【論文閱讀】A Gentle Introduction to Graph Neural Networks [圖神經網絡入門]（3）

What types of problems have graph structured data?
什么樣的問題需要圖類型的數據?

We have described some examples of graphs in the wild, but what tasks do we want to perform on this data? There are three general types of prediction tasks on graphs: graph-level, node-level, and edge-level.
我們已經描述了一些圖的示例，但是我們希望對這些數據執行什么任務呢?在圖上一般有三種類型的預測任務: 圖層面、節點層面和邊層面的任務。

In a graph-level task, we predict a single property for a whole graph. For a node-level task, we predict some property for each node in a graph. For an edge-level task, we want to predict the property or presence of edges in a graph.
在圖層面的任務中，我們預測整個圖的單個屬性。對于節點層面的任務，我們預測圖中每個節點的一些屬性。對于邊層面的任務，我們希望預測圖中邊的屬性或是否存在。

For the three levels of prediction problems described above (graph-level, node-level, and edge-level), we will show that all of the following problems can be solved with a single model class, the GNN. But first, let’s take a tour through the three classes of graph prediction problems in more detail, and provide concrete examples of each.
對于上面描述的三個層面的預測問題(圖層面、節點層面和邊層面)，我們將說明以下所有問題都可以通過一個模型來解決，就是GNN。但首先，讓我們更詳細地了解一下這三類圖預測問題，并列舉每種問題的具體示例。

There are other related tasks that are areas of active research. For instance, we might want to generate graphs, or explain predictions on a graph. More topics can be found in the Into the weeds section .
還有其他相關的任務是較為活躍的研究領域。例如，我們可能想要生成圖，或者對圖上的預測進行解釋。更多的主題可以在進入weeds部分找到。

Graph-level task
圖層面的任務

In a graph-level task, our goal is to predict the property of an entire graph. For example, for a molecule represented as a graph, we might want to predict what the molecule smells like, or whether it will bind to a receptor implicated in a disease.
在圖層面的任務中，我們的目標是預測整個圖的屬性。例如，對于一個用圖表示的分子，我們可能想要預測這個分子的氣味，或者它是否會與一種與疾病有關的受體結合。

輸入: 圖
輸出: 每個圖的標簽，(例如，“圖包含兩個環嗎?”)

This is analogous to image classification problems with MNIST and CIFAR, where we want to associate a label to an entire image. With text, a similar problem is sentiment analysis where we want to identify the mood or emotion of an entire sentence at once.
這類似于MNIST和CIFAR的圖像分類問題，在這些問題中，我們希望將一個標簽關聯到整個圖像。對于文本，一個類似的問題是情緒分析，我們想要一次性確定整個句子的心境或情緒。

Node-level task
節點層面的任務

Node-level tasks are concerned with predicting the identity or role of each node within a graph.
節點層面的任務與預測圖中每個節點的標識或角色有關。

A classic example of a node-level prediction problem is Zach’s karate club [15] . The dataset is a single social network graph made up of individuals that have sworn allegiance to one of two karate clubs after a political rift. As the story goes, a feud between Mr. Hi (Instructor) and John H (Administrator) creates a schism in the karate club. The nodes represent individual karate practitioners, and the edges represent interactions between these members outside of karate. The prediction problem is to classify whether a given member becomes loyal to either Mr. Hi or John H, after the feud. In this case, distance between a node to either the Instructor or Administrator is highly correlated to this label.
關于節點級別預測問題的一個經典例子便是Zach的空手道俱樂部[15]。該數據集是一個單一的社交網絡圖，由出現分歧后選擇效忠于兩個空手道俱樂部之一的個人組成。隨著故事的發展，Mr. Hi(教練)和John H(管理員)之間的分歧在空手道俱樂部造成了分裂。節點代表每個空手道練習者，邊緣代表空手道之外這些成員之間的互動。預測的問題是區分一個給定的成員在出現分歧之后是忠于Mr. Hi還是John H。在這種情況下，節點到教練或管理員之間的距離與此標簽高度相關。

輸入: 帶有未標記節點的圖
輸出: 圖節點的標簽

On the left we have the initial conditions of the problem, on the right we have a possible solution, where each node has been classified based on the alliance. The dataset can be used in other graph problems like unsupervised learning.
左邊是該問題的初始條件，右邊是可能的解決方案，每個節點都根據聯盟進行了分類。該數據集可以用于其他圖問題，如無監督學習。

Following the image analogy, node-level prediction problems are analogous to image segmentation, where we are trying to label the role of each pixel in an image. With text, a similar task would be predicting the parts-of-speech of each word in a sentence (e.g. noun, verb, adverb, etc).
與圖像層面類比，節點層面的預測問題類似于圖像分割，我們試圖標記圖像中每個像素的角色。在文本中，類似的任務是預測句子中每個單詞的詞性(例如名詞、動詞、副詞等)。

Edge-level task
邊層面的任務

The remaining prediction problem in graphs is edge prediction.
圖的其他類型的預測問題是邊層面的預測。

One example of edge-level inference is in image scene understanding. Beyond identifying objects in an image, deep learning models can be used to predict the relationship between them. We can phrase this as an edge-level classification: given nodes that represent the objects in the image, we wish to predict which of these nodes share an edge or what the value of that edge is. If we wish to discover connections between entities, we could consider the graph fully connected and based on their predicted value prune edges to arrive at a sparse graph.
邊層面預測的一個例子是圖像場景理解。除了識別圖像中的物體，深度學習模型還可以用來預測它們之間的關系。我們可以將其描述為邊層面分類: 給定代表圖像中對象的節點，我們希望預測這些節點中哪些節點共享一條邊，或者那條邊的值是多少。如果我們想要發現實體之間的連接，我們可以認為圖是完全連通的，并根據它們的預測值剪枝邊來得到一個稀疏圖。

在上圖(b)中，原始圖像(a)被分割成五個實體:每個拳擊手、裁判、觀眾和墊子。圖(c )顯示了這些實體之間的關系。

輸入: 全連通圖，無標記邊
輸出: 每條邊的標簽

在左邊，我們有一個根據上面圖像的場景構建的初始圖。右邊是根據模型的輸出對某些連接進行剪枝時，該圖可能的邊的標簽。

參考文獻

[15] An Information Flow Model for Conflict and Fission in Small Groups Zachary, W.W., 1977. J. Anthropol. Res., Vol 33(4), pp. 452--473. The University of Chicago Press.

總結

以上是生活随笔為你收集整理的【论文阅读】A Gentle Introduction to Graph Neural Networks [图神经网络入门]（3）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。