State-of-the-art recommender systems are increasingly focused on optimizing implementation efficiency, such as enabling on-device recommendations under memory constraints. Current methods commonly use lightweight embe...
详细信息
State-of-the-art recommender systems are increasingly focused on optimizing implementation efficiency, such as enabling on-device recommendations under memory constraints. Current methods commonly use lightweight embeddings for users and items or employ compact embeddings to enhance reusability and reduce memory usage. However, these approaches consider only the coarse-grained aspects of embeddings, overlooking subtle semantic nuances. This limitation results in an adversarial degradation of meta-embedding performance, impeding the system's ability to capture intricate relationships between users and items, leading to suboptimal recommendations. To address this, we propose a novel approach to efficiently learn meta-embeddings with varying grained and apply fine-grained meta-embeddings to strengthen the representation of their coarse-grained counterparts. Specifically, we introduce a recommender system based on a graph neural network, where each user and item is represented as a node. These nodes are directly connected to coarse-grained virtual nodes and indirectly linked to fine-grained virtual nodes, facilitating learning of multi-grained semantics. Fine-grained semantics are captured through sparse meta-embeddings, which dynamically balance embedding uniqueness and memory constraints. To ensure their sparseness, we rely on initialization methods such as sparse principal component analysis combined with a soft thresholding activation function. Moreover, we propose a weight-bridging update strategy that aligns coarse-grained meta-embedding with several fine-grained meta-embeddings based on the underlying semantic properties of users and items. Comprehensive experiments demonstrate that our method outperforms existing baselines. The code of our proposal is available at https://***/htyjers/C2F-MetaEmbed.
This paper first estimated the infectious capacity of COVID-19 based on the time series evolution data of confirmed cases in multiple countries. Then, a method to infer the cross-regional spread speed of COVID-19 was ...
详细信息
This paper first estimated the infectious capacity of COVID-19 based on the time series evolution data of confirmed cases in multiple countries. Then, a method to infer the cross-regional spread speed of COVID-19 was introduced in this paper, which took the gross domestic product(GDP) of each region as one of the factors that affect the spread speed of COVID-19 and studied the relationship between the GDP and the infection density of each region(China's Mainland, the United States, and EU countries). In addition, the geographic distance between regions was also considered in this method and the effect of geographic distance on the spread speed of COVID-19 was studied. Studies have shown that the probability of mutual infection of these two regions decreases with increasing geographic distance. Therefore, this paper proposed an epidemic disease spread index based on GDP and geographic distance to quantify the spread speed of COVID-19 in a region. The analysis results showed a strong correlation between the epidemic disease spread index in a region and the number of confirmed cases. This finding provides reasonable suggestions for the control of epidemics. Strengthening the control measures in regions with higher epidemic disease spread index can effectively control the spread of epidemics.
Fluorescence imaging techniques represent essential tools in in vitro,preclinical,and clinical *** this study,an improved one-step hydrothermal method to synthesize citric acid(CA)modifiedα-NaYbF_(4):2%Er^(3+)nanocry...
详细信息
Fluorescence imaging techniques represent essential tools in in vitro,preclinical,and clinical *** this study,an improved one-step hydrothermal method to synthesize citric acid(CA)modifiedα-NaYbF_(4):2%Er^(3+)nanocrystals was *** introduction of various doping ions into NaYbF_(4):2%Er^(3+)and the different valence states of the same ions affect both the crystal size and upconversion luminesce *** fore,we investigated the upconversion luminesce nce enha ncement of NaYbF_(4):2%Er^(3+)by ion doping and find that the upconversion luminescence intensity of the upconversion nanoparticles(UCNPs)co-doped with 5 mol%Fe^(2+)ions shows the greatest enhancement,especially for red emission at654 ***,HeLa cells incubated with UCNPs allow for imaging with strong red upconversion emission detectio *** laser scanning microscope(CLSM)fluorescent images of HeLa cells indicate that NaYbF_(4):2%Er/5%Fe^(2+)leads to a clear outline and improves visualization of the cell *** addition,the CA coated NaYbF_(4):2%Er^(3+)/5%Fe^(2+)nanoparticles and NaYbF_(4):2%Er^(3+)/5%Fe^(2+)show low cytotoxicity in HeLa *** imaging reveals the efficiency of these UCNPs to analyze the lungs,liver,and ***,these results indicate that the Cit-NaYbF_(4):2%Er^(3+)/5%Fe^(2+)UCNPs are efficient nanoprobes for fluorescence molecular to mography.
Frame aggregation is fully supported in the newly published IEEE 802.11ax standard to improve throughput. With frame aggregation, a mobile station combines multiple subframes into an aggregate MAC service data unit(A-...
详细信息
Frame aggregation is fully supported in the newly published IEEE 802.11ax standard to improve throughput. With frame aggregation, a mobile station combines multiple subframes into an aggregate MAC service data unit(A-MSDU) or an aggregate MAC protocol data unit(A-MPDU) for transmission. It is challenging for a mobile station in 802.11ax WLANs to set an appropriate number of subframes being included in an AMSDU or A-MPDU. This problem is solved in this paper by the proposed equal interval frame aggregation(EIFA)scheme which lets a mobile station aggregate at most k subframes at a fixed time period of T. A novel Markov model is developed for deriving the probability of number of subframes in the data buffer at the mobile station,resulting in the throughput and packet delay in the ***, the optimization problem of maximizing the throughput with the constraint on delay is formulated,and its solution leads to the optimal pair of parameters k and T for improving throughput in the EIFA *** results show the EIFA has a higher throughput than the ones in which the mobile station chooses the minimum, the maximum, or a random number of subframes.
Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually...
详细信息
Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually migrate data at a granularity of 4 KB pages,and thus waste memory bandwidth and DRAM *** this paper,we propose Mocha,a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically,but manages them in a cache/memory *** the commercial NVM device-Intel Optane DC Persistent Memory Modules(DCPMM)actually access the physical media at a granularity of 256 bytes(an Optane block),we manage the DRAM cache at the 256-byte size to adapt to this feature of *** design not only enables fine-grained data migration and management for the DRAM cache,but also avoids write amplification for Intel Optane *** also create an Indirect Address Cache(IAC)in Hybrid Memory Controller(HMC)and propose a reverse address mapping table in the DRAM to speed up address translation and cache ***,we exploit a utility-based caching mechanism to filter cold blocks in the NVM,and further improve the efficiency of the DRAM *** implement Mocha in an architectural *** results show that Mocha can improve application performance by 8.2%on average(up to 24.6%),reduce 6.9%energy consumption and 25.9%data migration traffic on average,compared with a typical hybrid memory architecture-HSCC.
The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the...
详细信息
The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.
Missing values pose a formidable obstacle in multivariate time series analysis. Existing imputation methods rely on entangled representations that struggle to simultaneously capture multiple orthogonal time-series pat...
详细信息
Against the backdrop of electromagnetic space integration,the radio system of equipment platforms,such as next-generation aircraft,must possess multifunctional integration and electromagnetic stealth ***,the equipment...
详细信息
Against the backdrop of electromagnetic space integration,the radio system of equipment platforms,such as next-generation aircraft,must possess multifunctional integration and electromagnetic stealth ***,the equipment platforms need to evolve towards flat *** requirements pose significant technical challenges for antenna system *** antenna must possess ultra-wideband to facilitate multi-function integration through the use of continuous radio frequency synthetic *** order to ensure good aerodynamics of the flat airborne platform,it is required to implement conformal design,while the ultra-low profile is the greatest challenge in conformal *** this background,this work proposes a novel airborne tightly coupled antenna with ultra-low profile,ultra-wideband,and vertical-polarized omnidirectional *** antenna unit utilizes a long slot structure and implements circular conformal design,where the resistive frequency selection surface is used to expand the operating *** antenna has a profile height of only 0.047 times the low-frequency *** and measurement results show that it achieves an impedance bandwidth of nearly 12∶1 with omnidirectional beam coverage,which meets the requirements of multifunctional future airborne antennas.
Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concer...
详细信息
Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concerns regarding their vulnerability to potential *** attacks turn into a major menace to federated learning on account of their concealed property and potent destructive *** altering the local model during routine machine learning training,attackers can easily contaminate the global *** detection and aggregation solutions mitigate certain threats,but they are still insufficient to completely eliminate the influence generated by ***,federated unlearning that can remove unreliable models while maintaining the accuracy of the global model has become a *** some existing federated unlearning approaches are rather difficult to be applied in large neural network models because of their high computational ***,we propose SlideFU,an efficient anti-poisoning attack federated unlearning *** primary concept of SlideFU is to employ sliding window to construct the training process,where all operations are confined within the *** design a malicious detection scheme based on principal component analysis(PCA),which calculates the trust factors between compressed models in a low-cost way to eliminate unreliable *** confirming that the global model is under attack,the system activates the federated unlearning process,calibrates the gradients based on the updated direction of the calibration *** on two public datasets demonstrate that our scheme can recover a robust model with extremely high efficiency.
Due to their biological interpretability,memristors are widely used to simulate synapses between artificial neural *** a type of neural network whose dynamic behavior can be explained,the coupling of resonant tunnelin...
详细信息
Due to their biological interpretability,memristors are widely used to simulate synapses between artificial neural *** a type of neural network whose dynamic behavior can be explained,the coupling of resonant tunneling diode-based cellular neural networks(RTD-CNNs)with memristors has rarely been reported in the ***,this paper designs a coupled RTD-CNN model with memristors(RTD-MCNN),investigating and analyzing the dynamic behavior of the *** on this model,a simple encryption scheme for the protection of digital images in police forensic applications is *** results show that the RTD-MCNN can have two positive Lyapunov exponents,and its output is influenced by the initial values,exhibiting ***,a set of amplitudes in its output sequence is affected by the internal parameters of the memristor,leading to nonlinear ***,the rich dynamic behaviors described above make the RTD-MCNN highly suitable for the design of chaos-based encryption schemes in the field of privacy *** tests and security analyses validate the effectiveness of this scheme.
暂无评论