Some results are exactly the same as pFedPrompt paper Table 1

[liuxingzhang]

Thank you for your amazing work and open-souring the implementation.

I wonder why in the Table 1 of your paper, the results of

• pFedPrompt
• PromptFL+FT
• PromptFL+FedPer
• PromptFL+FedAMP

are exactly the same (same mean and same std) as the corresponding results in pFedPrompt paper's [1] Table 1? If the federated dataset partition and the seeds for running these experiments are the same as pFedPrompt's experiments, why are the results of PromptFL and PromptFL+FedProx in your experiments different from theirs?

[1] Guo, Tao, Song Guo, and Junxiao Wang. "Pfedprompt: Learning personalized prompt for vision-language models in federated learning." In Proceedings of the ACM Web Conference 2023, pp. 1364-1374. 2023.

[snow-zhai]

I have the same questions. Could you open all the baseline source code? Thank you,