There are many styles of training machine learning models including the familiar supervised and unsupervised learning to active learning, semi-supervised learning and self-supervised learning. In this post, I will explain the difference between semi-supervised and self-supervised styles of learning. To get started, let us first recap what is supervised learning, the most popular machine learning methodology to build predictive models. Supervised learning uses annotated or labeled data to train predictive models. A label attached to a data vector is nothing but the response that the predictive model should generate for that data vector as input during the model training. For example, we will label pictures of cats and dogs with labels cat and dog to train a Cat versus Dog classifier. We assume a large enough training data set with labels is available when building a classifier.
When there are no labels attached to the training data, then the learning style is known as unsupervised learning. In unsupervised learning the aim is to partition the data into different groups based upon similarities of the training vectors. The k-means clustering is the most well-known unsupervised learning technique. Often, the number of the data groups to be formed is specified by the user.
Semi-Supervised Learning
In a real world setting, training examples with labels need to be acquired for a predictive modeling task. Labeling or annotating examples is expensive and time-consuming; many application domains require expert annotators. Thus, we often need ways to work with a small labeled training data set. In certain situations, we may be able to acquire, in addition to a small labeled training data set, additional training examples without labels with labeling being too expensive to perform. In such cases, it is possible to label the unlabeled examples using the small available set of labeled examples. This type of learning is referred as semi-supervised learning and it falls somewhere between supervised and unsupervised learning.
The term semi-supervised classification is often used to describe the process of labeling training examples using a small set of labeled examples for classification modeling. A similar idea is also used in clustering in an approach known as the semi-supervised clustering. In semi-supervised clustering, the goal is to group a given set of examples into different clusters with the condition that certain examples must be clustered together and certain examples must be put in different clusters. In other words, some kind of constraints are imposed on resulting clusters in terms of cluster memberships of certain specified examples. For an example of semi-supervised classification, you can check this blog post. In another blog post, you can read about constrained k-means clustering as a technique for semi-supervised clustering.
Transfer Learning
In certain situations we have a small set of labeled examples but cannot acquire more training examples even without the labels. One possible solution in such situations is transfer learning. In transfer learning, we take a trained predictive model that was trained on a related task and re-train it with our available labeled data. The re-training fine-tunes the parameters of the trained model to make it perform well for our predictive task. Transfer learning is popular in deep learning where many trained predictive models are publicly available. While performing transfer learning, we often employ data augmentation to the available labeled examples to create additional examples with labels. The common data augmentation operations include translation, rotation, cropping and resizing, and blurring.
Self-Supervised Learning
The Self-supervised learning is essentially unsupervised learning wherein the labels, the desired predictions, are provided by the data itself and hence the name self-supervised learning. The objective of the self-supervised learning is to learn the latent characteristics of the data that could be useful in many ways. Although the self-supervised learning has been around for a long time, for example as in autoencoders, its current popularity is primarily due its use in training the large language models.
The example below shows how the desired output is defined via self-learning. In the example, the words in green are masked and the model is trained to predict the masked words using the surrounding words. Thus, the masked words function as labels. The masking of the words is done in a random fashion for the given corpus and thus no manual labeling is needed.
The idea of random masking is not the only way to self-generate labels; several variations at the word level as well as the sentence level are possible and have been successfully used in different language modeling efforts. For example, self-learning can be employed to predict the neighboring sentences that come before and after a selected sentence in a given document.
The tasks defined to perform self-supervised learning are called pretext tasks because these tasks are not the end-goal and the results of these tasks are used for building the final systems.
Self-generation of labels for prediction is easily extended to images to define a variety of pretext tasks for self-supervised learning. As an example, images can be subjected to rotations of (90 degrees, 180 degrees etc.) and the pretext task is defined to predict the rotation applied to the images. Such a pretext task can make the model learn the canonical orientation of image objects. Data augmentation is also commonly used in self-supervised learning to create image variations.
All in all, self-supervised learning is a valuable concept that eliminates the need for external annotation. The success of large language models can be majorly attributed to this style of machine learning.