Filters








64,082 Hits in 4.3 sec

Learning to Explain Entity Relationships in Knowledge Graphs

Nikos Voskarides, Edgar Meij, Manos Tsagkias, Maarten de Rijke, Wouter Weerkamp
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
doi:10.3115/v1/p15-1055 dblp:conf/acl/VoskaridesMTRW15 fatcat:o6ezw3il4fbq5g2adbvl3ps4ly

On the role of knowledge graphs in explainable machine learning

Freddy Lecue
2021 Zenodo  
-date Name of the company/template : 87211168-GRP-EN-004 OPEN Knowledge Graph in Machine Learning (7) "How to explain transfer learning with appropriate knowledge representation?  ...  as knowledge graph embeddings / entities 10 OPEN Low-level features to high-level features Knowledge Graph in Machine Learning (4) Open question: What is the impact of semantic representation  ... 
doi:10.5281/zenodo.4903179 fatcat:jkpc2bfwtbayjawzl2vtymid7y

Deep Learning-Based Knowledge Graph Generation for COVID-19

Taejin Kim, Yeoil Yun, Namgyu Kim
2021 Sustainability  
However, traditional "dictionary-based" or "supervised" knowledge graph building methods rely on predefined human-annotated resources of entities and their relationships.  ...  Many attempts have been made to construct new domain-specific knowledge graphs using the existing knowledge base of various domains.  ...  (b) A COVID-19-specific knowledge graph can explain COVID-19-focused relationships between the entities in the general knowledge graph.  ... 
doi:10.3390/su13042276 fatcat:h3ubxdey6rdejmnpapsqwrvv6m

CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning [article]

Utkarshani Jaimini, Amit Sheth
2022 arXiv   pre-print
The proposed Causal Knowledge Graph (CausalKG) framework, leverages recent progress of causality and KG towards explainability.  ...  AI algorithms use a representation based on knowledge graphs (KG) to represent the concepts of time, space, and facts.  ...  This research is support in part by National Science Foundation (NSF) Award # 2133842 "EAGER: Advancing Neurosymbolic AI with Deep Knowledge-infused Learning," and Award #2119654, "RII Track 2 FEC: Enabling  ... 
arXiv:2201.03647v1 fatcat:kqeoqjsdz5dgjil2aqjj65ehzu

Knowledge Graph Reasoning Based on Tensor Decomposition and MHRP-Learning

Tangsen Huang, Xiaowu Li, Sheping Zhai, Juanli Wei, Constantine Kotropoulos
2021 Advances in Multimedia  
In the process of learning and reasoning knowledge graph, the existing tensor decomposition technology only considers the direct relationship between entities in knowledge graph.  ...  Firstly, MHRP-learning is adopted to obtain the relationship path between entity pairs in the knowledge graph. Then, the tensor decomposition is performed to get a novel learning framework.  ...  by means of MHRP-learning. (3) e multipath relationship between entities in knowledge graph and the new facts between entities are explored to further enrich and improve of knowledge graph. e rest of  ... 
doi:10.1155/2021/8880553 fatcat:uw5cbolttjg3zl334jhbpetbpe

Knowledge Graph-based Recommendation Systems: The State-of-the-art and Some Future Directions

Sajisha P. S, Anoop V.S, Ansal K. A
2019 International Journal of Machine Learning and Networked Collaborative Engineering  
Being a mechanism to represent entities and relationships using nodes and edges, knowledge graphs find applications in areas such as question answering, summarization, to name a few.  ...  Anyhow, we consider any knowledge base as a knowledge graph if it exhibits (1) represents entities and their relationships in nodes and edges (2) the classes and/or concepts and their relationships in  ... 
doi:10.30991/ijmlnce.2019v03i03.004 fatcat:45ornhc7qzceffqffv7z4xfdd4

LinkNBed: Multi-Graph Representation Learning with Entity Linkage

Rakshit Trivedi, Bunyamin Sisman, Xin Luna Dong, Christos Faloutsos, Jun Ma, Hongyuan Zha
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multiple graphs.  ...  An effective and scalable approach to jointly learn over multiple graphs and eventually construct a unified graph is a crucial next step for the success of knowledge-based inference for many downstream  ...  This project was supported in part by NSF(IIS-1639792, IIS-1717916).  ... 
doi:10.18653/v1/p18-1024 dblp:conf/acl/FaloutsosTSDMZ18 fatcat:2jbo23d3d5benelgik2byae3ni

Knowledge Graph Semantic Enhancement of Input Data for Improving AI

Shreyansh Bhatt, Amit Sheth, Valerie Shalin, Jinjin Zhao, Amit Sheth
2020 IEEE Internet Computing  
The term Knowledge Graph (KG) is in vogue as for many practical applications, it is convenient and useful to organize this background knowledge in the form of a graph.  ...  Background knowledge provides complementary, real world factual information that can augment the limited labeled data to train a machine learning algorithm.  ...  Iterative optimization for knowledge enhanced machine learning In order to augment input data effectively with a KG and to preserve the explainability potential of the KG, recent approaches iteratively  ... 
doi:10.1109/mic.2020.2979620 fatcat:q4xrsmddnfbvzjhev4xqknfo64

Explainable Link Prediction for Emerging Entities in Knowledge Graphs [article]

Rajarshi Bhowmik, Gerard de Melo
2020 arXiv   pre-print
To overcome this issue, we propose an inductive representation learning framework that is able to learn representations of previously unseen entities.  ...  However, these approaches typically consider static snapshots of the knowledge graphs, severely restricting their applicability for evolving knowledge graphs with newly emerging entities.  ...  Acknowledgement We thank Diffbot for their grant support to Rajarshi Bhowmik's work. We also thank Diffbot and Google for providing the computing infrastructure required for this project.  ... 
arXiv:2005.00637v2 fatcat:s2mkqqwbczeadg4qyi2os2ezj4

The Mobilisation of AI in Education: A Bourdieusean Field Analysis

Huw C Davies, Rebecca Eynon, Cory Salveson
2020 Sociology  
In this article, using a relatively novel method for sociology – a knowledge graph – together with Bourdieusean theory, we critically examine how and why different stakeholders in education, educational  ...  Drawing on this analysis, we argue that AI is currently being mobilised in education in problematic ways and advocate for more systematic sociological thinking and research to re-orientate the field to  ...  Acknowledgements The authors would like to thank the three anonymous reviewers for their helpful comments on the article and Dr Erin Young for her contribution to the research project.  ... 
doi:10.1177/0038038520967888 fatcat:mha5pwfg7bbbzlav64cmszweza

Wider Vision: Enriching Convolutional Neural Networks via Alignment to External Knowledge Bases [article]

Xuehao Liu, Sarah Jane Delany, Susan McKeever
2021 arXiv   pre-print
We use an entity alignment method to align the feature nodes in a CNN with the nodes in a ConceptNet based knowledge graph.  ...  Our demonstrated approach of aligning a CNN with an external knowledge base paves the way to reason about and beyond the trained model, with future adaptations to explainable models and zero-shot learning  ...  We note that this approach of bringing knowledge graphs into machine learning systems in order to expand knowledge beyond the training set is gaining traction in the machine learning research domain -and  ... 
arXiv:2102.11132v1 fatcat:ram3zstygzf77bfkox6pwyrsvi

Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs

Nicholas Halliwell
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This thesis is focused on providing a method, including datasets and scoring metrics, to quantitatively evaluate explanation methods on link prediction on Knowledge Graphs.  ...  Recently, explanation methods have been proposed to evaluate the predictions of Graph Neural Networks on the task of link prediction.  ...  In order to investigate this further, one first step would be to understand what properties of the graph the graph embedding has learned.  ... 
doi:10.1609/aaai.v36i11.21577 fatcat:5na5vxpixfdehoh5inoph6zaz4

Learning semantic Image attributes using Image recognition and knowledge graph embeddings [article]

Ashutosh Tiwari, Sandeep Varma
2020 arXiv   pre-print
Linking known entities in knowledge graphs and learning open-world images using language models has attracted lots of interest over the years.  ...  In this paper, we propose a shared learning approach to learn semantic attributes of images by combining a knowledge graph embedding model with the recognized attributes of images.  ...  ACKNOWLEDGEMENT The authors would like to extend their gratitude to all whose help and advice led to the completion of this work.  ... 
arXiv:2009.05812v1 fatcat:uquxuxscf5fgpfrjs6xhx6pbge

LinkNBed: Multi-Graph Representation Learning with Entity Linkage [article]

Rakshit Trivedi and Bunyamin Sisman and Jun Ma and Christos Faloutsos and Hongyuan Zha and Xin Luna Dong
2018 arXiv   pre-print
To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multiple graphs.  ...  An effective and scalable approach to jointly learn over multiple graphs and eventually construct a unified graph is a crucial next step for the success of knowledge-based inference for many downstream  ...  This project was supported in part by NSF(IIS-1639792, IIS-1717916).  ... 
arXiv:1807.08447v1 fatcat:lwls52nn6zgapmfbpds4syz2yu

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph [article]

Weizhi Ma, Min Zhang, Yue Cao, Woojeong, Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma, Xiang Ren
2019 arXiv   pre-print
In this paper, we propose a novel joint learning framework to integrate induction of explainable rules from knowledge graph with construction of a rule-guided neural recommendation model.  ...  Our model demonstrates robust performance over "noisy" item knowledge graphs, generated by linking item names to related entities.  ...  In the past years, knowledge graphs have been used as important resources for many tasks [7, 39] . One of the main usage of knowledge graph is reasoning and entity relationship prediction.  ... 
arXiv:1903.03714v1 fatcat:rodpblzg2vhwzdr2brwrfx6ybm
« Previous Showing results 1 — 15 out of 64,082 results