TWP
============

TWP is a continual learning method for graphs, which stabilizes parameters important in topological aggregation by graph neural networks through regularization.
For the details, see the `original paper <https://arxiv.org/pdf/1706.08840.pdf>`_.

Node-level Problems
-------------------------

.. automodule:: begin.algorithms.twp.nodes
    :undoc-members:
    :members:
    :private-members:

Link-level Problems
-------------------------

.. automodule:: begin.algorithms.twp.links
    :undoc-members:
    :members:
    :private-members:

Graph-level Problems
-------------------------

.. automodule:: begin.algorithms.twp.graphs
    :undoc-members:
    :members:
    :private-members: