Summary of Trust and Resilience in Federated Learning Through Smart Contracts Enabled Decentralized Systems, by Lorenzo Cassano et al.
Trust and Resilience in Federated Learning Through Smart Contracts Enabled Decentralized Systems
by Lorenzo Cassano, Jacopo D’Abramo, Siraj Munir, Stefano Ferretti
First submitted to arxiv on: 9 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
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 This paper presents a Federated Learning (FL) system designed to ensure trust and reliability through decentralized architectures. The system utilizes Inter-Planetary File System (IPFS) to securely store model parameters and a smart contract for tracking collaborators’ behavior. This innovative approach efficiently manages parameter updates, strengthening data security. Two weight aggregation methods are explored: classic averaging and federated proximal aggregation. Experimental results confirm the feasibility of this proposal. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating a way for many computers to work together on a big task without sharing their individual information. They use special technology called Inter-Planetary File System (IPFS) to keep things safe. A “smart contract” helps them keep track of what’s going on. The experiment shows that this new way works well. |
Keywords
» Artificial intelligence » Federated learning » Tracking
