Mathjax support in Markdown (#4683)

* markdown

* Update README.md

* update

* changelog

CHANGELOG.md

@@ -23,6 +23,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added support for graph-level outputs in `to_hetero` ([#4582](https://github.com/pyg-team/pytorch_geometric/pull/4582))
 - Added `CHANGELOG.md` ([#4581](https://github.com/pyg-team/pytorch_geometric/pull/4581))
 ### Changed
+- Math support in Markdown ([#4683](https://github.com/pyg-team/pytorch_geometric/pull/4683))
 - Allow for `setter` properties in `Data` and `HeteroData` ([#4682](https://github.com/pyg-team/pytorch_geometric/pull/4682))
 - Allow for optional `edge_weight` in `GCN2Conv` ([#4670](https://github.com/pyg-team/pytorch_geometric/pull/4670))
 - Fixed the interplay between `TUDataset` and `pre_transform` that modify node features ([#4669](https://github.com/pyg-team/pytorch_geometric/pull/4669))

README.md

@@ -123,9 +123,7 @@ More information about evaluating final model performance can be found in the co
 In addition to the easy application of existing GNNs, PyG makes it simple to implement custom Graph Neural Networks (see [here](https://pytorch-geometric.readthedocs.io/en/latest/notes/create_gnn.html) for the accompanying tutorial).
 For example, this is all it takes to implement the [edge convolutional layer](https://arxiv.org/abs/1801.07829) from Wang *et al.*:
 
-<p align="center">
-  <img height="40" src="https://raw.githubusercontent.com/pyg-team/pytorch_geometric/master/docs/source/_figures/edge_conv.svg?sanitize=true" />
-</p>
+$$x_i^{\prime} ~ = ~ \max_{j \in \mathcal{N}(i)} ~ \textrm{MLP}_{\theta} \left( [ ~ x_i, ~ x_j - x_i ~ ] \right)$$
 
 ```python
 import torch