add FedAS

Author: TsingZ0

README.md

@@ -23,7 +23,7 @@ Figure 1: An Example for FedAvg. You can create a scenario using `generate_DATA.
 ```
 ### Key Features
 
-- **37 traditional FL ([tFL](#traditional-fl-tfl)) and personalized FL ([pFL](#personalized-fl-pfl)) algorithms, 3 scenarios, and 24 datasets.**
+- **38 traditional FL ([tFL](#traditional-fl-tfl)) and personalized FL ([pFL](#personalized-fl-pfl)) algorithms, 3 scenarios, and 24 datasets.**
 
 - Some **experimental results** are avalible in its [paper](https://arxiv.org/abs/2312.04992) and [here](#experimental-results). 
 
@@ -107,6 +107,7 @@ The origin of the **data heterogeneity** phenomenon is the characteristics of us
 - **FedDBE** — [Eliminating Domain Bias for Federated Learning in Representation Space](https://openreview.net/forum?id=nO5i1XdUS0) *NeurIPS 2023*
 - **FedCAC** — [Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration](https://arxiv.org/abs/2309.11103) *ICCV 2023*
 - **PFL-DA** — [Personalized Federated Learning via Domain Adaptation with an Application to Distributed 3D Printing](https://www.tandfonline.com/doi/full/10.1080/00401706.2022.2157882) *Technometrics 2023*
+- **FedAS** — [FedAS: Bridging Inconsistency in Personalized Federated Learning](https://openaccess.thecvf.com/content/CVPR2024/papers/Yang_FedAS_Bridging_Inconsistency_in_Personalized_Federated_Learning_CVPR_2024_paper.pdf) *CVPR 2024*
 
   ***Knowledge-distillation-based pFL (more in [HtFLlib](https://github.com/TsingZ0/HtFLlib))***
 

docs/algo.html

@@ -246,6 +246,7 @@ <h3>Personalized FL (pFL)</h3>
                     <li><strong>FedDBE</strong> — <a href="https://openreview.net/forum?id=nO5i1XdUS0">Eliminating Domain Bias for Federated Learning in Representation Space</a> <em>NeurIPS 2023</em></li>
                     <li><strong>FedCAC</strong> — <a href="https://arxiv.org/abs/2309.11103">Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration</a> <em>ICCV 2023</em></li>
                     <li><strong>PFL-DA</strong> — <a href="https://www.tandfonline.com/doi/full/10.1080/00401706.2022.2157882">Personalized Federated Learning via Domain Adaptation with an Application to Distributed 3D Printing</a> <em>Technometrics 2023</em></li>
+                    <li><strong>FedAS</strong> — <a href="https://openaccess.thecvf.com/content/CVPR2024/papers/Yang_FedAS_Bridging_Inconsistency_in_Personalized_Federated_Learning_CVPR_2024_paper.pdf">FedAS: Bridging Inconsistency in Personalized Federated Learning</a> <em>CVPR 2024</em></li>
                 </ul>
 
                 <li><strong><em>Knowledge-distillation-based pFL (more in <a href="https://github.com/TsingZ0/HtFLlib">HtFLlib</a>)</em></strong></li>

docs/docs.html

@@ -199,7 +199,7 @@ <h4>Simple File Structure</h4>
 
                 <h4>Key Features</h4>
                 <p>
-                    <li><strong>37</strong> traditional FL (tFL) or personalized FL (pFL) algorithms,  <strong>3</strong> scenarios, and <strong>24</strong> datasets.</li>
+                    <li><strong>38</strong> traditional FL (tFL) or personalized FL (pFL) algorithms,  <strong>3</strong> scenarios, and <strong>24</strong> datasets.</li>
                     <li>Some experimental results are avalible in the <a href="https://arxiv.org/abs/2312.04992"><strong>PFLlib paper</strong></a> and <a href="benchmark.html"><strong>Benchmark Results</strong></a>.</li>
                     <li>The benchmark platform can simulate scenarios using the 4-layer CNN on Cifar100 for <strong>500 clients</strong> on one NVIDIA GeForce RTX 3090 GPU card with <strong>only 5.08GB GPU memory cost</strong>.</li>
                     <li>We provide <a href="features.html#privacy-evaluation">privacy evaluation</a> and <a href="features.html#systematical-research-supprot">systematical research support</a>.</li>

docs/index.html

@@ -195,7 +195,7 @@ <h1><a href="index.html" id="PFLlib">PFLlib</a></h1>
     <div class="hero">
         <div>
             <h1>PFLlib is all you need</h1>
-            <p>A <strong>beginner-friendly</strong> and comprehensive personalized federated learning <strong>library</strong> and <strong>benchmark platform</strong>. <br /> <strong>37</strong> traditional FL (tFL) or personalized FL (pFL) algorithms,  <strong>3</strong> scenarios, and <strong>24</strong> datasets.</p>
+            <p>A <strong>beginner-friendly</strong> and comprehensive personalized federated learning <strong>library</strong> and <strong>benchmark platform</strong>. <br /> <strong>38</strong> traditional FL (tFL) or personalized FL (pFL) algorithms,  <strong>3</strong> scenarios, and <strong>24</strong> datasets.</p>
             <button onclick="window.location.href='docs.html'">Get Started</button>
         </div>
     </div>