Unverified Commit e9632568 authored by István Ketykó's avatar István Ketykó Committed by GitHub
Browse files

[Doc] Update message-api.rst (#3844)



fix #3812
Co-authored-by: default avatarQuan (Andy) Gan <coin2028@hotmail.com>
Co-authored-by: default avatarMinjie Wang <wmjlyjemaine@gmail.com>
parent f73c7a64
......@@ -96,7 +96,7 @@ features ``ft``, and finally multiply ``ft`` by 2 to get the result
``final_ft``. After the call, DGL will clean the intermediate messages ``m``.
The math formula for the above function is:
.. math:: {final\_ft}_i = 2 * \sum_{j\in\mathcal{N}(i)} ({ft}_j * a_{ij})
.. math:: {final\_ft}_i = 2 * \sum_{j\in\mathcal{N}(i)} ({ft}_j * a_{ji})
DGL's built-in functions support floating point data types, i.e. the feature must
be ``half`` (``float16``) /``float``/``double`` tensors.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment