Magnetic resonance imaging plays an important role in auxiliary diagnosis and brain exploration. However, limited by hardware, scanning time and cost, it's challenging to acquire high-resolution (HR) magnetic reso...
详细信息
Short carrier lifetimes is a key challenge limiting the open-circuit voltage (VOC) and power conversion efficiency (PCE) of kesterite Cu2ZnSn(S,Se)4 (CZTSSe) solar cells. In this work, for the first time, lanthanide e...
详细信息
The world indicators released by the World Bank or other organizations usually give the basic public knowledge about the world. However, separate and static index lacks the complex interplay among different indicators...
详细信息
With the increasing number of services and their homogenization, the use of Quality of Service (QoS) for recommendations has become necessary. However, existing QoS prediction solutions have limitations in solving the...
With the increasing number of services and their homogenization, the use of Quality of Service (QoS) for recommendations has become necessary. However, existing QoS prediction solutions have limitations in solving the noise and label imbalance problems of dataset, which greatly limit the improvement of QoS prediction accuracy. In this paper, we propose FSNet that contains a feature distribution smoothing module and an improved W-Huber loss function. The feature distribution smoothing module mitigates the effect of noise problem by fitting potential Gaussian distribution of known features with a supervised feedforward neural network. W-Huber loss function mitigates the impact of label imbalance problem on QoS prediction by reweighting the two components of Huber loss function. We conduct extensive experiments on real large-scale QoS dataset, and the results demonstrate that the proposed FSNet method outperforms existing QoS prediction methods.
This paper studies quasi-Newton methods for solving nonlinear equations. We propose block variants of both good and bad Broyden's methods, which enjoy explicit local superlinear convergence rates. Our block good B...
This paper studies quasi-Newton methods for solving nonlinear equations. We propose block variants of both good and bad Broyden's methods, which enjoy explicit local superlinear convergence rates. Our block good Broyden's method has a faster condition-number-free convergence rate than existing Broyden's methods because it takes the advantage of multiple rank modification on Jacobian estimator. On the other hand, our block bad Broyden's method directly estimates the inverse of the Jacobian provably, which reduces the computational cost of the iteration. Our theoretical results provide some new insights on why good Broyden's method outperforms bad Broyden's method in most of the cases. The empirical results also demonstrate the superiority of our methods and validate our theoretical analysis.
作者：
Liu, HaozheZhang, WentianLiu, FengWu, HaoqianShen, LinlinThe Computer Vision Institute
College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society The National Engineering Laboratory for Big Data System Computing Technology The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China
The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by inform...
详细信息
An increasing number of deep learning methods is being applied to quantify the perception of urban environments, study the relationship between urban appearance and resident safety, and improve urban appearance. Most ...
详细信息
An increasing number of deep learning methods is being applied to quantify the perception of urban environments, study the relationship between urban appearance and resident safety, and improve urban appearance. Most advanced methods extract image feature representations from street-level images through conventional visual computation algorithms or deep convolutional neural networks and then directly predict the results using features. Unfortunately, these methods take color and texture information together during processing. Color and texture are prime image features, and they affect human perception and judgment differently. We argue that color and texture should be operated differently; therefore, we formulate an end-to-end learning methodology to process input images according to color and texture information before inputting it into the neural network. The processed images and the original image constitute three input streams for the triad attention ranking convolutional neural network(AR-CNN) model proposed in this *** accordance with the aspects of color and texture, an improved attention mechanism in the convolution layer is proposed. Our objective is to obtain the scores of humans on urban appearance in accordance with the prediction results computed from pairwise comparisons generated by the AR-CNN model.
False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrie...
详细信息
Federated Learning (FL) is a distributed machine learning framework that enhances privacy by enabling multiple participants to train a global model without sharing their raw data. However, FL still faces the threat po...
详细信息
ISBN:
(数字)9798350351255
ISBN:
(纸本)9798350351262
Federated Learning (FL) is a distributed machine learning framework that enhances privacy by enabling multiple participants to train a global model without sharing their raw data. However, FL still faces the threat posed by data and Byzantine attacks (e.g., data poisoning and model poisoning attacks) from malicious clients aimed to decrease the FL global training accuracy. Previous studies have proposed solutions to improve the robustness of FL systems. However, these robust approaches have not effectively defended against Byzantine attacks from malicious clients in non-Independent and Identically Distributed (non-IID) environments, decreasing overall training accuracy. In this work to address this issues, we propose a new defence framework that aims to enhance model accuracy against Byzantine attacks from malicious clients in non-IID environments. In our approach, the central server performs the Inverse Deep Learning Gradient attack using the gradient data submitted by users in each round, obtaining an inversed artificial gradient. We then assess the squared L2 norm difference between this inversed gradient and the actual gradients to detect malicious clients. Simultaneously, we assign weights to each client involved in the aggregation based on differences in the squared L2 norm, aiming to minimize the impact of malicious actors on the overall model. We have experimentally evaluated our method and demonstrated its ability to maintain training accuracy under attack in non-IID environments using standard datasets.
With the development of information technology, the medical field has accumulated a large amount of medical data, which continues to grow. Efficient extraction and effective utilization of knowledge from this vast amo...
详细信息
ISBN:
(数字)9798350377613
ISBN:
(纸本)9798350377620
With the development of information technology, the medical field has accumulated a large amount of medical data, which continues to grow. Efficient extraction and effective utilization of knowledge from this vast amount of medical data are crucial for realizing its immense value. Traditional knowledge acquisition algorithms face challenges in effectively identifying and acquiring new types of knowledge in practical applications. To address this, this paper proposes a class-incremental learning method based on a prototype network gating mechanism, called PGMoE. This method integrates multiple experts through a prototype network-based gating mechanism, dynamically adjusting the model's response to new and old knowledge, thereby effectively mitigating the issue of catastrophic forgetting in class-incremental learning. PGMoE not only improves the stability and accuracy of the model in continuous learning processes but also ensures the model's ability to remember historical knowledge. Comparative experiments on multiple datasets with existing class-incremental learning methods demonstrate that PGMoE has significant performance advantages in handling continuous learning tasks.
暂无评论