Skip to content

Commit 091e4e3

Browse files
committed
prettier equations
1 parent e03f862 commit 091e4e3

File tree

1 file changed

+4
-2
lines changed

1 file changed

+4
-2
lines changed

g3doc/tutorials/framework.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -17,8 +17,10 @@ Note that the generalized neighbor loss equation is flexible and can have other
1717
forms besides the one illustrated above. For example, we can also select
1818
![equation](http://www.sciweavers.org/tex2img.php?eq=%5C%28%5Csum_%7Bx_j%20%5Cin%20%5Cmathcal%7BN%7D%28x_i%29%7D%5Cmathcal%7BE%7D%28y_i%2Cg_%5Ctheta%28x_j%29%5C%29&bc=White&fc=Black&im=jpg&fs=12&ff=arev&edit=0)
1919
to be the
20-
neighbor loss, which calculates the distance between the ground truth \\(y_i\\)
21-
and the prediction from the neighbor \\(g_\theta(x_j)\\). This is commonly used
20+
neighbor loss, which calculates the distance between the ground truth
21+
![equation](http://www.sciweavers.org/tex2img.php?eq=%20%5C%28y_i%5C%29&bc=White&fc=Black&im=jpg&fs=12&ff=arev&edit=0)
22+
and the prediction from the neighbor ![equation](http://www.sciweavers.org/tex2img.php?eq=%5C%28g_%5Ctheta%28x_j%29%5C%29&bc=White&fc=Black&im=jpg&fs=12&ff=arev&edit=0).
23+
This is commonly used
2224
in adversarial learning
2325
[(Goodfellow et al., ICLR'15)](https://arxiv.org/pdf/1412.6572.pdf). Therefore,
2426
NSL generalizes to **Neural Graph Learning** if neighbors are explicitly

0 commit comments

Comments
 (0)