Recently,many researches have created adversarial samples to enrich the diversity of training data for improving the text classification performance via reducing the loss incurred in the neural network ***,existing st...
详细信息
Recently,many researches have created adversarial samples to enrich the diversity of training data for improving the text classification performance via reducing the loss incurred in the neural network ***,existing studies have focused solely on adding perturbations to the input,such as text sentences and embedded representations,resulting in adversarial samples that are very similar to the original *** adversarial samples can not significantly improve the diversity of training data,which restricts the potential for improved classification *** alleviate the problem,in this paper,we extend the diversity of generated adversarial samples based on the fact that adding different disturbances between different layers of neural network has different *** propose a novel neural network with perturbation strategy(PTNet),which generates adversarial samples by adding perturbation to the intrinsic representation of each hidden layer of the neural ***,we design two different perturbation ways to perturb each hidden layer:1)directly adding a certain threshold perturbation;2)adding the perturbation in the way of adversarial *** above settings,we can get more perturbed intrinsic representations of hidden layers and use them as new adversarial samples,thus improving the diversity of the augmented training *** validate the effectiveness of our approach on six text classification datasets and demonstrate that it improves the classification ability of the *** particular,the classification accuracy on the sentiment analysis task improved by an average of 1.79%and on question classification task improved by 3.2%compared to the BERT baseline,respectively.
Though obstruction-free progress property is weaker than other non-blocking properties including lock-freedom and wait-freedom,it has advantages that have led to the use of obstruction-free implementations for softwar...
详细信息
Though obstruction-free progress property is weaker than other non-blocking properties including lock-freedom and wait-freedom,it has advantages that have led to the use of obstruction-free implementations for software transactional memory(STM)and in anonymous and fault-tolerant distributed ***,existing work can only verify obstruction-freedom of specific data structures(e.g.,STM and list-based algorithms).In this paper,to fill this gap,we propose a program logic that can formally verify obstruction-freedom of practical implementations,as well as verify linearizability,a safety property,at the same *** also propose informal principles to extend a logic for verifying linearizability to verifying *** this approach,the existing proof for linearizability can be reused directly to construct the proof for both linearizability and ***,we have successfully applied our logic to verifying a practical obstruction-free double-ended queue implementation in the first classic paper that has proposed the definition of obstruction-freedom.
Currently,the main idea of iterative rendering methods is to allocate a fixed number of samples to pixels that have not been fully rendered by calculating the completion *** is obvious that this strategy ignores the c...
详细信息
Currently,the main idea of iterative rendering methods is to allocate a fixed number of samples to pixels that have not been fully rendered by calculating the completion *** is obvious that this strategy ignores the changes in pixel values during the previous rendering process,which may result in additional iterative operations.
Thanks to its ubiquity,using radio frequency (RF) signals for sensing has found widespread *** traditional integrated sensing and communication systems,such as joint radar-communication systems,common sensing tasks in...
Thanks to its ubiquity,using radio frequency (RF) signals for sensing has found widespread *** traditional integrated sensing and communication systems,such as joint radar-communication systems,common sensing tasks include target localization and ***,increasingly intelligent systems,such as smart agriculture,lowaltitude economy,and smart healthcare,have demanded more comprehensive and continuous information sensing capabilities to support higher-level *** sensing has the potential to offer both spatial and temporal continuity,meeting the multi-dimensional sensing needs of these intelligent ***,numerous advanced systems have been proposed,expanding the application scope of RF sensing to be more pervasive,including discrete state ubiquitous sensing tasks (such as material identification [1]),and continuous state ubiquitous sensing tasks (such as health monitoring [2]).With the advent of the 6G era,it is anticipated that the sensing potential of RF systems will be further unleashed.
In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems,...
详细信息
In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems, which will relieve the burden on end-users across all industry sectors by featuring AI-enhanced functionalities, such as personalized and automated in-database AI-powered analytics, and selfdriving capabilities for improved system performance. In this paper, we explore the evolution of data systems with a focus on deepening the fusion of AI and DB. We present NeurDB, an AI-powered autonomous data system designed to fully embrace AI design in each major system component and provide in-database AI-powered analytics. We outline the conceptual and architectural overview of NeurDB, discuss its design choices and key components, and report its current development and future plan.
Visible and infrared image fusion(VIF)aims to combine information from visible and infrared images into a single fused *** VIF methods usually employ a color space transformation to keep the hue and saturation from th...
详细信息
Visible and infrared image fusion(VIF)aims to combine information from visible and infrared images into a single fused *** VIF methods usually employ a color space transformation to keep the hue and saturation from the original visible ***,for fast VIF methods,this operation accounts for the majority of the calculation and is the bottleneck preventing faster *** this paper,we propose a fast fusion method,FCDFusion,with little color *** preserves color information without color space transformations,by directly operating in RGB color *** incorporates gamma correction at little extra cost,allowing color and contrast to be rapidly *** regard the fusion process as a scaling operation on 3D color vectors,greatly simplifying the calculations.A theoretical analysis and experiments show that our method can achieve satisfactory results in only 7 FLOPs per *** to state-of-theart fast,color-preserving methods using HSV color space,our method provides higher contrast at only half of the computational *** further propose a new metric,color deviation,to measure the ability of a VIF method to preserve *** is specifically designed for VIF tasks with color visible-light images,and overcomes deficiencies of existing VIF metrics used for this *** code is available at https://***/HeasonLee/FCDFusion.
This paper aimed to propose two algorithms,DA-M and RF-M,of reducing the impact of multipath interference(MPI)on intensity modulation direct detection(IM-DD)systems,particularly for four-level pulse amplitude modulati...
详细信息
This paper aimed to propose two algorithms,DA-M and RF-M,of reducing the impact of multipath interference(MPI)on intensity modulation direct detection(IM-DD)systems,particularly for four-level pulse amplitude modulation(PAM4)***-M reduced the fluctuation by averaging the signal in blocks,RF-M estimated MPI by subtracting the decision value of the corresponding block from the mean value of a signal block,and then generated interference-reduced samples by subtracting the interference signal from the product of the corresponding MPI estimate and then weighting *** paper firstly proposed to separate the signal before decision-making into multiple blocks,which significantly reduced the complexity of DA-M and *** results showed that the MPI noise of 28 GBaud IMDD system under the linewidths of 1e5 Hz,1e6 Hz and 10e6 Hz can be effectively alleviated.
Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)***,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approache...
详细信息
Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)***,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approaches the ground-truth image ***,the multistage generation strategy results in complex T2I ***,this study proposes a novel feature-grounded single-stage T2I model,which considers the“real”distribution learned from training images as one input and introduces a worst-case-optimized similarity measure into the loss function to enhance the model's generation *** results on two benchmark datasets demonstrate the competitive performance of the proposed model in terms of the Frechet inception distance and inception score compared to those of some classical and state-of-the-art models,showing the improved similarities among the generated image,text,and ground truth.
Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning ***,any metapaths consistin...
详细信息
Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning ***,any metapaths consisting of multiple,simple metarelations must be driven by domain *** sensitive,expensive,and limited metapaths severely reduce the flexibility and scalability of the existing models.A metapath-free,scalable representation learning model,called Metarelation2vec,is proposed for HNs with biased joint learning of all metarelations in a bid to address this ***,a metarelation-aware,biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given ***,grouped nodes by the type,a common and shallow skip-gram model is used to separately learn structural proximity for each node ***,grouped links by the type,a novel and shallow model is used to separately learn the semantic proximity for each link ***,supervised by the cooperation probabilities of all meta-words,the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs,ensuring the accuracy and scalability of the *** experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.
Inductive knowledge graph embedding(KGE)aims to embed unseen entities in emerging knowledge graphs(KGs).The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring...
详细信息
Inductive knowledge graph embedding(KGE)aims to embed unseen entities in emerging knowledge graphs(KGs).The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring entities and relations with graph neural networks(GNNs).However,these methods rely on the existing neighbors of unseen entities and suffer from two common problems:data sparsity and feature ***,the data sparsity problem means unseen entities usually emerge with few triplets containing insufficient ***,the effectiveness of the features extracted from original KGs will degrade when repeatedly propagating these features to represent unseen entities in emerging KGs,which is termed feature smoothing *** tackle the two problems,we propose a novel model entitled Meta-Learning Based Memory Graph Convolutional Network(MMGCN)consisting of three different components:1)the two-layer information transforming module(TITM)developed to effectively transform information from original KGs to emerging KGs;2)the hyper-relation feature initializing module(HFIM)proposed to extract type-level features shared between KGs and obtain a coarse-grained representation for each entity with these features;and 3)the meta-learning training module(MTM)designed to simulate the few-shot emerging KGs and train the model in a meta-learning *** extensive experiments conducted on the few-shot link prediction task for emerging KGs demonstrate the superiority of our proposed model MMGCN compared with state-of-the-art methods.
暂无评论