Fix link (#378)

Author: aurorarossi

docs/src/api/conv.md

@@ -12,7 +12,7 @@ The table below lists all graph convolutional layers implemented in the *GraphNe
 - *Sparse Ops*: implements message passing as multiplication by sparse adjacency matrix instead of the gather/scatter mechanism. This can lead to better CPU performances but it is not supported on GPU yet. 
 - *Edge Weight*: supports scalar weights (or equivalently scalar features) on edges. 
 - *Edge Features*: supports feature vectors on edges.
-- *Heterograph*: supports heterogeneous graphs (see [`GNNHeteroGraphs`](@ref)).
+- *Heterograph*: supports heterogeneous graphs (see [`GNNHeteroGraph`](@ref)).
 
 | Layer                       |Sparse Ops|Edge Weight|Edge Features| Heterograph  |
 | :--------                   |  :---:   |:---:      |:---:        |  :---:       |