一句话：研究集中式、联邦与增量式协作训练对代码生成效果及数据记忆泄露风险的影响。
在机器学习中，跨地点与跨组织的数据集训练模型面临隐私和法律挑战，如何有效利用分布式且相互隔离的数据进行协作训练日益重要。本文研究影响协作训练方法在代码下一词预测任务中有效性的关键因素，并分析生成代码的正确性与实用性，展示协作训练的潜力。同时，论文评估不同参与方训练数据在集中式、联邦式和增量式等协作训练设置下的记忆化程度，揭示其可能造成的数据泄露风险。工作强调在提升代码生成模型效果的同时，需要关注并平衡记忆化带来的隐私隐患。
In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training settings, which are capable of leveraging valuable knowledge from distributed and isolated datasets, is increasingly crucial. This study investigates key factors that impact the effectiveness of collaborative training methods in code next-token prediction, as well as the correctness and utility of the generated code, showing the promise of such methods. Additionally, we evaluate the memorization of different participant training data across various collaborative training settings, including centralized, federated, and incremental training, showing their potential risks in leaking data.