Variational Gridded Graph Convolution Network for Node Classification

The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.

SNP site-drug association prediction algorithm based on denoising variational auto-encoder

Single nucletide polymorphism(SNP)is an important factor for the study of genetic variation in human families and animal and plant strains.Therefore,it is widely used in the study of population genetics and disease related gene.In pharmacogenomics research,identifying the association between SNP site and drug is the key to clinical precision medication,therefore,a predictive model of SNP site and drug association based on denoising variational auto-encoder(DVAE-SVM)is proposed.Firstly,k-mer algorithm is used to construct the initial SNP site feature vector,meanwhile,MACCS molecular fingerprint is introduced to generate the feature vector of the drug module.Then,we use the DVAE to extract the effective features of the initial feature vector of the SNP site.Finally,the effective feature vector of the SNP site and the feature vector of the drug module are fused input to the support vector machines(SVM)to predict the relationship of SNP site and drug module.The results of five-fold cross-validation experiments indicate that the proposed algorithm performs better than random forest(RF)and logistic regression(LR)classification.Further experiments show that compared with the feature extraction algorithms of principal component analysis(PCA),denoising auto-encoder(DAE)and variational auto-encode(VAE),the proposed algorithm has better prediction results.

A DIRECTED GRAPH ALGORITHM OF VARIATIONAL GEOMETRY BASED ON GEOMETRIC REASONING

The undirected graph to express engineering drawings is discussed .The principle to re-solve and reason the undirected graph is presented, and the algorithm finally transforms theundirected graph into the resolvable directed graph. Therefore,a rapid and simple way is suppliedfor variational design. A prototype of this algorithm has been implemented, and some examplesare given.

Exploring Variational Auto-encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI

Generative AI models for music and the arts in general are increasingly complex and hard to understand.The field of ex-plainable AI(XAI)seeks to make complex and opaque AI models such as neural networks more understandable to people.One ap-proach to making generative AI models more understandable is to impose a small number of semantically meaningful attributes on gen-erative AI models.This paper contributes a systematic examination of the impact that different combinations of variational auto-en-coder models(measureVAE and adversarialVAE),configurations of latent space in the AI model(from 4 to 256 latent dimensions),and training datasets(Irish folk,Turkish folk,classical,and pop)have on music generation performance when 2 or 4 meaningful musical at-tributes are imposed on the generative model.To date,there have been no systematic comparisons of such models at this level of com-binatorial detail.Our findings show that measureVAE has better reconstruction performance than adversarialVAE which has better musical attribute independence.Results demonstrate that measureVAE was able to generate music across music genres with inter-pretable musical dimensions of control,and performs best with low complexity music such as pop and rock.We recommend that a 32 or 64 latent dimensional space is optimal for 4 regularised dimensions when using measureVAE to generate music across genres.Our res-ults are the first detailed comparisons of configurations of state-of-the-art generative AI models for music and can be used to help select and configure AI models,musical features,and datasets for more understandable generation of music.

Distributed algorithm for solving variational inequalities over time-varying unbalanced digraphs

In this paper,we study a distributed model to cooperatively compute variational inequalities over time-varying directed graphs.Here,each agent has access to a part of the full mapping and holds a local view of the global set constraint.By virtue of an auxiliary vector to compensate the graph imbalance,we propose a consensus-based distributed projection algorithm relying on local computation and communication at each agent.We show the convergence of this algorithm over uniformly jointly strongly connected unbalanced digraphs with nonidentical local constraints.We also provide a numerical example to illustrate the effectiveness of our algorithm.

Feature-aided pose estimation approach based on variational auto-encoder structure for spacecrafts

Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit tasks.Benefiting from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yielded impressive achievements for spacecraft pose estimation.To improve the robustness and interpretability of CNNs,this paper proposes a Pose Estimation approach based on Variational Auto-Encoder structure(PE-VAE)and a Feature-Aided pose estimation approach based on Variational Auto-Encoder structure(FA-VAE),which aim to accurately estimate the 6 DoF pose of a target spacecraft.Both methods treat the pose vector as latent variables,employing an encoder-decoder network with a Variational Auto-Encoder(VAE)structure.To enhance the precision of pose estimation,PE-VAE uses the VAE structure to introduce reconstruction mechanism with the whole image.Furthermore,FA-VAE enforces feature shape constraints by exclusively reconstructing the segment of the target spacecraft with the desired shape.Comparative evaluation against leading methods on public datasets reveals similar accuracy with a threefold improvement in processing speed,showcasing the significant contribution of VAE structures to accuracy enhancement,and the additional benefit of incorporating global shape prior features.

A novel deep learning framework with variational auto-encoder for indoor air quality prediction

Exposure to poor indoor air conditions poses significant risks to human health, increasing morbidity and mortality rates. Soft measurement modeling is suitable for stable and accurate monitoring of air pollutants and improving air quality. Based on partial least squares (PLS), we propose an indoor air quality prediction model that utilizes variational auto-encoder regression (VAER) algorithm. To reduce the negative effects of noise, latent variables in the original data are extracted by PLS in the first step. Then, the extracted variables are used as inputs to VAER, which improve the accuracy and robustness of the model. Through comparative analysis with traditional methods, we demonstrate the superior performance of our PLS-VAER model, which exhibits improved prediction performance and stability. The root mean square error (RMSE) of PLS-VAER is reduced by 14.71%, 26.47%, and 12.50% compared to single VAER, PLS-SVR, and PLS-ANN, respectively. Additionally, the coefficient of determination (R2) of PLS-VAER improves by 13.70%, 30.09%, and 11.25% compared to single VAER, PLS-SVR, and PLS-ANN, respectively. This research offers an innovative and environmentally-friendly approach to monitor and improve indoor air quality.

时空邻域感知的时序兴趣点推荐

如何捕捉用户行为的动态变化和依赖关系是当前兴趣点推荐的一个重要问题,主要面临着数据稀疏、时空序列特征提取难以及用户个性化差异不易捕捉等挑战。为了解决这些挑战,提出了一种基于时空邻域感知及隐含状态变化的时序兴趣点推荐方法。该方法将用户行为的学习转换成了潜在状态的学习,并以一种结合距离信息的方式引入空间信息,有效地捕捉了用户的移动特征。首先,利用变分自编码器表征用户的潜在状态,再通过图神经网络学习到潜在状态之间的依赖关系,从而捕捉到用户行为的时序依赖;然后,利用注意力机制和径向基函数来捕捉用户与地点候选集之间的空间依赖,进而评估用户访问每个地点的概率,实现兴趣点推荐。在三个真实数据集上进行了实验比较和分析,显示了该方法相比于现有的基准算法具有更好的时序推荐性能。

基于异常感知的变分图自编码器的图级异常检测算法

图异常检测在识别复杂数据结构的异常模式中具有重要作用,被广泛地应用于有害分子识别、金融欺诈检测、社交网络分析等领域.但目前的图异常检测研究大多数聚焦在节点级别的异常检测,针对图级别的异常检测方法仍然较少,且这些方法并不能对异常图数据进行充分挖掘,且对异常标签比较敏感,无法有效地捕捉异常样本的特征,存在模型泛化能力差、性能翻转问题,异常检测能力有待提升.提出了一种基于异常感知的变分图自编码器的图级异常检测算法(anomaly-aware variational graph autoencoder based graph-level anomaly detection algorithm,VGAE-D),利用具有异常感知能力的变分图自编码器提取正常图和异常图数据的特征,并差异化正常图和异常图在编码空间中的编码信息分布,对图编码信息进一步挖掘来计算图的异常得分.在不同领域的8个公开数据集上进行实验,实验结果表明,提出的图级别异常检测方法能有效地对不同数据集中的异常图进行识别,异常检测性能高于目前主流的图级别异常方法,且具有少异常样本学习能力,较大程度上克服了性能翻转问题.

基于变分贝叶斯的鲁棒自适应因子图优化组合导航算法

复杂环境下的量测粗差和时变噪声严重影响了状态估计的精度和可靠性,对此提出了一种基于变分贝叶斯的鲁棒自适应因子图优化组合导航算法。首先,基于先验和后验两阶段更新将变分贝叶斯推断引入因子图优化框架中,以估计时变量测噪声协方差;其次,利用相邻帧间的平均新息构造量测协方差预测值,作为粗差判据来实现稳健估计。基于INS/GNSS组合导航的仿真和现场实验评估表明,所提方法能在粗差干扰的情况下有效估计时变量测噪声,相比M估计和滑动窗口自适应因子图优化算法的水平定位误差分别减小了26.7%和39.8%,兼顾了估计精度和抗差性能,具有较好的复杂环境适应性。

融合多个性化桥和自监督学习的跨域推荐算法

针对跨域推荐系统中目标域中项目交互较少的用户,提出一种融合多个性化桥和自监督学习的跨域推荐算法(MS-PTUPCDR)。首先,在目标域加入变分二部图编码器,使用变分推理框架生成潜在变量,目标域用户表示聚合其同构邻居信息。其次,将用户单一偏好桥扩展为用户多个性化偏好桥,将用户在多源域可转移的用户因子转移到目标域,在目标域加入多头注意力机制融合分别来自不同源域转换的用户潜在因子作为自监督学习的辅助任务。最后,在目标域中将聚合用户邻居因子和融合后的用户多源域转移用户因子进行自监督学习。在目标域通过用户自监督学习后的用户因子和目标域项目因子点积进行目标域项目评分预测。算法在Amazon和MovieLens两个数据集上进行实验,结果表明算法在MAE和RMSE两个评价指标上优于对比基线算法,在两个数据集上与最优对比基线算法相比,MAE平均提升1.96%,RMSE平均提升1.92%,验证了算法的有效性。

融合图卷积残差网络与边收缩池化的VQ-VAE网格重建算法

3D网格因其复杂性和不规则性使其有效表示成为挑战。为解决常规图卷积难以对3D网格有效传递和融合信息的问题,提出基于变分量化自编码器的3D网格模型,以探索其隐空间并用于3D网格的生成。提出带残差的图卷积模块,在处理3D网格这种复杂的图结构时,残差连接更有效地整合多层特征信息,支持更深的网络结构,显著提升模型的性能和泛化能力。在网格简化的边收缩算法基础上构建了可靠的多层池化和反池化操作,有效编码了层次结构中较粗糙和较稠密网格之间的对应关系。将3D网格形状投影到潜在空间的过程中,潜在特征被过度压缩导致信息损失,采用向量量化将潜在特征映射到预先定义的离散向量,在保持紧凑表示下更有效地编码和重建数据。实验结果表明,所提算法能够学习对可变形形状集合的紧凑表示,且在形状生成、形状插值等各种应用中表现出色。

张量分解和自适应图全变分的高光谱图像去噪

高光谱图像在采集过程中受到观测条件、成像仪材料属性、传输条件等客观因素的影响,不可避免地会引入各种噪声。这严重降低了高光谱图像的质量以及限制了后续处理的精度。因此,高光谱图像去噪是一个极其重要的预处理步骤。针对高光谱图像去噪问题,提出了低秩张量分解和自适应图全变分的高光谱图像去噪算法。首先,利用低秩张量分解来描述高光谱图像的全局空间和光谱相关性,并使用自适应权重图全变分来刻画高光谱图像空间维度上的分段平滑特性和保留高光谱图像的边缘信息;此外,采用l1-范数、Frobenius-范数分别刻画包括条纹噪声、脉冲噪声、死线噪声在内的稀疏噪声和高斯噪声。由此高光谱图像去噪问题归结为一个包含低秩张量分解和自适应图全变分的约束优化问题。利用增广拉格朗日乘子法对该优化问题进行交替求解。实验结果表明,所提出的高光谱图像去噪算法与现有的算法相比,能够充分刻画高光谱图像数据的内在结构特性,具有更好的去噪性能。

一种基于变分多跳图注意力编码器的深层协同真值发现

大数据时代,数据价值的释放经常需要融合多源数据,数据冲突成为这一过程中无法避免的关键问题。为了从冲突数据中筛选出真实声明以及可靠数据源,研究人员提出了真值发现方法。然而,现有的真值发现大多注重数据源与声明之间的直接协同信息,忽略了更深层的间接协同与对抗信息,导致不足以表达出数据源与声明的特征。针对此问题,提出了基于变分多跳图注意力编码器的真值发现方法(TD-VMGAE),基于数据源与声明之间的包含关系构建二分图网络,采用多跳图注意力层为每个节点表征汇聚间接协同信息以及对抗信息,并设计真值发现变分自编码器,抽取节点表征中所需的分类分布,对数据源和声明进行协同分类。实验结果表明,所提方法在3个不同尺度的数据集中均有不错的表现,消融实验和可视化也验证了所提方法的有效性和泛化能力。

基于自监督信息增强的图表示学习

针对图表示学习模型依赖具体任务进行特征保留以及节点表示的泛化性有限等问题,本文提出一种基于自监督信息增强的图表示学习模型(Self-Variational Graph Auto Encoder,Self-VGAE)。Self-VGAE首先使用图卷积编码器和节点表示内积解码器构建变分图自编码器(Variational Graph Auto Encoder,VGAE),并对原始图进行特征提取和编码;然后,使用拓扑结构和节点属性生成自监督信息,在模型训练过程中约束节点表示的生成。在多个图分析任务中,Self-VGAE的实验表现均优于当前较为先进的基线模型,表明引入自监督信息能够增强对节点特征相似性和差异性的保留能力以及对拓扑结构的保持、推断能力,并且Self-VGAE具有较强的泛化能力。

基于局部数据增强动态图的事件预测

事件指在真实世界中特定的时间和地点发生的与特定主题相关的活动,例如,社会动乱、暴恐袭击、自然灾害和传染病流行等事件会对国家安全和人民群众的生活产生重大威胁。如果能对此类事件的发生进行有效预测,将最大程度地减少负面事件带来的影响或最大化正面事件带来的利益。关于事件的研究中,准确预测事件仍然是一个非常具有挑战性的任务。文中提出了一种基于图注意力网络的事件预测方法LAT-GAT(Local Augmented Temporal-GAT),该方法使用条件变分编码器,在所构建的事件图中对目标节点的邻居节点生成新的特征样本,与节点原有特征进行拼合,形成新的节点特征,实现了对事件的传播结构的利用;另外,LAT-GAT还考虑了历史事件发生的时间先后顺序,将网络在上一时间点的输出结果集成到当前时间的特征中,从而实现了对事件传播时间特性的利用。最后,在泰国、印度、埃及和俄罗斯这4个国家真实事件数据集上,与多种代表性基线方法进行了对比实验。实验结果表明,LAT-GAT在4个国家数据上的F1评分都优于基线方法;在泰国、俄罗斯和印度数据集上召回率优于基线方法;在泰国、埃及和印度数据集上也获得了最高的准确率。还通过消融实验考察了模型参数对最终结果的影响。

基于图嵌入编码形态信息的非均匀多任务强化学习方法

传统强化学习方法存在效率低下、泛化性能差、策略模型不可迁移的问题。针对此问题,提出了一种非均匀多任务强化学习方法,通过学习多个强化任务提升效率和泛化性能,将智能体形态构建为图,利用图神经网络能处理任意连接和大小的图来解决状态和动作空间维度不同的非均匀任务,突破模型不可迁移的局限,充分发挥图神经网络天然地利用图结构归纳偏差的优点,实现了模型高效训练和泛化性能提升,并可快速迁移到新任务。多任务学习实验结果表明,与以往方法相比,该方法在多任务学习和迁移学习实验中均表现出更好的性能,在迁移学习实验中展现出更准确的知识迁移。通过引入图结构偏差,使该方法具备更高的效率和更好的迁移泛化性能。

水稻泛基因组学的发展与前景:重要工具与应用

与单个基因组不同,泛基因组一般是指包含一个物种或群体中全部基因组信息的数据集。近十年来,泛基因组学在水稻中已逐步成为研究热点,相关泛基因组成果和工具已在群体遗传学、进化生物学和生物育种实践等多个下游研究领域中获得广泛应用。本文聚焦于水稻泛基因组学的发展历程与应用前景,回顾了水稻泛基因组学的内涵发展和研究成果的时间线,总结了现有的水稻泛基因组代表性重要成果工具及其在多个领域中的主要应用,展望了其面临的挑战和发展前景。

Non-intrusive Load Monitoring Based on Graph Total Variation for Residential Appliances

Non-intrusive load monitoring is a technique for monitoring the operating conditions of electrical appliances by collecting the aggregated electrical information at the household power inlet.Despite several studies on the mining of unique load characteristics,few studies have extensively considered the high computational burden and sample training.Based on lowfrequency sampling data,a non-intrusive load monitoring algorithm utilizing the graph total variation(GTV)is proposed in this study.The algorithm can effectively depict the load state without the need for prior training.First,the combined Kmeans clustering algorithm and graph signals are used to build concise and accurate graph structures as load models.The GTV representing the internal structure of the graph signal is introduced as the optimization model and solved using the augmented Lagrangian iterative algorithm.The introduction of the difference operator reduces the computing cost and addresses the inaccurate reconstruction of the graph signal.With low-frequency sampling data,the algorithm only requires a little prior data and no training,thereby reducing the computing cost.Experiments conducted using the reference energy disaggregation dataset and almanac of minutely power dataset demonstrated the stable superiority of the algorithm and its low computational burden.

一阶常微分方程的知识图谱

一阶常微分方程的方程类型较多,解法不一.在学习的过程中会因为方程类型的判断不准确,导致学习困难.本文通过构造一阶常微分方程的知识图谱,将繁杂的知识进行关联与梳理,呈现常见一阶常微分方程的方程类型和解法之间的相互关系,并以实例进行说明.构建微分方程的知识图谱可以对微分方程中的概念、方法和技巧等进行全面和系统地整合,呈现出方程之间的内在联系和逻辑关系,可以培养学生的逻辑思维能力,帮助学生更加深入和全面地学习微分方程的知识,提高学习效果.