Graph Neural Networks Explained
Graph neural networks (GNNs) belong to a category of neural networks that operate naturally on data structured as graphs. Despite being what can be a confusing topic, GNNs can be distilled into just a handful of simple concepts.
Starting With Recurrent Neural Networks (RNNs)
We’ll pick a likely familiar starting point: recurrent neural networks. As you may recall, recurrent neural networks are well-suited to data that are arranged in a sequence, such as time series data or language. The defining feature for a recurrent neural network is that the state of an RNN depends not only on the current inputs but also on the network’s previous hidden state. There have been many improvements to RNNs over the years, generally falling under the category of LSTM-style RNNs with a multiplicative gating function between the current and previous hidden state of the model. A review of LSTM variants and their relation to vanilla RNNs can be found here.