Link Prediction
====================
In this problem, you will be implementing a link prediction model using a Graph Neural Network (GNN).
**Example:** Given a graph with nodes and edges, predict the likelihood of a new edge between two nodes.
**Constraints:** Use a GNN architecture with a message passing mechanism and a readout function to predict the likelihood of the new edge.
**Note:** You can assume the graph is represented as an adjacency matrix.
Test Cases
Test Case 1
Input:
[[0, 1, 0], [1, 0, 1], [0, 1, 0]]Expected:
[0.5, 0.5, 0.5]Test Case 2
Input:
[[0, 0, 1], [0, 1, 0], [1, 0, 0]]Expected:
[0.5, 0.5, 0.5]+ 3 hidden test cases