dgl/tutorials/models/3_generative_model at peizhou/negative__patch - dgl

mirror of https://github.com/dmlc/dgl.git synced 2026-06-06 20:04:24 +08:00

Files

Hongzhi (Steve), Chen 3c8ac0934e [Misc] Rename number_of_edges and number_of_nodes to num_edges and num_nodes. (#5490 )

* Other

* revert

---------

Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>

2023-03-29 11:00:26 +08:00

5_dgmg.py

[Misc] Rename number_of_edges and number_of_nodes to num_edges and num_nodes. (#5490 )

2023-03-29 11:00:26 +08:00

README.txt

[Doc] Tutorials re-organization (#2683 )

2021-02-20 17:42:45 +08:00

README.txt

.. _tutorials3-index:

Generative models
--------------------

* **DGMG** `[paper] <https://arxiv.org/abs/1803.03324>`__ `[tutorial]
  <3_generative_model/5_dgmg.html>`__ `[PyTorch code]
  <https://github.com/dmlc/dgl/tree/master/examples/pytorch/dgmg>`__:
  This model belongs to the family that deals with structural
  generation. Deep generative models of graphs (DGMG) uses a state-machine approach. 
  It is also very challenging because, unlike Tree-LSTM, every
  sample has a dynamic, probability-driven structure that is not available
  before training. You can progressively leverage intra- and
  inter-graph parallelism to steadily improve the performance.