Examples of relation prediction tasks include: recommending content to users in social platforms, predicting drug side-effects, or inferring new facts in a relational databases.

Examples of Relation Prediction Tasks

Like node classification, relation prediction blurs the boundaries of traditional machine learning categories — often being referred to as both supervised and unsupervised — and it requires inductive biases that are specific to the graph domain. In addition, like node classification, there are many variants of relation prediction, including settings where the predictions are made over a single, fixed graph, as well as settings where relations must be predicted across multiple disjoint graphs.

Categorization of Relation Prediction

Relation prediction (link prediction, graph completion, relation inference) is a machine learning task on graph data where the goal is to infer the missing edges of a graph, when given a set of nodes and an incomplete set of edges between these nodes.

University of Michigan - Ann Arbor

Machine learning is inherently a problem-driven discipline, where we seek to build models that can learn from data in order to solve particular tasks. Machine learning on graphs is no different, except the usual categories of supervised and unsupervised are not necessarily the most informative or useful when it comes to graphs.

Machine Learning on Graphs

Hamilton, W.L. Graph Representation Learning. *Synthesis Lectures on Artificial Intelligence and Machine Learning*. 2020, 14(3), 1–159. https://doi.org/10.2200/S01045ED1V01Y202009AIM046

Graph Representation Learning by William Hamilton

Node classification is a machine learning task on graph data where the goal is to predict the label, which could be a type, category, or attribute, associated with all the nodes, when only given the true labels on a training set of nodes.

Node Classification

Relation Prediction

Community detection is a machine learning task on graph data where the goal is to infer latent community structures given only the input graph.

Community Detection

In this set of machine learning tasks on graph data, instead of making predictions over the individual components of a single graph, we are given a dataset of multiple different graphs. In graph classification and regression, the goal is to make independent predictions specific to each graph. On the other hand, in graph clustering, the goal is to learn an unsupervised measure of similarity between pairs of graphs.

Learn Before

Related

Learn After