RESUMO
Federated Learning is a distributed machine learning framework that aims to train a global shared model while keeping their data locally, and previous researches have empirically proven the ideal performance of federated learning methods. However, recent researches found the challenge of statistical heterogeneity caused by the non-independent and identically distributed (non-IID), which leads to a significant decline in the performance of federated learning because of the model divergence caused by non-IID data. This statistical heterogeneity is dramatically restricts the application of federated learning and has become one of the critical challenges in federated learning. In this paper, a dynamic weighted model aggregation algorithm based on statistical heterogeneity for federated learning called DWFed is proposed, in which the index of statistical heterogeneity is firstly quantitatively defined through derivation. Then the index is used to calculate the weights of each local model for aggregating federated model, which is to constrain the model divergence caused by non-IID data. Multiple experiments on public benchmark data set reveal the improvements in performance and robustness of the federated models in heterogeneous settings.
RESUMO
Relation extraction is a popular subtask in natural language processing (NLP). In the task of entity relation joint extraction, overlapping entities and multi-type relation extraction in overlapping triplets remain a challenging problem. The classification of relations by sharing the same probability space will ignore the correlation information among multiple relations. A relational-adaptive entity relation joint extraction model based on multi-head self-attention and densely connected graph convolution network (which is called MA-DCGCN) is proposed in the paper. In the model, the multi-head attention mechanism is specifically used to assign weights to multiple relation types among entities so as to ensure that the probability space of multiple relation is not mutually exclusive. This mechanism also predicts the strength of the relationship between various relationship types and entity pairs flexibly. The structure information of deeper level in the text graph is extracted by the densely connected graph convolution network, and the interaction information of entity relation is captured. To demonstrate the superior performance of our model, we conducted a variety of experiments on two widely used public datasets, NYT and WebNLG. Extensive results show that our model achieves state-of-the-art performance. Especially, the detection effect of overlapping triplets is significantly improved compared with the several existing mainstream methods.
RESUMO
Microaneurysms (MAs) are the earliest detectable diabetic retinopathy (DR) lesions. Thus, the ability to automatically detect MAs is critical for the early diagnosis of DR. However, achieving the accurate and reliable detection of MAs remains a significant challenge due to the size and complexity of retinal fundus images. Therefore, this paper presents a novel MA detection method based on a deep neural network with a multilayer attention mechanism for retinal fundus images. First, a series of equalization operations are performed to improve the quality of the fundus images. Then, based on the attention mechanism, multiple feature layers with obvious target features are fused to achieve preliminary MA detection. Finally, the spatial relationships between MAs and blood vessels are utilized to perform a secondary screening of the preliminary test results to obtain the final MA detection results. We evaluated the method on the IDRiD_VOC dataset, which was collected from the open IDRiD dataset. The results show that our method effectively improves the average accuracy and sensitivity of MA detection.