributing your algorithms, datasets, and metrics to this project.***
👏 **PFLlib now has its official website and domain name: https://www.pfllib.com/!!!**
@@ -33,13 +33,13 @@ Figure 1: An Example for FedAvg. You can create a scenario using `generate_DATA.
- Refer to [this guide](#how-to-start-simulating-examples-for-fedavg) to learn how to use it.
-- The evaluation platform can simulate scenarios using the 4-layer CNN on Cifar100 for **500 clients** on **one NVIDIA GeForce RTX 3090 GPU card** with only **5.08GB GPU memory** cost.
+- The benchmark platform can simulate scenarios using the 4-layer CNN on Cifar100 for **500 clients** on **one NVIDIA GeForce RTX 3090 GPU card** with only **5.08GB GPU memory** cost.
- We provide [privacy evaluation](#privacy-evaluation) and [systematical research supprot](#systematical-research-supprot).
- You can now train on some clients and evaluate performance on new clients by setting `args.num_new_clients` in `./system/main.py`. Please note that not all tFL/pFL algorithms support this feature.
-- PFLlib primarily focuses on data (statistical) heterogeneity. For algorithms and an evaluation platform that address **both data and model heterogeneity**, please refer to our extended project **[Heterogeneous Federated Learning (HtFLlib)](https://github.com/TsingZ0/HtFLlib)**.
+- PFLlib primarily focuses on data (statistical) heterogeneity. For algorithms and a benchmark platform that address **both data and model heterogeneity**, please refer to our extended project **[Heterogeneous Federated Learning (HtFLlib)](https://github.com/TsingZ0/HtFLlib)**.
- As we strive to meet diverse user demands, frequent updates to the project may alter default settings and scenario creation codes, affecting experimental results.
@@ -381,7 +381,7 @@ This library is designed to be easily extendable with new algorithms and dataset
- **New Optimizer**: If you need a new optimizer for training, add it to `./system/flcore/optimizers/fedoptimizer.py`.
-- **New Evaluation Platform or Library**: The evaluation framework is flexible, allowing users to build custom platforms or libraries for specific applications, such as [FL-IoT](https://github.com/TsingZ0/FL-IoT) and [HtFLlib](https://github.com/TsingZ0/HtFLlib).
+- **New Benchmark Platform or Library**: Our framework is flexible, allowing users to build custom platforms or libraries for specific applications, such as [FL-IoT](https://github.com/TsingZ0/FL-IoT) and [HtFLlib](https://github.com/TsingZ0/HtFLlib).
## Privacy Evaluation
diff --git a/docs/about.html b/docs/about.html
index db251d02..d6a9d1a3 100644
--- a/docs/about.html
+++ b/docs/about.html
@@ -116,7 +116,7 @@
We create a beginner-friendly library with an evaluation platform for those new to federated learning (FL). Join us in benefiting the FL community by contributing your algorithms, datasets, and metrics to this project.
+
We create a beginner-friendly library with a benchmark platform for those new to federated learning (FL). Join us in benefiting the FL community by contributing your algorithms, datasets, and metrics to this project.
Value
PFLlib is ideal for companies aiming to explore, select, and evaluate standard/personalized federated learning methods. It enables the evaluation of algorithms and their adaptability to diverse scenarios, offering valuable insights for informed algorithm selection in real-world applications. With its robust features, PFLlib is well-suited for a wide range of industries, from healthcare to finance.
To integrate all the algorithms, datasets, and scenarios, we standardize the experimental settings and create a unified evaluation platform for a fair comparison of these algorithms. Here, we present the benchmark results of 20 algorithms across two widely-used label skew scenarios. This is just one example. You can obtain different results by resetting all the configurations in main.py in our PFLlib.
+
Benchmark Platform
+
To integrate all the algorithms, datasets, and scenarios, we standardize the experimental settings and create a unified benchmark platform for a fair comparison of these algorithms. Here, we present the benchmark results of 20 algorithms across two widely-used label skew scenarios. This is just one example. You can obtain different results by resetting all the configurations in main.py in our PFLlib.
Leaderboard
Our methods—FedCP, GPFL, and FedDBE—lead the way. Notably, FedDBE stands out with robust performance across varying data heterogeneity levels.
The test accuracy (%) on the CV and NLP tasks in label skew settings.
The evaluation platform can simulate scenarios using the 4-layer CNN on Cifar100 for 500 clients on one NVIDIA GeForce RTX 3090 GPU card with only 5.08GB GPU memory cost.
+
The benchmark platform can simulate scenarios using the 4-layer CNN on Cifar100 for 500 clients on one NVIDIA GeForce RTX 3090 GPU card with only 5.08GB GPU memory cost.
You can now train on some clients and evaluate performance on new clients by setting args.num_new_clients in ./system/main.py. Please note that not all tFL/pFL algorithms support this feature.
-
PFLlib primarily focuses on data (statistical) heterogeneity. For algorithms and an evaluation platform that address both data and model heterogeneity, please refer to our extended project HtFLlib.
+
PFLlib primarily focuses on data (statistical) heterogeneity. For algorithms and a benchmark platform that address both data and model heterogeneity, please refer to our extended project HtFLlib.
As we strive to meet diverse user demands, frequent updates to the project may alter default settings and scenario creation codes, affecting experimental results.
- New Evaluation Platform or Library: The evaluation framework is flexible, allowing users to build
+ New Benchmark Platform or Library: Our code framework is flexible, allowing users to build
custom platforms or libraries for specific applications, such as
FL-IoT and
HtFLlib.
diff --git a/docs/index.html b/docs/index.html
index 59cbd8e5..ff7b1f7d 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -194,7 +194,7 @@
A beginner-friendly and comprehensive personalized federated learning library, benchmark, and evaluation platform. 37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 24 datasets.
+
A beginner-friendly and comprehensive personalized federated learning library and benchmark platform. 37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 24 datasets.