少样本类增量学习与非独立同分布分散数据
Few-Shot Class-Incremental Learning with Non-IID Decentralized Data
AI总结：
本文提出联邦少样本类增量学习范式及合成数据驱动框架，通过噪声感知生成重放和类特定加权聚合，应对非独立同分布数据下的少样本学习、灾难性遗忘和数据异质性挑战。
摘要：
少样本类增量学习对于开发可扩展和自适应的智能系统至关重要，因为它使模型能够在保护先前积累的知识的同时，用最少的标注数据获取新类别。然而，现有方法以集中式方式处理连续数据流，限制了其在优先考虑数据隐私和安全场景中的适用性。为此，本文引入了联邦少样本类增量学习，这是一种去中心化的机器学习范式，专门用于从分布在多个客户端上的稀缺数据中逐步学习新类别。在这种学习范式中，客户端在本地更新其模型以学习新类别，同时保护数据隐私，然后将模型更新传输到中央服务器进行全局聚合。然而，该范式面临若干问题，如少样本学习困难、灾难性遗忘和数据异质性。为解决这些挑战，我们提出了一个基于合成数据的框架，利用重放缓冲区数据来维持现有知识并促进新知识的获取。在该框架内，开发了一个噪声感知的生成重放模块，通过平衡新数据和重放数据来微调本地模型，同时生成新类别的合成数据以进一步扩展重放缓冲区用于未来任务。此外，设计了一种类特定加权聚合策略，通过根据本地模型在合成数据上的性能自适应地聚合类特定参数来应对数据异质性。这使得无需直接访问客户端数据即可实现有效的全局模型优化。在三个广泛使用的数据集上进行的大量实验证明了所引入框架的有效性和优越性。
英文摘要：
Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge. Nonetheless, existing methods deal with continuous data streams in a centralized manner, limiting their applicability in scenarios that prioritize data privacy and security. To this end, this paper introduces federated few-shot class-incremental learning, a decentralized machine learning paradigm tailored to progressively learn new classes from scarce data distributed across multiple clients. In this learning paradigm, clients locally update their models with new classes while preserving data privacy, and then transmit the model updates to a central server where they are aggregated globally. However, this paradigm faces several issues, such as difficulties in few-shot learning, catastrophic forgetting, and data heterogeneity. To address these challenges, we present a synthetic data-driven framework that leverages replay buffer data to maintain existing knowledge and facilitate the acquisition of new knowledge. Within this framework, a noise-aware generative replay module is developed to fine-tune local models with a balance of new and replay data, while generating synthetic data of new classes to further expand the replay buffer for future tasks. Furthermore, a class-specific weighted aggregation strategy is designed to tackle data heterogeneity by adaptively aggregating class-specific parameters based on local models performance on synthetic data. This enables effective global model optimization without direct access to client data. Comprehensive experiments across three widely-used datasets underscore the effectiveness and preeminence of the introduced framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
