fix img url

summaries/explainability/knowlege_graphs_survey.md

@@ -267,12 +267,12 @@
 - Loss Function
   - The loss function in TransE uses a margin-based ranking criterion. This function includes both positive and negative examples to ensure the model distinguishes between correct and incorrect triples.
   - The loss function can be formulated as:
-    
+
      $L = \sum_{(h, r, t) \in \mathcal{S}} \sum_{(h', r, t') \in \mathcal{S'}} \left[ \gamma + d(\mathbf{h} + \mathbf{r}, \mathbf{t}) - d(\mathbf{h'} + \mathbf{r}, \mathbf{t'}) \right]_{+}$
 
   - $\mathcal{S}$ is the set of positive (valid) triples.
 
-  - $\mathcal{S'}$ is the set of negative (invalid) triples generated by corrupting $ \mathcal{S} $.
+  - $\mathcal{S'}$ is the set of negative (invalid) triples generated by corrupting $\mathcal{S}$.
   - $\gamma$ is the margin, a hyperparameter that defines the minimum distance between positive and negative triples.
   - $d(\cdot)$ is the distance function (either L1 or L2 norm).