Summary of Mixture Of Experts Made Personalized: Federated Prompt Learning For Vision-language Models, by Jun Luo et al.
Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models
by Jun Luo, Chen Chen, Shandong Wu
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel federated learning framework, pFedMoAP, that personalizes the prompt learning process using Mixture of Experts (MoE). The framework allows clients to download multiple pre-aggregated prompts as fixed non-local experts and uses a local attention-based gating network to generate enhanced text features aligned with local image data. This approach benefits from both local and downloaded adaptive prompt experts, leading to improved performance on 9 datasets under various federated settings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers developed a new way to do federated learning that helps prompts learn better by using multiple expert prompts. They tested this method on nine different datasets and showed it works well in different scenarios. |
Keywords
» Artificial intelligence » Attention » Federated learning » Mixture of experts » Prompt
