针对机器人抓取的非独立同分布数据，提出分层联邦学习框架提升模型性能。
MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping
- 按数据质量和数量筛选优质机器人作为顶层节点训练初始模型。
- 在量少且分布不均的数据上，性能比传统联邦学习提升最高8%。
- 适合数据差异大、隐私要求高的多机器人协作抓取场景。
联邦学习（FL）是一种能够实现设备间协同建模且保护数据隐私的机器学习范式，在机器人操作任务中已展现潜力。然而，抓取任务在该框架下的探索仍不足：机器人在不传输数据的前提下训练全局模型，虽保障了隐私，但面临数据非独立同分布（non-IID）且样本量少的问题，导致性能下降，尤其在抓取任务中表现明显。为此，本文提出 MTF-Grasp，一种面向机器人抓取的多层级联邦学习方法，充分考虑机器人间数据分布的非独立同分布特性，包括数量偏斜问题。该方法基于数据质量与数量，筛选出“顶层”机器人，利用其更优的数据分布和更多样本训练初始种子模型，并将其分发给“低层”机器人，降低后者因数据差而导致的模型性能退化风险。实验表明，该方法在数量偏斜的 Cornell 与 Jacquard 抓取数据集上，相较传统联邦学习设置，性能最高提升 8%。
原文摘要 · Abstract (English)
Federated Learning (FL) is a promising machine learning paradigm that enables participating devices to train privacy-preserved and collaborative models. FL has proven its benefits for robotic manipulation tasks. However, grasping tasks lack exploration in such settings where robots train a global model without moving data and ensuring data privacy. The main challenge is that each robot learns from data that is nonindependent and identically distributed (non-IID) and of low quantity. This exhibits performance degradation, particularly in robotic grasping. Thus, in this work, we propose MTF-Grasp, a multi-tier FL approach for robotic grasping, acknowledging the unique challenges posed by the non-IID data distribution across robots, including quantitative skewness. MTF-Grasp harnesses data quality and quantity across robots to select a set of "top-level" robots with better data distribution and higher sample count. It then utilizes top-level robots to train initial seed models and distribute them to the remaining "low-level" robots, reducing the risk of model performance degradation in low-level robots. Our approach outperforms the conventional FL setup by up to 8% on the quantity-skewed Cornell and Jacquard grasping datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。