英文是纯手打的!论文原文的summarizing and paraphrasing。可能会出现难以避免的拼写错误和语法错误,若有发现欢迎评论指正!文章偏向于笔记,谨慎食用
目录
3.2. Multi-modality and multi-view
1. 省流版
1.1. 心得
(1)走错频道了,怎么是机器学习,那就看看创新点吧
(2)感觉多模态很多都是说smri, fmri, DTI三个的。但是好像EEG也能变成脑图诶,为什么似乎到目前为止没有看到把EEG来作为第四个模态的呢?而且我发现这几个模态的脑图谱不是共享的(好像AAL是可以用作fmri和smri),那这个节点数要怎么对齐啊?
(3)但其实这篇文章用不同的脑图谱也是在解决(2)这个问题诶,等我看看
1.2. 论文总结图
2. 论文逐段精读
2.1. Abstract
①Existing GNNs ignore the node feature (其实有些还是带了) and graph reconstruction (看完后面的,作者似乎认为一次编码一次解码就是图重构)
②They proposed a novel Multi-View Attribute Graph Convolution Networks (MAGCN) with two-pathway encoders for clustering. The first pathway is multiview attribute graph attention networks that can reduces noise, redundancy and learns the embedding features of multi-view graph data. The second pathway is consistent embedding encoders, which is able to capture the geometric relationship and the consistency of probability distribution among different views
2.2. Introduction
①Transform graph data into low dimensional (减少特征数量~), compact (不那么分散) and continuous (不是离散数据) feature space is the capability of graph embedding
②GNN is suitable for handling single-view data rather than multi-view
③The limits of existing multi-view models: a) can not assign different weights for different neighbors, b) might ignore the node feature or graph reconstruction, c) do not consider the similarities between different views(啊啊这个也可以考虑的吗我要看看你是怎么考虑的)
④Existing GNN mostly focus on multi-graph(又是什么的多图?)instead of multi-attribute(你举社交网络的例子干嘛?说人们可以有多个属性,如工作、爱好等,那脑图的属性是啥?)
paragon n. 完美典范,尽善尽美的人(或物);(100克拉以上的)无暇钻石
2.3. Related Work
The authors enumerate some neighbor aggregation, attention based and multi view models
2.4. Proposed Methodology
2.4.1. Notation
①Defining a graph , where denotes node set, denotes edge set, denotes the number of nodes
②The attribute feature of nodes: , where denotes the number of views
2.4.2. The Framework of MAGCN
①The overall framework:
they first encode to graph embedding by multi-view attribute graph convolution encoders (green).Then transforming to consistent clustering embedding by consistent embedding encoders (purple)
(1)Multi-view Attribute Graph Convolution Encoder
①The graph embedding function can be simply expressed as , where denotes the auto-encoder parameter
② Part of Multi-view Attribute Graph Convolution Encoder (MAGCE) for view :
③The -th output of MAGCE:
where denotes the " relevance coefficient matrix with added self-connection"(这是功能连接矩阵加了I还是邻接矩阵加了I还是别的啊);
;
denotes the activate function
④The starts from and end with
⑤The learnable relevance matrix in the -th layer:
where and denote the trainable parameters, denote activation function
⑥Normalizing to get the final relevance coefficient :
where denotes the neighbors of node
⑦The output of the -th layer multi-view attribute graph convolution decoders:
⑧The reconstructed graph structure and denotes the inner product operator
⑨The reconstruction loss:
(2)Consistent Embedding Encoders
①Reducing the dimensionality of graph embeddings by mapping function:
where denotes the encoder parameter
②The similarity between two views can be Manhattan Distance, Euclidean distance, cosine similarity, etc.
③The loss function of geometric relationship consistency:
④Defining the adaptive fusion
⑤The original probability distribution of with t-distribution:
where denotes the initial clauster centroids, denotes the degree of freedom, denotes the probability of assigning node to cluster
⑥The target probability distribution of :
where denotes soft cluster frequencies
⑦Loss(我真看不懂前面叭叭的一大堆,但这loss看上去其实也就是L2):
2.4.3. Task for Clustering
①Total loss function:
②Clustering label of node :
2.5. Task for Clustering
2.5.1. Experimental Setting
(1)Metrics and Databases
①Dataset: Cora, Citeseer, Pubmed
②Evaluation metrics: clustering accuracy (ACC), normalized mutual information (NMI) and average rand index (ARI)
③View 2 creating: adopting Fast Fourier Transform (FFT), Gabor transform, Euler transform and Cartesian product in view 1
(2)Implementation Details
①The node representation dimensions of the two layer in Cora is [512, 512], in Citeseer is [2000, 512], in Pubmed is [128, 64].
②They adopt fully connected layer in in integrate-encoder in all datasets
③Activate function: ReLU
④
(3)Comparison Algorithms
①node attribute: K-Means
②graph structure: Graph Encoder, DeepWalk, denoising autoencoder for graph embedding (DNGR) and modularized nonnegative matrix factorization (M-NMF)
③graph structure & node attribute: graph autoencoders (GAE) and variational graph auto-encoders (VGAE), marginalized graph autoencoder (MGAE), adversarial regularized graph autoencoder (ARGAE) and adversarial variational regularized graph autoencoder (ARVGAE), deep attentional embedding graph clustering (DAEGA) and graph attention auto-encoders (GATE)
④deep multi-view clustering: deep canonical correlation analysis (DCCA) and deep typical correlated autoencoder (DCCAE)
2.5.2. Experimental Results
(1)Evaluation Metrics with Comparison Algorithms
①Comparison table:
(2)Analysis of Probability Distribution Consistency
①Through iterations, , and steadily learn more accurate prediction capability:
where the x-axis denotes the clusters and the y-axis denotes the cluster probability
(3)Impact of Parameters
①Controlling variables method is used for analyzing the three regularization parameters:
(4)Analyzing Different View 2
①Comparison that using different methods to construct view 2
2.6. Conclusions
As a model which contains dual encoders, MAGCN reconstructs the high dimensional features and integrates low dimensional consistent information
3. 知识补充
3.1. Discrete Data
(1)定义:
不连续的特征空间主要指的是在特征空间中,某些特征值或特征组合之间存在间隙或跳跃,没有形成连续的分布或变化。这样的特征空间在实际应用中很常见,尤其当处理离散数据、分类数据或具有明显边界的数据时。以下是一些不连续特征空间的例子:
-
分类数据:例如,在描述一个人的性别时,通常使用“男”或“女”这样的标签,这些标签之间是不连续的。类似地,描述血型(A、B、AB、O)或民族时也存在不连续性。
-
整数特征:当特征值只能取整数时,特征空间也是不连续的。例如,描述一个物体的数量或某个指标的评分等级时。
-
二进制特征:二进制特征只能取0或1,这种特征空间显然是不连续的。这在很多计算机视觉和机器学习的应用中都很常见,比如某些特征是否被激活或存在。
-
时间戳数据:虽然时间本身是连续的,但当我们以特定的时间间隔(如小时、天、月等)来记录数据时,特征空间就变得不连续了。
-
地理数据:在地理信息系统中,地理坐标(经度和纬度)虽然理论上可以是连续的,但由于数据获取的限制或处理的需要,可能只记录特定地点的数据,从而形成不连续的特征空间。
-
基因序列数据:在生物信息学中,基因序列由一系列离散的碱基对(A、T、C、G)组成,这些碱基对之间的变化是不连续的。
-
文本数据:在处理文本数据时,词语或短语作为特征,它们之间的转换通常也是不连续的。尽管可以通过词嵌入等方法将文本数据映射到连续空间,但原始的词或短语空间仍然是不连续的。
(2)例子:
脑图里面如果要用到什么性别年龄来做特征就是不连续的。智商和时间序列算连续吗?
3.2. Multi-modality and multi-view
(1)Multi-modality
感觉在脑图这边,不同的成像方式(EEG, fmri, smri, DTI, CT)之类的叫多模态
(2)Multi-view
文中给的multi-view是不同的脑图谱,AAL-90,AAL-120之类的
(3)?
那么问题来了,叠皮尔逊FC+其他的FC+邻接矩阵这样的通道算什么呢
4. Reference List
Cheng, J. et al. (2020) 'Multi-View Attribute Graph Convolution Networks for Clustering', Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pp. 2973-2979. doi: Multi-View Attribute Graph Convolution Networks for Clustering | IJCAI