Lab: Training Graph Embeddings - Revision history

Sinoa: /* Useful readings */

2023-04-18T06:38:35Z

Useful readings

← Older revision		Revision as of 06:38, 18 April 2023
Line 8:		Line 8:
	'''Classes and methods:'''		'''Classes and methods:'''
	The following TorchKGE class from the previous lab remains central:		The following TorchKGE class from the previous lab remains central:
	* '''Model''' - contains the embeddings (entity and relation vectors) for the KG		* ''Model'' - contains the embeddings (entity and relation vectors) for the KG

	In addition, we will also use:		In addition, we will also use:
	* '''KnowledgeGraph''' - contains the knowledge graph (KG)		* ''KnowledgeGraph'' - contains the knowledge graph (KG)

	==Tasks==		==Tasks==

Sinoa: /* Lab 14: Training Graph Embeddings */

2023-04-18T06:38:11Z

Lab 14: Training Graph Embeddings

← Older revision		Revision as of 06:38, 18 April 2023
Line 1:		Line 1:

	~~=Lab 14: Training Graph Embeddings=~~

	==Topics==		==Topics==

Sinoa at 06:37, 18 April 2023

2023-04-18T06:37:50Z

← Older revision		Revision as of 06:37, 18 April 2023
Line 5:		Line 5:
	Training knowledge graph embeddings with TorchKGE.		Training knowledge graph embeddings with TorchKGE.

	~~<!--~~ ==~~Tutorial~~== ~~-->~~		==Useful readings==
			* [https://torchkge.readthedocs.io/en/latest/ Welcome to TorchKGE’ s documentation!]

	==Classes and methods==		'''Classes and methods:'''
	The following TorchKGE class from the previous lab remains central:		The following TorchKGE class from the previous lab remains central:
	* '''Model''' - contains the embeddings (entity and relation vectors) for the KG		* '''Model''' - contains the embeddings (entity and relation vectors) for the KG
Line 14:		Line 14:
	In addition, we will also use:		In addition, we will also use:
	* '''KnowledgeGraph''' - contains the knowledge graph (KG)		* '''KnowledgeGraph''' - contains the knowledge graph (KG)

	~~More classes will be suggested below.~~

	~~<!--~~
	~~<syntaxhighlight>~~
	~~</syntaxhighlight>~~
	~~-->~~

	==Tasks==		==Tasks==
			'''Task: pre-trained models''':
	'''~~Pre~~-trained models''':
	* Choose a KG and TransE model you want to work with. It should have a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#pre-trained-models pre-trained model] available. (Freebase FB15k is still a good choice, see the note below if you want to use Wikidata.)		* Choose a KG and TransE model you want to work with. It should have a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#pre-trained-models pre-trained model] available. (Freebase FB15k is still a good choice, see the note below if you want to use Wikidata.)
	* Load the pre-trained model (you do no need the KG yet). and evaluate it using the examples given here: https://torchkge.readthedocs.io/en/latest/tutorials/evaluation.html .		* Load the pre-trained model (you do no need the KG yet). and evaluate it using the examples given here: https://torchkge.readthedocs.io/en/latest/tutorials/evaluation.html .
Line 31:		Line 23:
	''Note:'' The Wikidata dataset returns two graphs. They are not train/test, but the dataset with and without additional attributes. Start with the one without attributes. You need to split it into train/validation/test yourself using [https://torchkge.readthedocs.io/en/latest/reference/data.html#knowledge-graph KG.split_kg()].		''Note:'' The Wikidata dataset returns two graphs. They are not train/test, but the dataset with and without additional attributes. Start with the one without attributes. You need to split it into train/validation/test yourself using [https://torchkge.readthedocs.io/en/latest/reference/data.html#knowledge-graph KG.split_kg()].

	'''~~Train~~ your own''':		'''Task: train your own''':
	* Load the corresponding KG using a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#datasets-loaders dataset loader].		* Load the corresponding KG using a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#datasets-loaders dataset loader].
	* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Shortest training] example, '''but use a much lower value for epoch''' (for example 200).		* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Shortest training] example, '''but use a much lower value for epoch''' (for example 200).
Line 37:		Line 29:
	* Also run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Simplest training] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do.		* Also run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Simplest training] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do.

	'''~~Train~~ with early stopping''':		'''Task: train with early stopping''':
	* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Training with Ignite] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do. How do the results compare with your exploration of different ''epoch'' values?		* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Training with Ignite] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do. How do the results compare with your exploration of different ''epoch'' values?

	~~<!--~~
	~~==Code to get started==~~

	~~<syntaxhighlight>~~
	~~</syntaxhighlight>~~
	~~-->~~

	==If You Have More Time==		==If You Have More Time==
	* Try this out on the other models supported by TorchKGE, both other TransX models and a deep model (ConvKB).		* Try this out on the other models supported by TorchKGE, both other TransX models and a deep model (ConvKB).
	* Try it out with different datasets, for example one you create youreself using SPARQL queries on an open KG.		* Try it out with different datasets, for example one you create youreself using SPARQL queries on an open KG.

	~~==Useful readings==~~
	* [https://torchkge.readthedocs.io/en/latest/ Welcome to TorchKGE’ s documentation!]

Sinoa: /* Classes and methods */

2022-04-14T13:04:29Z

Classes and methods

← Older revision		Revision as of 13:04, 14 April 2022
Line 13:		Line 13:

	In addition, we will also use:		In addition, we will also use:
	* '''KG''' - contains the knowledge graph (KG)		* '''KnowledgeGraph''' - contains the knowledge graph (KG)

	More classes will be suggested below.		More classes will be suggested below.

Sinoa: /* Classes and methods */

2022-04-14T12:43:11Z

Classes and methods

← Older revision		Revision as of 12:43, 14 April 2022
Line 9:		Line 9:

	==Classes and methods==		==Classes and methods==
	The following TorchKGE ~~classes~~ from the previous lab ~~remain~~ central:		The following TorchKGE class from the previous lab remains central:
			* '''Model''' - contains the embeddings (entity and relation vectors) for the KG

			In addition, we will also use:
	* '''KG''' - contains the knowledge graph (KG)		* '''KG''' - contains the knowledge graph (KG)
	* '''Model''' - contains the embeddings (entity and relation vectors) for the KG

	More classes will be suggested below.		More classes will be suggested below.

Sinoa: /* Tasks */

2022-04-14T12:34:54Z

Tasks

← Older revision		Revision as of 12:34, 14 April 2022
Line 23:		Line 23:

	'''Pre-trained models''':		'''Pre-trained models''':
	* Choose a KG and TransE model you want to work with. It should have a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#pre-trained-models pre-trained model] available.		* Choose a KG and TransE model you want to work with. It should have a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#pre-trained-models pre-trained model] available. (Freebase FB15k is still a good choice, see the note below if you want to use Wikidata.)
	* Load the pre-trained model (you do no need the KG yet). and evaluate it using the examples given here: https://torchkge.readthedocs.io/en/latest/tutorials/evaluation.html .		* Load the pre-trained model (you do no need the KG yet). and evaluate it using the examples given here: https://torchkge.readthedocs.io/en/latest/tutorials/evaluation.html .
	* ''Extra:'' You can also evaluate the model on [https://torchkge.readthedocs.io/en/latest/reference/evaluation.html#relation-prediction relation prediction] but, the way TransE is pre-trained, it is awful on this task.		* ''Extra:'' You can also evaluate the model on [https://torchkge.readthedocs.io/en/latest/reference/evaluation.html#relation-prediction relation prediction] but, the way TransE is pre-trained, it is awful on this task.

			''Note:'' The Wikidata dataset returns two graphs. They are not train/test, but the dataset with and without additional attributes. Start with the one without attributes. You need to split it into train/validation/test yourself using [https://torchkge.readthedocs.io/en/latest/reference/data.html#knowledge-graph KG.split_kg()].

	'''Train your own''':		'''Train your own''':

Sinoa: /* Classes and methods */

2022-04-14T12:27:08Z

Classes and methods

← Older revision		Revision as of 12:27, 14 April 2022
Line 12:		Line 12:
	* '''KG''' - contains the knowledge graph (KG)		* '''KG''' - contains the knowledge graph (KG)
	* '''Model''' - contains the embeddings (entity and relation vectors) for the KG		* '''Model''' - contains the embeddings (entity and relation vectors) for the KG

			More classes will be suggested below.

	<!--		<!--
Line 17:		Line 19:
	</syntaxhighlight>		</syntaxhighlight>
	-->		-->


	==Tasks==		==Tasks==

Sinoa: Created page with " =Lab 14: Training Graph Embeddings= ==Topics== Training knowledge graph embeddings with TorchKGE. ==Classes and methods== The following TorchKGE cla..."

2022-04-14T12:18:28Z

Created page with " =Lab 14: Training Graph Embeddings= ==Topics== Training knowledge graph embeddings with TorchKGE.  ==Classes and methods== The following TorchKGE cla..."

New page

=Lab 14: Training Graph Embeddings=

==Topics==
Training knowledge graph embeddings with TorchKGE.



==Classes and methods==
The following TorchKGE classes from the previous lab remain central:
* '''KG''' - contains the knowledge graph (KG)
* '''Model''' - contains the embeddings (entity and relation vectors) for the KG



==Tasks==

'''Pre-trained models''':
* Choose a KG and TransE model you want to work with. It should have a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#pre-trained-models pre-trained model] available.
* Load the pre-trained model (you do no need the KG yet). and evaluate it using the examples given here: https://torchkge.readthedocs.io/en/latest/tutorials/evaluation.html .
* ''Extra:'' You can also evaluate the model on [https://torchkge.readthedocs.io/en/latest/reference/evaluation.html#relation-prediction relation prediction] but, the way TransE is pre-trained, it is awful on this task.

'''Train your own''':
* Load the corresponding KG using a [https://torchkge.readthedocs.io/en/latest/reference/utils.html#datasets-loaders dataset loader].
* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Shortest training] example, '''but use a much lower value for epoch''' (for example 200).
* Take note of the evaluation metrics and final loss, and re-run the example using different numbers of epochs. What happens when you increase the number?
* Also run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Simplest training] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do.

'''Train with early stopping''':
* Run the [https://torchkge.readthedocs.io/en/latest/tutorials/training.html Training with Ignite] example. Use the documentation to make sure you have an idea of what the different parts of the algorithm do. How do the results compare with your exploration of different ''epoch'' values?



==If You Have More Time==
* Try this out on the other models supported by TorchKGE, both other TransX models and a deep model (ConvKB).
* Try it out with different datasets, for example one you create youreself using SPARQL queries on an open KG.

==Useful readings==
* [https://torchkge.readthedocs.io/en/latest/ Welcome to TorchKGE’ s documentation!]