Graph Neural Networks
Neural networks reflect the behaviour of the human brain, allowing computer programs to recognize patterns and solve common problems in the fields of AI, machine learning, and deep learning. Neural Networks are essentially a part of Deep Learning, which in turn is a subset of Machine Learning. So, Neural Networks are considered highly advanced application of Machine Learning that are now finding applications in many fields of interest.
Understanding AI vs ML vs Deep Learning
The biggest advantage of Deep Learning algorithms over machine learning algorithms are that they try to learn high-level features from the data in an incremental manner. This reduces the need of domain expertise and hard-core feature extraction. Below shows an example of classification to identify a car:
Graph Neural Network is a type of Neural Network which directly operates on the Graph structure. They are designed to perform inference on data described by graphs. They can learn and model non-linear and complex relationships, which is important because in real-life, many of the relationships between inputs and outputs are non-linear as well as complex.
Graph Networks have been applied at ultra-large Social Media, Search & eCommerce companies. The most prevalent application is at Google within their search engines where they have applied graph technology to associate information available on the internet. eCommerce Portal ranging from Decathlon and Shopee utilised such technology too. Currently the technology is only available to such ultra-large companies through their propriety software and not the general scale companies but as technology and tools becomes more prevalent and open, this can now be brought to the masses.