Summary of Towards Efficient Replay in Federated Incremental Learning, by Yichen Li et al.
Towards Efficient Replay in Federated Incremental Learning
by Yichen Li, Qunwei Li, Haozhao Wang, Ruixuan Li, Wenliang Zhong, Guannan Zhang
First submitted to arxiv on: 9 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
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 Federated Incremental Learning (FIL) is a machine learning framework where data arrives incrementally at edge clients with limited storage capacity. Traditional Federated Learning assumes fixed client data, but this paper addresses catastrophic forgetting by proposing Re-Fed, a generic framework for FIL. When new tasks arrive, each client caches important samples based on global and local importance, then trains the model using both cached and new task samples. Theoretical analysis shows Re-Fed’s ability to alleviate catastrophic forgetting. Empirical results demonstrate competitive performance compared to state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a world where machines learn together from different pieces of information, even if that information keeps changing. This is called Federated Incremental Learning (FIL). The problem with this type of learning is that the machines forget what they learned before when new information comes in. To solve this, researchers created a simple framework called Re-Fed. It helps machines remember important lessons from the past by caching them and then using them to learn even more. In tests, Re-Fed performed just as well as other methods. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
