Implement `edge_predictor` sparse attention network

[martinnormark]

Develop the network for proposing candidate triangles. This component is responsible for predicting the connectivity between the sampled points.

1. Input:
   • Sampled points from the PointSampler
   • Original mesh connectivity (edges)
2. Main components: a. k-nn graph construction b. DevConv layer c. Sparse self-attention layer
3. Functionality steps: a. Extend the original mesh connectivity:
   • Construct a k-nn graph over the sampled points
   • Combine this with the original mesh edges to avoid isolated nodes b. Process the extended graph:
   • Apply a DevConv layer c. Apply sparse self-attention:
   • Predict the probability that point x_i is connected with point x_j
4. Output:
   • A simplified adjacency matrix (A_s) representing the predicted connectivity
5. Key equations:
   • Self-attention: S[i, j] = softmax((W_q f_j)^T (W_k f_i))
   • Simplified adjacency: A_s[i, j] = S[i, :] A S[j, :]^T

To implement this, we'll need:

1. A function to construct the k-nn graph
2. The DevConv layer (which we already have)
3. A sparse self-attention mechanism
4. A method to combine the original and predicted connectivity

Additional considerations:

• The paper mentions using k=15 for the k-nn graph
• The DevConv layer should have 64 hidden dimensions (as mentioned for the PointSampler)

[martinnormark]

Done in 00a68224d02fa110e7fd3edb318b748b5cec355f