Summary of Active-passive Federated Learning For Vertically Partitioned Multi-view Data, by Jiyuan Liu et al.
Active-Passive Federated Learning for Vertically Partitioned Multi-view Data
by Jiyuan Liu, Xinwang Liu, Siqi Wang, Xingchen Hu, Qing Liao, Xinhang Wan, Yi Zhang, Xin Lv, Kunlun He
First submitted to arxiv on: 6 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 In this paper, researchers propose a novel approach to vertical federated learning that addresses the limitations of existing methods. Specifically, they introduce Active-Passive Federated Learning (APFed), which allows for flexible collaboration between clients in model inference. The APFed framework consists of an active client that builds the complete model and passive clients that assist in the process. Once the model is built, the active client can make independent inferences without relying on the passive clients. The authors demonstrate the effectiveness of their approach by instantiating two classification methods using reconstruction loss and contrastive loss, respectively, and testing them through a set of experiments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning helps devices share information while keeping data private. A new approach called Active-Passive Federated Learning (APFed) makes it easier to use machine learning models without needing all the devices to work together at once. APFed has two types of devices: active and passive. The active device builds a complete model, while passive devices help with the process but don’t need to be involved in every step. This approach is useful when devices belong to different organizations or have different priorities. |
Keywords
» Artificial intelligence » Classification » Contrastive loss » Federated learning » Inference » Machine learning
