Federated tree-based models are popular in many real-world applications owing to their high accuracy and good interpretability. However, the classical synchronous method causes inefficient federated tree model training due to tree node dependencies. Inspired by speculative execution techniques in modern high-performance processors, this paper proposes SpecFL, a novel and efficient speculative federated learning system. Instead of simply waiting, SpecFL optimistically predicts the outcome of the prior tree node. By resolving tree node dependencies with a split point predictor, the training tasks of child tree nodes can be executed speculatively in advance via separate threads. This speculation enables cross-layer concurrent training, thus significantly reducing the waiting time. Furthermore, we propose a greedy speculation policy to exploit speculative training for deeper inter-layer concurrent training and an eager rollback mechanism for lossless model quality. We implement SpecFL and evaluate its efficiency in a real-world federated learning setting with six public datasets. The evaluation results demonstrate that SpecFL can be 2.08-3.33x and 2.14-3.44x faster than the state-of-the-art GBDT and RF implementations, respectively.

In recent studies, object detection of satellite remote sensing images by deep learning method has emerged as a major concern in the fields of environmental detection, military investigation and geography. The current object detection practice, such as Faster RCNN, SSD and YOLO (v1-v5), is using new CNN based deep learning method to replace conventional sliding window and handcraft detectors, and it has achieved impressive success for some specific fields in natural scene images. However, in the task of satellite remote sensing images, it's still a major challenge that the existing models cannot guarantee the multi-scale object detection and real-time monitoring with high accuracy. To address these challenges, in this paper, we proposed SeMo- YOLO, a novel one stage deep learning detector based on the combination of MobileNet, YOLOv3 and channel attention mechanism. Experiment result shows that SeMo-YOLO and it's tiny version can achieve significant improvement in the aspect of accuracy for multiscale remote sensing object detection. It has a mAP (@.5) of 92%, 94%, and 95% on RSOD, HRRSD2019 and SAR-SSDD datasets respectively, which has bring significant improvement in detection precision than the existing state-of-the-art Networks. In addition, the weight parameters of the proposed model are less than the existing YOLOv3 so as to it can achieve relatively higher detection speed near real time.