Add bias to TAGConv (#4597)

* add bias to TAGConv

* changelog

Author: rusty1s

CHANGELOG.md

@@ -9,5 +9,6 @@ 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
+- The `bias` argument in `TAGConv` is now actually apllied ([#4597](https://github.com/pyg-team/pytorch_geometric/pull/4597))
 - Fixed subclass behaviour of `process` and `download` in `Datsaet` ([#4586](https://github.com/pyg-team/pytorch_geometric/pull/4586))
 ### Removed

torch_geometric/nn/conv/tag_conv.py

@@ -5,6 +5,7 @@
 from torch_geometric.nn.conv import MessagePassing
 from torch_geometric.nn.conv.gcn_conv import gcn_norm
 from torch_geometric.nn.dense.linear import Linear
+from torch_geometric.nn.inits import zeros
 from torch_geometric.typing import Adj, OptTensor
 
 
@@ -51,14 +52,21 @@ def __init__(self, in_channels: int, out_channels: int, K: int = 3,
         self.K = K
         self.normalize = normalize
 
-        self.lins = torch.nn.ModuleList(
-            [Linear(in_channels, out_channels) for _ in range(K + 1)])
+        self.lins = torch.nn.ModuleList([
+            Linear(in_channels, out_channels, bias=False) for _ in range(K + 1)
+        ])
+
+        if bias:
+            self.bias = torch.nn.Parameter(torch.Tensor(out_channels))
+        else:
+            self.register_parameter('bias', None)
 
         self.reset_parameters()
 
     def reset_parameters(self):
         for lin in self.lins:
             lin.reset_parameters()
+        zeros(self.bias)
 
     def forward(self, x: Tensor, edge_index: Adj,
                 edge_weight: OptTensor = None) -> Tensor:
@@ -80,6 +88,10 @@ def forward(self, x: Tensor, edge_index: Adj,
             x = self.propagate(edge_index, x=x, edge_weight=edge_weight,
                                size=None)
             out += lin.forward(x)
+
+        if self.bias is not None:
+            out += self.bias
+
         return out
 
     def message(self, x_j: Tensor, edge_weight: OptTensor) -> Tensor: