From 81d8a5eacd09314d3ee9f4ea3897eb5dc239aea2 Mon Sep 17 00:00:00 2001
From: Joel <44105587+j-brkr@users.noreply.github.com>
Date: Wed, 1 Apr 2026 15:02:46 +0800
Subject: [PATCH] Fix link to modeling guide in graph_tensor.md

Corrected a reference to the modeling guide in the documentation.
---
 tensorflow_gnn/docs/guide/graph_tensor.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tensorflow_gnn/docs/guide/graph_tensor.md b/tensorflow_gnn/docs/guide/graph_tensor.md
index 47073402..47ac85aa 100644
--- a/tensorflow_gnn/docs/guide/graph_tensor.md
+++ b/tensorflow_gnn/docs/guide/graph_tensor.md
@@ -306,7 +306,7 @@ GraphTensor.
 Graph Neural Networks can be built by interspersing broadcast and pool
 operations with trainable transformations of hidden states on nodes and
 possibly edges. (Most users of TF-GNN will not need to write code at this level
-themselves; please see the [modeling guide](gnn_modeling).) A tensor of values
+themselves; please see the [modeling guide](gnn_modeling.md).) A tensor of values
 for all nodes in a node set or all edges in an edge set is the basic unit of
 work on which low-level TensorFlow operations are performed, much like a batch
 of intermediate activations in a plain feed-forward network. That gives us a