Abstract: Provided is a negative electrode plate, comprising: a negative electrode current collector and a first negative electrode active material layer. The first negative electrode active material layer is arranged on at least one surface of the negative electrode current collector, wherein, components of the first negative electrode active material layer comprise, by mass: 30%-70% of a silicon-based material, 15%-40% of a binder and 15%-40% of a conductive agent.

Abstract: Provided are a secondary battery and a battery module, battery pack, and electric apparatus containing such secondary battery. The secondary battery includes: a positive electrode plate including a positive electrode film layer; a separator; and a negative electrode plate. The negative electrode plate includes: a first negative electrode film layer, the first negative electrode film layer being provided opposite the positive electrode film layer with the separator therebetween; and a second negative electrode film layer, the second negative electrode film layer including a negative electrode film layer not provided opposite the positive electrode film layer, and the second negative electrode film layer including a central region and a peripheral region surrounding the central region, where a lithium source used for supplementing lithium to the first negative electrode film layer is stored in at least a portion of the peripheral region of the second negative electrode film layer.

Abstract: A secondary battery is provided, including a positive electrode plate and a negative electrode plate. The positive electrode plate includes a positive electrode current collector and a positive electrode film layer provided on two surfaces of the positive electrode current collector, the negative electrode plate includes a negative electrode current collector and a negative electrode film layer provided on two surfaces of the negative electrode current collector, and the negative electrode film layer includes a reaction zone opposite the positive electrode film layer and a non-reaction zone not opposite the positive electrode film layer, where a lithium supplement layer and a barrier layer are provided on the non-reaction zone. A preparation method of secondary battery, a battery module, a battery pack, and an electric apparatus are also provided.

Abstract: Embodiments of the present disclosure provide hierarchical, differential privacy enhancements to federated, machine learning. Local machine learning models may be generated and/or trained by data owners participating in the federated learning framework based on their respective data sets. Noise corresponding to and satisfying a first privacy loss requirement are introduced to the data owners' respective data sets, and noise corresponding to and satisfying a first privacy loss requirement are introduced to the local models generated and/or trained by the data owners. The data owners transmit model data corresponding to their respective local models to a coordinator, which in turn aggregates the data owners' model data. After introducing noise corresponding to and satisfying a third privacy loss requirement to the aggregated model data, the coordinator transmits the aggregated model data to the data owners to facilitate updating and/or re-training on their respective machine learning models.

Abstract: Embodiments of the present disclosure provide hierarchical, differential privacy enhancements to federated, machine learning. Local machine learning models may be generated and/or trained by data owners participating in the federated learning framework based on their respective data sets. Noise corresponding to and satisfying a first privacy loss requirement are introduced to the data owners' respective data sets, and noise corresponding to and satisfying a first privacy loss requirement are introduced to the local models generated and/or trained by the data owners. The data owners transmit model data corresponding to their respective local models to a coordinator, which in turn aggregates the data owners' model data. After introducing noise corresponding to and satisfying a third privacy loss requirement to the aggregated model data, the coordinator transmits the aggregated model data to the data owners to facilitate updating and/or re-training on their respective machine learning models.