Multilayer Satellite Network Collaborative Mobile Edge Caching:A GCN-Based Multi-Agent Approach

With the explosive growth of highdefinition video streaming data,a substantial increase in network traffic has ensued.The emergency of mobile edge caching(MEC)can not only alleviate the burden on core network,but also significantly improve user experience.Integrating with the MEC and satellite networks,the network is empowered popular content ubiquitously and seamlessly.Addressing the research gap between multilayer satellite networks and MEC,we study the caching placement problem in this paper.Initially,we introduce a three-layer distributed network caching management architecture designed for efficient and flexible handling of large-scale networks.Considering the constraint on satellite capacity and content propagation delay,the cache placement problem is then formulated and transformed into a markov decision process(MDP),where the content coded caching mechanism is utilized to promote the efficiency of content delivery.Furthermore,a new generic metric,content delivery cost,is proposed to elaborate the performance of caching decision in large-scale networks.Then,we introduce a graph convolutional network(GCN)-based multi-agent advantage actor-critic(A2C)algorithm to optimize the caching decision.Finally,extensive simulations are conducted to evaluate the proposed algorithm in terms of content delivery cost and transferability.

融合自适应周期与兴趣量因子的轻量级GCN推荐

推荐系统在成熟的数据挖掘技术推动下,已能高效地利用评分数据、行为轨迹等显隐性信息,再与复杂而先进的深度学习技术相结合,取得了很好的效果.同时,其应用需求也驱动着对基础数据的深度挖掘与利用,以及对技术要求的减负成为一个研究热点.基于此,提出一种利用GCN(graph convolutional network)方法进行深度信息融合的轻量级推荐模型LG_APIF.该模型结合行为记忆,通过艾宾浩斯遗忘曲线模拟用户兴趣变化过程,采用线性回归等相对轻量的传统方法挖掘项目的自适应周期等深度信息;分析用户当前的兴趣分布,计算项目的兴趣量,以获取用户的潜在兴趣类型;构建用户-类型-项目三元组的图结构,并结合减负后的GCN技术来生成最终的项目推荐列表.实验验证所提方法的有效性,通过与8个经典模型在Last.fm,Douban,Yelp,MovieLens数据集中的对比,表明该方法在Precision,Recall及NDCG指标上都得到良好改善,其中,Precision平均提升2.11%,Recall平均提升1.01%,NDCG平均提升1.48%.

多视角融合的时空动态GCN城市交通流量预测

城市交通流量预测是构建绿色低碳、安全高效的智能交通系统的重要组成部分.时空图神经网络由于具有强大的时空数据表征能力,被广泛应用于城市交通流量预测.当前,时空图神经网络在城市交通流量预测中仍存在以下两方面局限性:1)直接构建静态路网拓扑图对城市空间相关性进行表示,忽略了节点的动态交通模式,难以表达节点流量之间的时序相似性,无法捕获路网节点之间在时序上的动态关联;2)只考虑路网节点的局部空间相关性,忽略节点的全局空间相关性,无法建模交通路网中局部区域和全局空间之间的依赖关系.为打破上述局限性,提出了一种多视角融合的时空动态图卷积模型用于预测交通流量:首先,从静态空间拓扑和动态流量模式视角出发,构建路网空间结构图和动态流量关联图,并使用动态图卷积学习节点在两种视角下的特征,全面捕获城市路网中多元的空间相关性;其次,从局部视角和全局视角出发,计算路网的全局表示,将全局特征与局部特征融合,增强路网节点特征的表现力,发掘城市交通流量的整体结构特征;接下来,设计了局部卷积多头自注意力机制来获取交通数据的动态时间相关性,实现在多种时间窗口下的准确流量预测;最后,在4种真实交通数据上的实验结果,证明了该模型的有效性和准确性.

Sampling Methods for Efficient Training of Graph Convolutional Networks:A Survey

Graph convolutional networks(GCNs)have received significant attention from various research fields due to the excellent performance in learning graph representations.Although GCN performs well compared with other methods,it still faces challenges.Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs.Therefore,motivated by an urgent need in terms of efficiency and scalability in training GCN,sampling methods have been proposed and achieved a significant effect.In this paper,we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN.To highlight the characteristics and differences of sampling methods,we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories.Finally,we discuss some challenges and future research directions of the sampling methods.

Modeling Multi-Targets Sentiment Classification via Graph Convolutional Networks and Auxiliary Relation

Existing solutions do not work well when multi-targets coexist in a sentence.The reason is that the existing solution is usually to separate multiple targets and process them separately.If the original sentence has N target,the original sentence will be repeated for N times,and only one target will be processed each time.To some extent,this approach degenerates the fine-grained sentiment classification task into the sentence-level sentiment classification task,and the research method of processing the target separately ignores the internal relation and interaction between the targets.Based on the above considerations,we proposes to use Graph Convolutional Network(GCN)to model and process multi-targets appearing in sentences at the same time based on the positional relationship,and then to construct a graph of the sentiment relationship between targets based on the difference of the sentiment polarity between target words.In addition to the standard target-dependent sentiment classification task,an auxiliary node relation classification task is constructed.Experiments demonstrate that our model achieves new comparable performance on the benchmark datasets:SemEval-2014 Task 4,i.e.,reviews for restaurants and laptops.Furthermore,the method of dividing the target words into isolated individuals has disadvantages,and the multi-task learning model is beneficial to enhance the feature extraction ability and expression ability of the model.

Attack Behavior Extraction Based on Heterogeneous Cyberthreat Intelligence and Graph Convolutional Networks

The continuous improvement of the cyber threat intelligence sharing mechanism provides new ideas to deal with Advanced Persistent Threats(APT).Extracting attack behaviors,i.e.,Tactics,Techniques,Procedures(TTP)from Cyber Threat Intelligence(CTI)can facilitate APT actors’profiling for an immediate response.However,it is difficult for traditional manual methods to analyze attack behaviors from cyber threat intelligence due to its heterogeneous nature.Based on the Adversarial Tactics,Techniques and Common Knowledge(ATT&CK)of threat behavior description,this paper proposes a threat behavioral knowledge extraction framework that integrates Heterogeneous Text Network(HTN)and Graph Convolutional Network(GCN)to solve this issue.It leverages the hierarchical correlation relationships of attack techniques and tactics in the ATT&CK to construct a text network of heterogeneous cyber threat intelligence.With the help of the Bidirectional EncoderRepresentation fromTransformers(BERT)pretraining model to analyze the contextual semantics of cyber threat intelligence,the task of threat behavior identification is transformed into a text classification task,which automatically extracts attack behavior in CTI,then identifies the malware and advanced threat actors.The experimental results show that F1 achieve 94.86%and 92.15%for the multi-label classification tasks of tactics and techniques.Extend the experiment to verify the method’s effectiveness in identifying the malware and threat actors in APT attacks.The F1 for malware and advanced threat actors identification task reached 98.45%and 99.48%,which are better than the benchmark model in the experiment and achieve state of the art.The model can effectivelymodel threat intelligence text data and acquire knowledge and experience migration by correlating implied features with a priori knowledge to compensate for insufficient sample data and improve the classification performance and recognition ability of threat behavior in text.

Micro-expression recognition algorithm based on graph convolutional network and Transformer model

Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.

A malware propagation prediction model based on representation learning and graph convolutional networks

The traditional malware research is mainly based on its recognition and detection as a breakthrough point,without focusing on its propagation trends or predicting the subsequently infected nodes.The complexity of network structure,diversity of network nodes,and sparsity of data all pose difficulties in predicting propagation.This paper proposes a malware propagation prediction model based on representation learning and Graph Convolutional Networks(GCN)to address the aforementioned problems.First,to solve the problem of the inaccuracy of infection intensity calculation caused by the sparsity of node interaction behavior data in the malware propagation network,a mechanism based on a tensor to mine the infection intensity among nodes is proposed to retain the network structure information.The influence of the relationship between nodes on the infection intensity is also analyzed.Second,given the diversity and complexity of the content and structure of infected and normal nodes in the network,considering the advantages of representation learning in data feature extraction,the corresponding representation learning method is adopted for the characteristics of infection intensity among nodes.This can efficiently calculate the relationship between entities and relationships in low dimensional space to achieve the goal of low dimensional,dense,and real-valued representation learning for the characteristics of propagation spatial data.We also design a new method,Tensor2vec,to learn the potential structural features of malware propagation.Finally,considering the convolution ability of GCN for non-Euclidean data,we propose a dynamic prediction model of malware propagation based on representation learning and GCN to solve the time effectiveness problem of the malware propagation carrier.The experimental results show that the proposed model can effectively predict the behaviors of the nodes in the network and discover the influence of different characteristics of nodes on the malware propagation situation.

基于RPEpose和XJ-GCN的轻量级跌倒检测算法框架

传统的以ViT(Vision Transformer)模型为基准架构的关节点检测模型通常采用二维正弦位置编码,易丢失图像关键的二维形状信息,导致精度下降;而行为分类模型中,传统的时空图卷积网络(ST-GCN)在单标签分区策略中存在非物理连接的关节连接间关联度缺失问题。针对上述问题,设计一种轻量化实时跌倒检测算法框架,以快速准确地检测跌倒行为。该框架包含关节点检测模型RPEpose(Relative Position Encoding pose estimation)和行为分类模型XJ-GCN(Cross-Joint attention Graph Convolutional Network)。一方面,RPEpose模型采用相对位置编码克服原有位置编码的位置不敏感的缺陷,提升ViT架构在关节点检测中的性能;另一方面,提出X-Joint(Cross-Joint)注意力机制,将分区策略重构为XJL(X-Joint Labeling)分区策略后,对所有关节连接之间的依赖关系建模,能获得关节连接潜在相关性,具有分类性能优异且参数量小的优势。实验结果表明,在COCO 2017验证集上,对于分辨率为256×192的图像,RPEpose模型的计算开销仅为8.2 GFLOPs(Giga FLOating Point of operations),测试平均精度(AP)为74.3%;在以交叉目标(X-Sub)为划分标准的NTU RGB+D数据集上,XJ-GCN模型的测试Top-1准确率为89.6%,所提框架RPEpose+XJ-GCN的处理速度为30 frame/s,预测准确率为87.2%,具有较高的实时性和准确性。

Heterogeneous graph construction and node representation learning method of Treatise on Febrile Diseases based on graph convolutional network

Objective To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases(Shang Han Lun,《伤寒论》)dataset and explore an optimal learning method represented with node attributes based on graph convolutional network(GCN).Methods Clauses that contain symptoms,formulas,and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs,which were used to propose a node representation learning method based on GCN−the Traditional Chinese Medicine Graph Convolution Network(TCM-GCN).The symptom-formula,symptom-herb,and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes,and thus acquiring the nodes’sum-aggregations of symptoms,formulas,and herbs to lay a foundation for the downstream tasks of the prediction models.Results Comparisons among the node representations with multi-hot encoding,non-fusion encoding,and fusion encoding showed that the Precision@10,Recall@10,and F1-score@10 of the fusion encoding were 9.77%,6.65%,and 8.30%,respectively,higher than those of the non-fusion encoding in the prediction studies of the model.Conclusion Node representations by fusion encoding achieved comparatively ideal results,indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.

基于GCN和QP的智能车辆换道决策规划

考虑动态驾驶场景下车辆间的交互影响,提出了一种基于图卷积网络和二次规划的智能车辆自主换道行为决策与运动规划方法.首先将感兴趣区域进行分层建模,以图结构数据的形式对驾驶场景的全局和局部动态交互信息进行聚合,通过图卷积网络输出自车应采取的驾驶行为决策指令,然后与运动规划模块结合,基于局部子图划分可通行区域,构建并求解二次规划模型,得到满足运动学约束的无碰撞运动轨迹,最终完成无碰撞自主换道.对提出的方法进行了仿真实验与实车验证,实验结果证明该方法的性能要优于传统的规划方法,具有更好的实验成功率以及场景泛化性能.

IR-GCN:二值图卷积神经网络推理加速器

针对图卷积神经网络(GCN)中数据规模庞大、不适合边缘端低功耗处理器高效推理计算的问题,本文提出一种将新型二值数据量化算法(IR-Net)应用于GCN模型推理计算的方法,并设计了对应的硬件加速器IR-GCN。同时,针对计算过程中工作负载分布不均衡的问题,实现了一种负载均衡模块设计,显著提高了计算效率。实验结果表明,在较小精度损失范围内,IR-GCN加速器可以同时降低计算延迟以及访存开销。与现有性能最优的研究相比,IR-GCN加速器平均具有2.4倍的计算加速比、7.9倍的功耗降低、13.7倍的芯片面积减少以及21.0倍的访存量降低。

CINO-TextGCN:融合CINO与TextGCN的藏文文本分类模型研究

为提高藏文新闻文本分类准确性,文章提出一种融合少数民族语言预训练模型(Chinese Minority Pr-etrained Language Model,CINO)和图卷积神经网络模型(Text Graph Convolutional Networks,TextGCN)的方法,即CINO-TextGCN模型。为有效评测该模型对藏文文本的分类性能,自建了较大规模和较高质量的藏文新闻文本公开数据集TNEWS(https://github.com/LG2016/CINO-TextGCN),通过实验发现,CINO-Text-GCN在公开数据集TNCC上的准确率为74.20%,在TNEWS上为83.96%。因此,该融合模型能够较好地捕捉到藏文文本语义,提升藏文文本分类性能。

基于改进GCN-sbuLSTM模型的高速公路交通量预测方法

为解决现有高速公路交通量预测方法在捕捉动态时空依赖关系方面的不足,提出了一种融合信息几何方法与注意力机制的新型高速路网交通量预测模型。首先,利用信息几何方法量化ETC门架之间的动态数据分布差异。然后,利用注意力机制来捕获交通的动态空间依赖关系。最后,结合一种堆叠的双向递归层结构,提出了一种长时间跨度的并行子模型算法,即基于信息几何方法(Information Geometry)和注意力机制(Attention Mechanism)优化的图卷积神经网络(GCN)结合堆叠双向单向长短期记忆神经网络(sbuLSTM)的组合模型—IGAGCN-sbuLSTM。采用该模型对100多条路段、3000多处门架近7亿条高速公路ETC门架系统数据进行分析,结果显示:与LSTM、GCN、GCN-LSTM、ASTGCN等现有4种模型相比,在10 min时间尺度下,IGAGCN-sbuLSTM组合模型的平均绝对误差(MAE)分别降低了2.39,3.72,1.02,1.46,均方根误差(RMSE)分别降低了3.25,4.32,2.05,5.65,平均绝对百分比误差(MAPE)分别降低了5.49%,12.54%,1.56%,0.5%。研究表明,IGAGCN-sbuLSTM模型在预测精度和不同时间间隔的预测性能上均优于现有的单一捕获特性模型及其他常用的组合模型,可广泛应用于高速公路收费、车速等数据的预测分析。

基于关联分区和ST-GCN的人体行为识别

基于骨骼的动作识别因不受人体物理特征的影响,简单清晰地传达了人体行为识别的重要信息而受到广泛关注。传统的应用程序骨架建模通常依赖遍历规则的人为设置而导致表达能力有限和推广困难。因此,在近年来热门的时空图卷积网络(ST-GCN)模型基础上提出了一种新的划分骨架关节点的分区策略。该策略相比于原始分区方法加强了身体相对位置之间的关系,从而有利于提高骨架关节点信息在时间和空间上的关联。与此同时,在训练过程中通过设置不同的迭代学习率以进一步提高识别精度。在两个不同性质的大规模数据集Kinetics和NTURGB+D上与现有方法进行识别效果的比较,实验结果表明了该方法的有效性。

CEEMDAN与GCN结合的配电变压器故障诊断

针对配电变压器故障特征提取困难、故障识别难度大的问题,提出一种将振动信号、自适应噪声完备集合经验模态分解(CEEMDAN)与图卷积神经网络(GCN)三者有机结合的故障诊断方法。首先,采用CEEMDAN对来自加速度传感器的振动信号进行处理,获得一组固有模态分量(intrinsic modal function);其次求取边际谱信息作为特征向量;然后,对特征向量矩阵构造无向加权完全图,并使用改进灰狼优化算法对高斯核带宽进行寻优;最后,搭建一个具备多通道和多连通的改进GCN模型进行特征二次挖掘与故障分类。与此同时,还在模型中加入一种名叫“峰值因子”指标实现对未知类型故障的辨识。在实例分析中,分别对油浸式和干式变压器进行故障模拟,提取不同状态的样本进行测试。实验结果表明,所提方法对油浸式和干式变压器的故障识别准确率分别达到97.73%和95.6%,优于其他两种对比方法。在面对未知类型故障以及运行工况发生变化时,也具备较高是识别能力。

基于Att_GCN模型的知识图谱推理算法

针对目前知识图谱推理方法中,传统神经网络方法不能有效考虑实体之间的相关性问题,提出了一种将图卷积神经网络(GCN)与注意力机制(Attention)相结合的知识图谱推理方法。该方法利用注意力机制对知识图谱中的实体与其邻域实体进行相关性计算,得到实体特征向量。通过图卷积神经网络的参数共享技术学习实体的所有邻域实体特征。将实体特征和关系特征进行特征融合,得到每个实体的隐性特征向量。通过实体分类实验和链接预测实验进行分析,结果表明,该方法的准确率较传统神经网络方法有进一步提高,为搜索、问答、推荐以及数据集成等领域提供了方法支持。

基于GCN的局部增强人体骨骼行为识别算法

为使人体骨骼这种非欧几里得结构数据更好地应用于人体行为识别任务中,将多种模态的特征融合后作为模型的输入,探讨关节的全局与局部的信息共现性,构建一个完整的空间信息推理模型。通过使用多层时间膨胀卷积网络提取骨骼数据在时间维度中的上下文依赖关系,使模型可以兼具捕获短期和长期的时序上下文依赖关系,有效提高时间信息的提取能力。提出的分层次时空图卷积神经网络模型在NTU-RGB+D-60和NTU-RGB+D-120数据集上均取得了较好的识别准确率。

一种基于层次化R-GCN的会话情绪识别方法

会话情绪识别包括说话者自身情绪影响以及说话者之间情绪影响这2个重要因素,为了充分考虑上述影响因素以提高会话情绪识别效果,提出一种基于层次化关系图卷积神经网络(HRGCN)的识别方法。使用一个基础神经网络对会话序列的特征数据进行优化,按照不同的说话者划分出2个不同的会话子序列,采用2个局部关系图卷积神经网络(R-GCN)分别对2个子序列进行局部建模,按照会话发生的时间顺序重新整合局部建模后的2个子序列,并利用全局R-GCN对其进行全局建模。通过对输入的多模态特征数据的分层次建模,使得会话序列捕获到更多的上下文信息。在IEMOCAP数据集上的实验结果表明,与当前流行的循环神经网络LSTM、GRU等相比,HRGCN方法的会话情绪识别性能较高,准确率与F1值分别达到84.48%与84.40%。

融合注意力机制的LSTM-GCN网络人体行为识别

针对现有人体骨架行为识别方法中因只侧重于视频数据中时间或空间信息的单独提取而存在的时空特征提取不充分的问题,提出一种融合注意力机制的LSTM-GCN网络。该网络设计为LSTM层和图卷积层两层,其中LSTM层重点提取骨架序列的时间信息,图卷积层重点提取骨架序列的空间信息。同时在两个网络层中融入了注意力机制,并按人体骨骼点对整体动作贡献程度对其分配不同的权重,实现了对数据中显著特征及关键帧的增强识别。两个网络层按一定的比重融合后利用Softmax对动作进行分类识别。为验证该方法的优越性,在Kinetics和NTU-RGB+D两个比较典型的公开数据集上进行了仿真实验和消融实验。同时录制了一些相似度高、易混淆的视频,并对其识别结果可视化,再次证明该方法的普适性。实验结果表明该方法可以有效增强人体骨骼行为识别性能,并在计算精度和识别效率上具有一定的优势。