diff --git a/topomodelx/nn/hypergraph/allset.py b/topomodelx/nn/hypergraph/allset.py
index 219f9049..0219747f 100644
--- a/topomodelx/nn/hypergraph/allset.py
+++ b/topomodelx/nn/hypergraph/allset.py
@@ -16,18 +16,20 @@ class AllSet(torch.nn.Module):
         Dimension of the input features.
     hidden_channels : int
         Dimension of the hidden features.
-    n_layers : int, default: 2
+    n_layers : int, default = 2
         Number of AllSet layers in the network.
-    layer_dropout: float, default: 0.2
+    layer_dropout : float, default = 0.2
         Dropout probability for the AllSet layer.
-    mlp_num_layers : int, default: 2
+    mlp_num_layers : int, default = 2
         Number of layers in the MLP.
-    mlp_dropout : float, default: 0.0
-        Dropout probability for the MLP.
-    mlp_activation : torch.nn.Module, default: None
+    mlp_activation : torch.nn.Module, default = None
         Activation function in the MLP.
-    mlp_norm : bool, default: False
+    mlp_dropout : float, default = 0.0
+        Dropout probability for the MLP.
+    mlp_norm : bool, default = False
         Whether to apply input normalization in the MLP.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -47,6 +49,7 @@ def __init__(
         mlp_activation=None,
         mlp_dropout=0.0,
         mlp_norm=None,
+        **kwargs,
     ):
         super().__init__()
 
@@ -59,6 +62,7 @@ def __init__(
                 mlp_activation=mlp_activation,
                 mlp_dropout=mlp_dropout,
                 mlp_norm=mlp_norm,
+                **kwargs,
             )
             for i in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/allset_transformer.py b/topomodelx/nn/hypergraph/allset_transformer.py
index ffaa4279..67bfd882 100644
--- a/topomodelx/nn/hypergraph/allset_transformer.py
+++ b/topomodelx/nn/hypergraph/allset_transformer.py
@@ -26,6 +26,8 @@ class AllSetTransformer(torch.nn.Module):
         Number of layers in the MLP.
     mlp_dropout : float, default: 0.2
         Dropout probability in the MLP.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -44,6 +46,7 @@ def __init__(
         dropout=0.2,
         mlp_num_layers=2,
         mlp_dropout=0.2,
+        **kwargs,
     ):
         super().__init__()
 
@@ -55,6 +58,7 @@ def __init__(
                 heads=heads,
                 mlp_num_layers=mlp_num_layers,
                 mlp_dropout=mlp_dropout,
+                **kwargs,
             )
             for i in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/dhgcn.py b/topomodelx/nn/hypergraph/dhgcn.py
index 846e78d9..e6f02e6c 100644
--- a/topomodelx/nn/hypergraph/dhgcn.py
+++ b/topomodelx/nn/hypergraph/dhgcn.py
@@ -16,8 +16,10 @@ class DHGCN(torch.nn.Module):
         Dimension of the input features.
     hidden_channels : int
         Dimension of the hidden features.
-    n_layer : int, default = 2
+    n_layers : int, default = 2
         Amount of message passing layers.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -31,6 +33,7 @@ def __init__(
         in_channels,
         hidden_channels,
         n_layers=1,
+        **kwargs,
     ):
         super().__init__()
 
@@ -39,6 +42,7 @@ def __init__(
                 in_channels=in_channels if i == 0 else hidden_channels,
                 intermediate_channels=hidden_channels,
                 out_channels=hidden_channels,
+                **kwargs,
             )
             for i in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/hmpnn.py b/topomodelx/nn/hypergraph/hmpnn.py
index d2ef5a6e..6dce8406 100644
--- a/topomodelx/nn/hypergraph/hmpnn.py
+++ b/topomodelx/nn/hypergraph/hmpnn.py
@@ -12,18 +12,18 @@ class HMPNN(torch.nn.Module):
     Parameters
     ----------
     in_channels : int
-        Dimension of input features
+        Dimension of input features.
     hidden_channels : Tuple[int]
         A tuple of hidden feature dimensions to gradually reduce node/hyperedge representations feature
         dimension from in_features to the last item in the tuple.
-    num_classes: int
-        Number of classes
     n_layers : int, default = 2
         Number of HMPNNLayer layers.
-    adjacency_dropout_rate: int, default = 0.7
+    adjacency_dropout_rate : int, default = 0.7
         Adjacency dropout rate.
     regular_dropout_rate : int, default = 0.5
         Regular dropout rate applied on features.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -40,6 +40,7 @@ def __init__(
         n_layers=2,
         adjacency_dropout_rate=0.7,
         regular_dropout_rate=0.5,
+        **kwargs,
     ):
         super().__init__()
 
@@ -52,6 +53,7 @@ def __init__(
                     hidden_channels,
                     adjacency_dropout=adjacency_dropout_rate,
                     updating_dropout=regular_dropout_rate,
+                    **kwargs,
                 )
                 for _ in range(n_layers)
             ]
@@ -66,7 +68,7 @@ def forward(self, x_0, x_1, incidence_1):
             Node features.
         x_1 : torch.Tensor, shape = (n_hyperedges, in_features)
             Hyperedge features.
-        incidence_1: torch.sparse.Tensor, shape = (n_nodes, n_hyperedges)
+        incidence_1 : torch.sparse.Tensor, shape = (n_nodes, n_hyperedges)
             Incidence matrix (B1).
 
         Returns
diff --git a/topomodelx/nn/hypergraph/hnhn.py b/topomodelx/nn/hypergraph/hnhn.py
index 6d8c0dc6..ba4fb878 100644
--- a/topomodelx/nn/hypergraph/hnhn.py
+++ b/topomodelx/nn/hypergraph/hnhn.py
@@ -20,6 +20,8 @@ class HNHN(torch.nn.Module):
         Number of HNHN message passing layers.
     layer_drop : float, default = 0.2
         Dropout rate for the hidden features.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -30,7 +32,13 @@ class HNHN(torch.nn.Module):
     """
 
     def __init__(
-        self, in_channels, hidden_channels, incidence_1, n_layers=2, layer_drop=0.2
+        self,
+        in_channels,
+        hidden_channels,
+        incidence_1,
+        n_layers=2,
+        layer_drop=0.2,
+        **kwargs,
     ):
         super().__init__()
 
@@ -39,6 +47,7 @@ def __init__(
                 in_channels=in_channels if i == 0 else hidden_channels,
                 hidden_channels=hidden_channels,
                 incidence_1=incidence_1,
+                **kwargs,
             )
             for i in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/hypergat.py b/topomodelx/nn/hypergraph/hypergat.py
index e8449cc7..02d480c7 100644
--- a/topomodelx/nn/hypergraph/hypergat.py
+++ b/topomodelx/nn/hypergraph/hypergat.py
@@ -16,8 +16,10 @@ class HyperGAT(torch.nn.Module):
         Dimension of the hidden features.
     n_layers : int, default = 2
         Amount of message passing layers.
-    layer_drop: float, default = 0.2
+    layer_drop : float, default = 0.2
         Dropout rate for the hidden features.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -32,6 +34,7 @@ def __init__(
         hidden_channels,
         n_layers=2,
         layer_drop=0.2,
+        **kwargs,
     ):
         super().__init__()
 
@@ -39,6 +42,7 @@ def __init__(
             HyperGATLayer(
                 in_channels=in_channels if i == 0 else hidden_channels,
                 hidden_channels=hidden_channels,
+                **kwargs,
             )
             for i in range(n_layers)
         )
@@ -49,8 +53,8 @@ def forward(self, x_0, incidence_1):
 
         Parameters
         ----------
-        x_1 : torch.Tensor, shape = (n_edges, channels_edge)
-            Edge features.
+        x_0 : torch.Tensor, shape = (n_nodes, channels_nodes)
+            Node features.
         incidence_1 : torch.Tensor, shape = (n_nodes, n_edges)
             Boundary matrix of rank 1.
 
diff --git a/topomodelx/nn/hypergraph/hypersage.py b/topomodelx/nn/hypergraph/hypersage.py
index a9744225..588461ab 100644
--- a/topomodelx/nn/hypergraph/hypersage.py
+++ b/topomodelx/nn/hypergraph/hypersage.py
@@ -14,10 +14,12 @@ class HyperSAGE(torch.nn.Module):
         Dimension of the input features.
     hidden_channels : int
         Dimension of the hidden features.
-    n_layer : int, default = 2
+    n_layers : int, default = 2
         Amount of message passing layers.
     alpha : int, default = -1
-        Max number of nodes in a neighborhood to consider. If -1 it considers all the nodes.ù
+        Max number of nodes in a neighborhood to consider. If -1 it considers all the nodes.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -39,14 +41,14 @@ def __init__(self, in_channels, hidden_channels, n_layers=2, alpha=-1, **kwargs)
             for i in range(n_layers)
         )
 
-    def forward(self, x_0, incidence):
+    def forward(self, x_0, incidence_1):
         """Forward computation through layers, then linear layer, then global max pooling.
 
         Parameters
         ----------
-        x : torch.Tensor, shape = (n_nodes, features_nodes)
+        x_0 : torch.Tensor, shape = (n_nodes, features_nodes)
             Edge features.
-        incidence : torch.Tensor, shape = (n_nodes, n_edges)
+        incidence_1 : torch.Tensor, shape = (n_nodes, n_edges)
             Boundary matrix of rank 1.
 
         Returns
@@ -55,6 +57,6 @@ def forward(self, x_0, incidence):
             Label assigned to whole complex.
         """
         for layer in self.layers:
-            x_0 = layer.forward(x_0, incidence)
+            x_0 = layer.forward(x_0, incidence_1)
 
         return x_0
diff --git a/topomodelx/nn/hypergraph/unigcn.py b/topomodelx/nn/hypergraph/unigcn.py
index 0852fb23..58998943 100644
--- a/topomodelx/nn/hypergraph/unigcn.py
+++ b/topomodelx/nn/hypergraph/unigcn.py
@@ -16,6 +16,8 @@ class UniGCN(torch.nn.Module):
         Dimension of the hidden features.
     n_layers : int, default = 2
         Amount of message passing layers.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -30,6 +32,7 @@ def __init__(
         in_channels,
         hidden_channels,
         n_layers=2,
+        **kwargs,
     ):
         super().__init__()
 
@@ -37,6 +40,7 @@ def __init__(
             UniGCNLayer(
                 in_channels=in_channels if i == 0 else hidden_channels,
                 hidden_channels=hidden_channels,
+                **kwargs,
             )
             for i in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/unigcnii.py b/topomodelx/nn/hypergraph/unigcnii.py
index 47d3673c..6aed07c8 100644
--- a/topomodelx/nn/hypergraph/unigcnii.py
+++ b/topomodelx/nn/hypergraph/unigcnii.py
@@ -28,6 +28,8 @@ class UniGCNII(torch.nn.Module):
         Dropout rate for the hidden features.
     use_norm : bool, default=False
         Whether to apply row normalization after every layer.
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -47,6 +49,7 @@ def __init__(
         input_drop=0.2,
         layer_drop=0.2,
         use_norm=False,
+        **kwargs,
     ):
         super().__init__()
         layers = []
@@ -65,6 +68,7 @@ def __init__(
                     alpha=alpha,
                     beta=beta,
                     use_norm=use_norm,
+                    **kwargs,
                 )
             )
 
diff --git a/topomodelx/nn/hypergraph/unigin.py b/topomodelx/nn/hypergraph/unigin.py
index d9549ada..1c0cd0a3 100644
--- a/topomodelx/nn/hypergraph/unigin.py
+++ b/topomodelx/nn/hypergraph/unigin.py
@@ -26,7 +26,8 @@ class UniGIN(torch.nn.Module):
         Whether to make eps a trainable parameter.
     use_norm : bool, default=False
         Whether to apply row normalization after every layer.
-
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -46,6 +47,7 @@ def __init__(
         eps=0,
         train_eps=False,
         use_norm=False,
+        **kwargs,
     ):
         super().__init__()
 
@@ -60,6 +62,7 @@ def __init__(
                 eps=eps,
                 train_eps=train_eps,
                 use_norm=use_norm,
+                **kwargs,
             )
             for _ in range(n_layers)
         )
diff --git a/topomodelx/nn/hypergraph/unisage.py b/topomodelx/nn/hypergraph/unisage.py
index a43b89dc..4b2cce19 100644
--- a/topomodelx/nn/hypergraph/unisage.py
+++ b/topomodelx/nn/hypergraph/unisage.py
@@ -26,9 +26,10 @@ class UniSAGE(torch.nn.Module):
         Aggregator function for hyperedges.
     v_aggr : Literal["sum", "mean",], default="mean"
         Aggregator function for nodes.
-    use_norm : boolean
+    use_norm : bool
         Whether to apply row normalization after every layer.
-
+    **kwargs : optional
+        Additional arguments for the inner layers.
 
     References
     ----------
@@ -54,6 +55,7 @@ def __init__(
             "mean",
         ] = "mean",
         use_norm: bool = False,
+        **kwargs,
     ):
         super().__init__()
 
@@ -67,6 +69,7 @@ def __init__(
                 e_aggr=e_aggr,
                 v_aggr=v_aggr,
                 use_norm=use_norm,
+                **kwargs,
             )
             for i in range(n_layers)
         )