Summary of Pfl-research: Simulation Framework For Accelerating Research in Private Federated Learning, by Filip Granqvist et al.
pfl-research: simulation framework for accelerating research in Private Federated Learning
by Filip Granqvist, Congzheng Song, Áine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); 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 Federated learning (FL) is an emerging machine learning paradigm where clients collaborate to train a global model without sharing their data. Existing tools lack efficiency for simulating FL on larger datasets, hindering research productivity. To address this, we introduce pfl-research, a Python framework supporting TensorFlow, PyTorch, and non-neural network models, tightly integrated with state-of-the-art privacy algorithms. Our study shows that pfl-research is 7-72 times faster than alternative frameworks on common cross-device setups. This speedup will significantly boost the productivity of the FL research community, enabling testing hypotheses on realistic datasets. We release a suite of benchmarks evaluating an algorithm’s overall performance on diverse scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to train machine learning models without sharing data between devices. It’s like having multiple puzzle pieces that need to fit together to make a complete picture. Researchers use simulations to test ideas quickly, but existing tools aren’t fast enough for large datasets. We created pfl-research, a tool that helps researchers work faster and more efficiently. Our tests showed that pfl-research is much faster than other tools, making it easier for researchers to do their job. This will help the community create better models and make new discoveries. |
Keywords
* Artificial intelligence * Federated learning * Machine learning * Neural network
