Given a set of parameters for a dataset, clustering can be thought of as discovering those clusters. What parameters do we use for this? The implicit clustering method, which finds the nearest clusters (or, in some versions, clusters more similar to each other) with the least computational cost, is probably the simplest and most commonly used method for doing this. In clustering, we aim to keep the clusters as closely related to each other as possible – whether we do this by taking more measurements or by using only a certain technique to collect data.
But what is the difference between clustering and splitting data into one or more datasets?
The methods of implicit clustering and managed clustering are actually very similar. The only difference is that we use different parameters to determine in which direction we should split the data. Take as an example a set of points on a sphere that define an interconnected network. Both methods aim to keep the network as close as possible to the network defined by the two nearest points. This is because we don’t care if we are very far from one or the other. So, using the implicit clustering algorithm (cluster distance), we will divide the sphere into two parts that define very different networks: one will be the network defined by the two closest points, and the other will be the network defined by the two farthest points. The result is two completely separate networks. But this is not a good approach, because the further we move away from the two closest points, the smaller the distance between the points, the more difficult it will be to find connections between them – since there is a limited number of points that are connected by a small distance.
On the other hand, the method of controlled clustering (cluster distance) would require us to measure the length between each pair of points, and then perform calculations that make the networks closest to each other the smallest distance possible. The result is likely to be two separate networks that are close to each other but not exactly the same. Since we need two networks to be similar to each other in order to detect a relationship, it is likely that this method will not work – instead, the two clusters will be completely different.