Matching spatial relation graphs using a constrained partial permutation strategy

A constrained partial permutation strategy is proposed for matching spatial relation graph (SRG), which is used in our sketch input and recognition system Smart Sketchpad for representing the spatial relationship among the components of a graphic object. Using two kinds of matching constraints dynamically generated in the matching process, the proposed approach can prune most improper mappings between SRGs during the matching process. According to our theoretical analysis in this paper, the time complexity of our approach is O(n 2) in the best case, and O(n!) in the worst case, which occurs infrequently. The spatial complexity is always O(n) for all cases. Implemented in Smart Sketchpad, our proposed strategy is of good performance.

Graph Transformers研究进展综述

随着图结构数据在各种实际场景中的广泛应用,对其进行有效建模和处理的需求日益增加。Graph Transformers(GTs)作为一类使用Transformers处理图数据的模型,能够有效缓解传统图神经网络(GNN)中存在的过平滑和过挤压等问题,因此可以学习到更好的特征表示。根据对近年来GTs相关文献的研究,将现有的模型架构分为两类:第一类通过绝对编码和相对编码向Transformers中加入图的位置和结构信息,以增强Transformers对图结构数据的理解和处理能力;第二类根据不同的方式(串行、交替、并行)将GNN与Transformers进行结合,以充分利用两者的优势。介绍了GTs在信息安全、药物发现和知识图谱等领域的应用,对比总结了不同用途的模型及其优缺点。最后,从可扩展性、复杂图、更好的结合方式等方面分析了GTs未来研究面临的挑战。

Effect of Partially Coherent Light on the Contrast of Speckle Patterns Obtained Using Digital Image Processing of Speckle Photography

The paper is devoted to study theoretically, the effects of some parameters on the visibility of the speckle patterns. For this propose, a theoretical model for a periodic rough surface was considered. Using this theoretical model, the effects of grain height, its density, the band width and spectral distribution of the line profile (Gaussian and Lorentzian) illuminating a rough surface on the visibility of speckle pattern are investigated. An experimental setup was constructed to study the effect of surface roughness and coherence of the illuminating light beam on the contrast of speckle pattern. The general behavior of the experimental results, which agree with published data, is compatible with the new theoretical model.

Absence of asymptomatic unruptured renal artery pseudoaneurysm on contrast-enhanced computed tomography after robot-assisted partial nephrectomy without parenchymal renorrhaphy

Objective:To assess the incidence of asymptomatic unruptured renal artery pseudoaneurysm(RAP)on contrast-enhanced computed tomography(CE-CT)after robot-assisted partial nephrectomy(RAPN)without parenchymal renorrhaphy.Methods:From May 2016 to December 2017,78 patients underwent RAPN for renal tumors.Inner suture was performed in the opened collecting system or renal sinus,whereas parenchymal renorrhaphy was not.For hemostasis,the soft coagulation system was used,and absorbable hemostats were placed on the resection bed.CE-CT was carried out within 7 days after surgery.Data on these patients were prospectively collected.A single radiologist determined the diagnosis of RAP.Results:Median(range)data were as follows:Patient age,65(19-82)years;radiographic tumor size,30(12-95)mm;operating time,166(102-294)min;warm ischemic time,16(7-67)min;and blood loss,15(0-4450)mL.One patient(1.6%)required a perioperative blood transfusion.No patient required conversion to open surgery or nephrectomy.CE-CT was carried out at median 6(3-7)days after surgery.CE-CT showed no RAP development in all 61 patients.Urinary leakage was not observed.One patient had acute cholecystitis,a postoperative complication classified as Clavien-Dindo grade higher than 3,which was treated with cholecystectomy.Positive surgical margin was identified in four patients(6.6%).Conclusion:RAPN using soft coagulation and absorbable hemostats without renorrhaphy appears to be feasible and safe.Our technique could eliminate the risk of RAP.

基于Graph Transformer的半监督异配图表示学习模型

现有的图卷积网络(GCN)模型基于同配性假设,无法直接应用于异配图的表示学习,且许多异配图表示学习的研究工作受消息传递机制的限制,导致节点特征混淆和特征过度挤压而出现过平滑问题。针对这些问题,提出一种基于Graph Transformer的半监督异配图表示学习模型HPGT(HeteroPhilic Graph Transformer)。首先,使用度连接概率矩阵采样节点的路径邻域,再通过自注意力机制自适应地聚合路径上的节点异配连接模式,编码得到节点的结构信息,用节点的原始属性信息和结构信息构建Transformer层的自注意力模块;其次,将每个节点自身的隐层表示与它的邻域节点的隐层表示分离更新以避免节点通过自注意力模块聚合过量的自身信息,再把每个节点表示与它的邻域表示连接,得到单个Transformer层的输出,另外,将所有的Transformer层的输出跳连到最终的节点隐层表示以防止中间层信息丢失;最后,使用线性层和Softmax层将节点的隐层表示映射到节点的预测标签。实验结果表明,与无结构编码(SE)的模型相比,基于度连接概率的SE能为Transformer层的自注意力模块提供有效的偏差信息,HPGT平均准确率提升0.99%~11.98%;与对比模型相比,在异配数据集(Texas、Cornell、Wisconsin和Actor)上,模型节点分类准确率提升0.21%~1.69%,在同配数据集(Cora、CiteSeer和PubMed)上,节点分类准确率分别达到了0.8379、0.7467和0.8862。以上结果验证了HPGT具有较强的异配图表示学习能力,尤其适用于强异配图节点分类任务。

A Partially Non-Cryptographic Security Routing Protocol in Mobile Ad Hoc Networks

In this paper, we propose a partially non-cryptographic security routing protocol （PNCSR） that protects both routing and data forwarding operations through the same reactive approach. PNCSR only apply public-key cryptographic system in managing token, but it doesn＇t utilize any cryptographic primitives on the routing messages. In PNCSR, each node is fair. Local neighboring nodes collaboratively monitor each other and sustain each other. It also uses a novel credit strategy which additively increases the token lifetime each time a node renews its token. We also analyze the storage, computation, and communication overhead of PNCSR, and provide a simple yet meaningful overhead comparison. Finally, the simulation results show the effectiveness of PNCSR in various situations.

融合Partial卷积与残差细化的遥感影像建筑物提取算法

由于高空间分辨率遥感图像中背景与建筑物对象的相似度高,导致网络难以兼顾不同大小的建筑物,建筑边界区域的像素与背景混淆,建筑边界很容易被漏检。为解决上述问题,提出融合Partial卷积与残差细化的遥感影像建筑物提取算法(UUNet)。以U-Net为基线网络,首先,改进编码器。在编码器前端加入两个Conv4×4,在最初扩大感受野,捕捉更多遥感影像特征信息,利用Partial卷积(PConv3×3)构造的PC模块,增强编码器提取多尺度建筑物特征的能力,用Conv2×2进行两倍下采样,减少建筑物特征信息丢失。其次,减少参数量。裁剪U-Net网络解码器三层结构为UUNet网络解码器。最后,增加改进的残差细化模块。在解码器输出端构造裁剪到三层结构的U型残差细化模块,对解码器输出的粗糙建筑物特征图进行进一步提纯,使建筑物边缘信息更加清晰,网络解码器与U型残差细化模块编码器进行跳跃连接,保留最初特征,将SimAM嵌入细化模块中,提高建筑物关注度,优化网络改善边界模糊,提升目标边界提取质量。在Satellite datasetⅡ(East Asia)数据集上进行消融实验,UUNet比U-Net的IoU_(Building)、IoU_(Background)、F1、OA和MIoU分别提高2.78个百分点、0.12个百分点、1.91个百分点、0.19个百分点、1.45个百分点,表明UUNet网络优于基线网络;在Satellite datasetⅡ(East Asia)数据集和WHU数据集上做对比实验,UUNet相较于现有的主流算法更优,能够显著地提升高分辨率遥感影像中建筑物提取的效果。

A comparative study of data-driven battery capacity estimation based on partial charging curves

With its generality and practicality, the combination of partial charging curves and machine learning(ML) for battery capacity estimation has attracted widespread attention. However, a clear classification,fair comparison, and performance rationalization of these methods are lacking, due to the scattered existing studies. To address these issues, we develop 20 capacity estimation methods from three perspectives:charging sequence construction, input forms, and ML models. 22,582 charging curves are generated from 44 cells with different battery chemistry and operating conditions to validate the performance. Through comprehensive and unbiased comparison, the long short-term memory(LSTM) based neural network exhibits the best accuracy and robustness. Across all 6503 tested samples, the mean absolute percentage error(MAPE) for capacity estimation using LSTM is 0.61%, with a maximum error of only 3.94%. Even with the addition of 3 m V voltage noise or the extension of sampling intervals to 60 s, the average MAPE remains below 2%. Furthermore, the charging sequences are provided with physical explanations related to battery degradation to enhance confidence in their application. Recommendations for using other competitive methods are also presented. This work provides valuable insights and guidance for estimating battery capacity based on partial charging curves.

Mammographic Findings Associated with Accelerated Partial Breast Irradiation Using Single Fraction Intraoperative Radiotherapy

Purpose: To evaluate the mammographic findings of women treated with accelerated partial breast irradiation (APBI) using single-fraction intraoperative radiotherapy (IORT). Materials/Methods: Women ≥ 40 years of age with unifocal invasive or intraductal carcinoma ≤ 2.5 cm on physical examination, mammography, and ultrasound were enrolled on an APBI trial using single fraction IORT. Post-treatment mammographic imaging was obtained at 6 months, 1 year, and then annually. Results: Between 12/02 and 6/04, 17 women underwent IORT at the time of lumpectomy (median age = 60 years;range = 40 - 83). The initial post-IORT mammogram showed increased density at the lumpectomy site in 11 patients (65%), while six patients (35%) had architectural distortion in the area of the irradiated tissue. Fifteen patients (88%) had numerous punctate, benign-appearing calcifications corresponding to the irradiated region. There was focal skin thickening near the incision in 13 patients (76%). At a median of 67 months, architectural distortion had stabilized and the benign-appearing calcifications remained stable in number and character. Eight patients (47%) had mammographic findings consistent with fat necrosis, ranging in size from 0.5 - 4 cm. Conclusions: After lumpectomy and IORT, mammographic changes include increased density and benign appearing calcifications in the irradiated region with focal skin thickening. These changes appear to stabilize over time and are consistent with post-treatment changes. These changes are important to identify in order to characterize benign changes from recurrent tumor.

Partial Volume Effect on MR Elastography

Magnetic resonance elastography (MRE) allows the quantitative assessment of the stiffness of tissues based on the tissue response to oscillatory shear stress. Shear wave displacements of the tissues are encoded as phase shifts and converted to stiffness (elastogram). Generally, a partial volume effect occurs when different materials are encompassed on the same voxel. In MRE, however, the partial volume effect occurs even if the voxel is filled with the same materials because wave displacements due to vibrations are spatially distributed. The purpose of this study was to investigate how the partial volume effect can affect the phase shift and the elastogram in MRE. We assumed that the partial volume effect appears only in the slice thickness direction and performed a simulation and MRE experiment with various slice thicknesses (1 - 19 mm), two types of imaging plane (coronal and axial) and two types of vibration frequency (100 and 200 Hz). The results of the simulation and the MRE experiment were similar, and indicated that the phase shift and the elastogram changed variously depending on the slice thickness, the wave pattern and the vibration frequency, even if the voxel was filled with the same material. To reduce the partial volume effect, it is necessary to perform the MRE under the following conditions: Use a wave pattern which barely causes this artefact, a smaller voxel size and a lower vibration frequency.

Preoperative albumin-bilirubin score and liver resection percentage determine postoperative liver regeneration after partial hepatectomy

BACKGROUND The success of liver resection relies on the ability of the remnant liver to regenerate.Most of the knowledge regarding the pathophysiological basis of liver regeneration comes from rodent studies,and data on humans are scarce.Additionally,there is limited knowledge about the preoperative factors that influence postoperative regeneration.AIM To quantify postoperative remnant liver volume by the latest volumetric software and investigate perioperative factors that affect posthepatectomy liver regenera-tion.METHODS A total of 268 patients who received partial hepatectomy were enrolled.Patients were grouped into right hepatectomy/trisegmentectomy(RH/Tri),left hepa-tectomy(LH),segmentectomy(Seg),and subsegmentectomy/nonanatomical hepatectomy(Sub/Non)groups.The regeneration index(RI)and late rege-neration rate were defined as(postoperative liver volume)/[total functional liver volume(TFLV)]×100 and(RI at 6-months-RI at 3-months)/RI at 6-months,respectively.The lower 25th percentile of RI and the higher 25th percentile of late regeneration rate in each group were defined as“low regeneration”and“delayed regeneration”.“Restoration to the original size”was defined as regeneration of the liver volume by more than 90%of the TFLV at 12 months postsurgery.RESULTS The numbers of patients in the RH/Tri,LH,Seg,and Sub/Non groups were 41,53,99 and 75,respectively.The RI plateaued at 3 months in the LH,Seg,and Sub/Non groups,whereas the RI increased until 12 months in the RH/Tri group.According to our multivariate analysis,the preoperative albumin-bilirubin(ALBI)score was an independent factor for low regeneration at 3 months[odds ratio(OR)95%CI=2.80(1.17-6.69),P=0.02;per 1.0 up]and 12 months[OR=2.27(1.01-5.09),P=0.04;per 1.0 up].Multivariate analysis revealed that only liver resection percentage[OR=1.03(1.00-1.05),P=0.04]was associated with delayed regeneration.Furthermore,multivariate analysis demonstrated that the preoperative ALBI score[OR=2.63(1.00-1.05),P=0.02;per 1.0 up]and liver resection percentage[OR=1.02(1.00-1.05),P=0.04;per 1.0 up]were found to be independent risk factors associated with volume restoration failure.CONCLUSION Liver regeneration posthepatectomy was determined by the resection percentage and preoperative ALBI score.This knowledge helps surgeons decide the timing and type of rehepatectomy for recurrent cases.

GraphMLP-Mixer:基于图-多层感知机架构的高效多行为序列推荐方法

在多行为序列推荐领域,图神经网络(GNNs)虽被广泛应用,但存在局限性,如对序列间协同信号建模不足和处理长距离依赖性等问题.针对这些问题,提出了一种新的解决框架GraphMLP-Mixer.该框架首先构造全局物品图来增强模型对序列间协同信号的建模,然后将感知机-混合器架构与图神经网络结合,得到图-感知机混合器模型对用户兴趣进行充分挖掘.GraphMLP-Mixer具有2个显著优势:一是能够有效捕捉用户行为的全局依赖性,同时减轻信息过压缩问题;二是其时间与空间效率显著提高,其复杂度与用户交互行为的数量成线性关系,优于现有基于GNN多行为序列推荐模型.在3个真实的公开数据集上进行实验,大量的实验结果验证了GraphMLP-Mixer在处理多行为序列推荐问题时的有效性和高效性.

基于GraphSAGE网络的藏文短文本分类研究

文本分类是自然语言处理领域的重要研究方向,由于藏文数据的稀缺性、语言学特征抽取的复杂性、篇章结构的多样性等因素导致藏文文本分类任务进展缓慢。因此,该文以图神经作为基础模型进行改进。首先,在“音节-音节”“音节-文档”建模的基础上,融合文档特征,采用二元分类模型动态网络构建“文档-文档”边,以充分挖掘短文本的全局特征,增加滑动窗口,减少模型的计算复杂度并寻找最优窗口取值。其次,针对藏文短文本的音节稀疏性,首次引入GraphSAGE作为基础模型,并探究不同聚合方式在藏文短文本分类上的性能差异。最后,为捕获节点间关系的异质性,对邻居节点进行特征加权再平均池化以增强模型的特征提取能力。在TNCC标题文本数据集上,该文模型的分类准确率达到了62.50%,与传统GCN、原始GraphSAGE和预训练语言模型CINO相比,该方法在分类准确率上分别提高了2.56%、1%和2.4%。

In-situ coating and surface partial protonation co-promoting performance of single-crystal nickel-rich cathode in all-solid-state batteries

The poor electrochemical performance of all-solid-state batteries(ASSBs),which is assemblied by Ni-rich cathode and poly(ethylene oxide)(PEO)-based electrolytes,can be attributed to unstable cathodic interface and poor crystal structure stability of Ni-rich cathode.Several coating strategies are previously employed to enhance the stability of the cathodic interface and crystal structure for Ni-rich cathode.However,these methods can hardly achieve simplicity and high efficiency simultaneously.In this work,polyacrylic acid(PAA)replaced traditional PVDF as a binder for cathode,which can achieve a uniform PAA-Li(LixPAA(0<x≤1))coating layer on the surface of single-crystal LiNi_(0.83)Co_(0.12)Mn_(0.05)O_(2)(SC-NCM83)due to H^(+)/Li^(+)exchange reaction during the initial charging-discharging process.The formation of PAA-Li coating layer on cathode can promote interfacial Li^(+)transport and enhance the stability of the cathodic interface.Furthermore,the partially-protonated surface of SC-NCM83 casued by H^(+)/Li^(+)exchange reaction can restrict Ni ions transport to enhance the crystal structure stability.The proposed SC-NCM83-PAA exhibits superior cycling performance with a retention of 92%compared with that(57.3%)of SC-NCM83-polyvinylidene difluoride(PVDF)after 200 cycles.This work provides a practical strategy to construct high-performance cathodes for ASSBs.

A STABILITY RESULT FOR TRANSLATINGSPACELIKE GRAPHS IN LORENTZ MANIFOLDS

In this paper,we investigate spacelike graphs defined over a domain Ω⊂M^(n) in the Lorentz manifold M^(n)×ℝ with the metric−ds^(2)+σ,where M^(n) is a complete Riemannian n-manifold with the metricσ,Ωhas piecewise smooth boundary,and ℝ denotes the Euclidean 1-space.We prove an interesting stability result for translating spacelike graphs in M^(n)×ℝ under a conformal transformation.

A Value for Games Defined on Graphs

Given a graph g=( V,A ) , we define a space of subgraphs M with the binary operation of union and the unique decomposition property into blocks. This space allows us to discuss a notion of minimal subgraphs (minimal coalitions) that are of interest for the game. Additionally, a partition of the game is defined in terms of the gain of each block, and subsequently, a solution to the game is defined based on distributing to each player (node and edge) present in each block a payment proportional to their contribution to the coalition.

Heterophilic Graph Neural Network Based on Spatial and Frequency Domain Adaptive Embedding Mechanism

Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.

Weighted Forwarding in Graph Convolution Networks for Recommendation Information Systems

Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.

An End-To-End Hyperbolic Deep Graph Convolutional Neural Network Framework

Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to scale-free graphs with power-law distributions,resulting in substantial distortions.Moreover,most of the existing GCN models are shallow structures,which restricts their ability to capture dependencies among distant nodes and more refined high-order node features in scale-free graphs with hierarchical structures.To more broadly and precisely apply GCNs to real-world graphs exhibiting scale-free or hierarchical structures and utilize multi-level aggregation of GCNs for capturing high-level information in local representations,we propose the Hyperbolic Deep Graph Convolutional Neural Network(HDGCNN),an end-to-end deep graph representation learning framework that can map scale-free graphs from Euclidean space to hyperbolic space.In HDGCNN,we define the fundamental operations of deep graph convolutional neural networks in hyperbolic space.Additionally,we introduce a hyperbolic feature transformation method based on identity mapping and a dense connection scheme based on a novel non-local message passing framework.In addition,we present a neighborhood aggregation method that combines initial structural featureswith hyperbolic attention coefficients.Through the above methods,HDGCNN effectively leverages both the structural features and node features of graph data,enabling enhanced exploration of non-local structural features and more refined node features in scale-free or hierarchical graphs.Experimental results demonstrate that HDGCNN achieves remarkable performance improvements over state-ofthe-art GCNs in node classification and link prediction tasks,even when utilizing low-dimensional embedding representations.Furthermore,when compared to shallow hyperbolic graph convolutional neural network models,HDGCNN exhibits notable advantages and performance enhancements.

GATiT:An Intelligent Diagnosis Model Based on Graph Attention Network Incorporating Text Representation in Knowledge Reasoning

The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the text.To better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic classification.In the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the input.In the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be diagnosed.To differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text subgraph.Themessage-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning process.Finally,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis results.Experimental results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.