Readings - Revision history

Sinoa at 08:26, 6 May 2025

2025-05-06T08:26:28Z

← Older revision		Revision as of 08:26, 6 May 2025
Line 242:		Line 242:
	* [[:file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]		* [[:file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]

			<!--
	==Session 13: KGs in Practice==		==Session 13: KGs in Practice==

Line 258:		Line 259:

	Useful materials:		Useful materials:
			-->

	<!--		<!--

Sinoa at 08:26, 6 May 2025

2025-05-06T08:26:11Z

← Older revision		Revision as of 08:26, 6 May 2025
Line 19:		Line 19:
	''Note:'' to download some of the papers, you may need to be inside UiB's network. Either use a computer directly on the UiB network or connect to your UiB account through VPN.		''Note:'' to download some of the papers, you may need to be inside UiB's network. Either use a computer directly on the UiB network or connect to your UiB account through VPN.

	=Lectures ~~(in progress)~~=		=Lectures=

	Below are the mandatory and suggested readings for each lecture. All the textbook chapters in Hogan et al. ("Knowledge Graphs") are mandatory, whereas the chapters in Allemang, Hendler & Gandon ("Semantic Web") are suggested.		Below are the mandatory and suggested readings for each lecture. All the textbook chapters in Hogan et al. ("Knowledge Graphs") are mandatory, whereas the chapters in Allemang, Hendler & Gandon ("Semantic Web") are suggested.
Line 61:		Line 61:

	Useful materials:		Useful materials:
	* Chapter 6 in Allemang, Hendler & Gandon (3rd edition)		* Chapter 6 in Allemang, Hendler & Gandon (3rd edition)3.12 Session 12: KGs and LLMs
	* [http://www.w3.org/TR/sparql11-query/ SPARQL 1.1 Query Language]		* [http://www.w3.org/TR/sparql11-query/ SPARQL 1.1 Query Language]
	* [http://www.w3.org/TR/sparql11-update/ SPARQL 1.1 Update Language]		* [http://www.w3.org/TR/sparql11-update/ SPARQL 1.1 Update Language]

Sinoa: /* Session 12: KGs and LLMs */

2025-04-28T09:16:18Z

Session 12: KGs and LLMs

← Older revision		Revision as of 09:16, 28 April 2025
Line 238:		Line 238:

	Useful materials:		Useful materials:
	* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf Pan et al. (2024) ''Unifying large language models and knowledge graphs: A roadmap'']]		* [[:file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf \| Pan et al. (2024) ''Unifying large language models and knowledge graphs: A roadmap'']]
	* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf Vaswani et al. (2017) ''Attention is all you need'']]		* [[:file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf \| Vaswani et al. (2017) ''Attention is all you need'']]
	* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]		* [[:file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]

	==Session 13: KGs in Practice==		==Session 13: KGs in Practice==

Sinoa: /* Session 12: KGs and LLMs */

2025-04-28T09:15:26Z

Session 12: KGs and LLMs

← Older revision		Revision as of 09:15, 28 April 2025
Line 238:		Line 238:

	Useful materials:		Useful materials:
	* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf \| Pan et al. (2024) ''Unifying large language models and knowledge graphs: A roadmap'']]		* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf Pan et al. (2024) ''Unifying large language models and knowledge graphs: A roadmap'']]
	* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf \| Vaswani et al. (2017) ''Attention is all you need'']]		* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf Vaswani et al. (2017) ''Attention is all you need'']]
	* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]		* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]

	==Session 13: KGs in Practice==		==Session 13: KGs in Practice==

Sinoa at 09:14, 28 April 2025

2025-04-28T09:14:47Z

← Older revision		Revision as of 09:14, 28 April 2025
Line 238:		Line 238:

	Useful materials:		Useful materials:
	* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf \| Unifying ~~Large Language Models~~ and ~~Knowledge Graphs~~: A ~~Roadmap~~]]		* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf \| Pan et al. (2024) ''Unifying large language models and knowledge graphs: A roadmap'']]
	* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf \| Attention is ~~All You Need~~]]		* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf \| Vaswani et al. (2017) ''Attention is all you need'']]
	* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| ~~Neurosymbolic AI~~]]		* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Hitzler et al. (2022) ''Neuro-symbolic approaches in artificial intelligence'']]

	==Session 13: KGs in Practice==		==Session 13: KGs in Practice==

Sinoa at 09:11, 28 April 2025

2025-04-28T09:11:44Z

← Older revision		Revision as of 09:11, 28 April 2025
Line 238:		Line 238:

	Useful materials:		Useful materials:
			* [[file:PanEtAl2023-Unifying_Large_Language_Models_and_Knowledge_Graphs_A_Roadmap.pdf \| Unifying Large Language Models and Knowledge Graphs: A Roadmap]]
			* [[file:Vaswani17-AttentionIsAllYouNeed-1706.03762%281%29.pdf \| Attention is All You Need]]
			* [[file:HitzlerEtAl-NeuroSymbolicIntegration-swj2291.pdf \| Neurosymbolic AI]]

	==Session 13: KGs in Practice==		==Session 13: KGs in Practice==

Sinoa at 09:05, 28 April 2025

2025-04-28T09:05:28Z

← Older revision		Revision as of 09:05, 28 April 2025
Line 224:		Line 224:
	* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG Documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.		* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG Documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.

	==Session 12: ~~KG Refinement (~~KGs and LLMs)==		==Session 12: KGs and LLMs==

	Themes:		Themes:
	* ~~Enriching~~ KGs		* Large Language Models (LLMs)
			* Combining KGs and Large Language Models (LLMs)
			** retrieval augmented knowledge fusion
			** end-to-end KG construction
			** LLM-augmented KG to text generation
			** KG-LLM synergy

	Mandatory readings:		Mandatory readings:

Sinoa: /* Session 11: Graph Neural Networks (GNNs) */

2025-04-07T08:52:42Z

Session 11: Graph Neural Networks (GNNs)

← Older revision		Revision as of 08:52, 7 April 2025
Line 222:		Line 222:
	* [[:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf \| The QA-GNN paper]]		* [[:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf \| The QA-GNN paper]]
	* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph		* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph
	* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG ~~documentation~~:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.		* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG Documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.

	==Session 12: KG Refinement (KGs and LLMs)==		==Session 12: KG Refinement (KGs and LLMs)==

Sinoa at 08:51, 7 April 2025

2025-04-07T08:51:40Z

← Older revision		Revision as of 08:51, 7 April 2025
Line 220:		Line 220:

	Useful materials:		Useful materials:
	* [[:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf [[The QA-GNN paper]]]]		* [[:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf \| The QA-GNN paper]]
	* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph		* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph
	* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.		* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.

Sinoa: /* Session 11: Graph Neural Networks (GNNs) */

2025-04-07T08:50:36Z

Session 11: Graph Neural Networks (GNNs)

← Older revision		Revision as of 08:50, 7 April 2025
Line 220:		Line 220:

	Useful materials:		Useful materials:
	* [:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf The QA-GNN paper]		* [[:file:Yasunaga2022-QA-GNN-2104.06378v5.pdf [[The QA-GNN paper]]]]
	* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph		* [https://conceptnet.io/ ConceptNet:] An open, multilingual knowledge graph
	* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.		* [https://pytorch-geometric.readthedocs.io/en/latest/ PyG documentation:] PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.