Filters








7 Hits in 2.4 sec

KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features [article]

Alberto Garcia-Duran, Mathias Niepert
<span title="2018-06-11">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features.  ...  To the best of our knowledge, KBLRN is the first approach that learns representations of knowledge bases by integrating latent, relational, and numerical features.  ...  KBLRN: Learning End-To-End Joint Representations for Knowledge Bases With KBLRN we aim to provide a framework for endto-end learning of KB representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.04676v3">arXiv:1709.04676v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sf6j4d2p6fajvmxnb4j2nqmeuu">fatcat:sf6j4d2p6fajvmxnb4j2nqmeuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826142950/https://arxiv.org/pdf/1709.04676v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2a/7a/2a7ac9ef780d28e8d058a57f10438513c85a6c2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.04676v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Incorporating Literals into Knowledge Graph Embeddings [article]

Agustinus Kristiadi, Mohammad Asif Khan, Denis Lukovnikov, Jens Lehmann, Asja Fischer
<span title="2019-07-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Most of the existing work on embedding (or latent feature) based knowledge graph analysis focuses mainly on the relations between entities.  ...  Knowledge graphs, on top of entities and their relationships, contain other important elements: literals.  ...  In latent feature models, lowdimensional, latent representations (also called embeddings) of entities and relations are learned.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.00934v3">arXiv:1802.00934v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tn6yelj64ffmbfornmrqmu37ai">fatcat:tn6yelj64ffmbfornmrqmu37ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014112804/https://arxiv.org/pdf/1802.00934v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1e/8a/1e8a18455d83e5dab63e1d2cf9902a0dd02e52b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.00934v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly? [article]

Genet Asefa Gesese, Russa Biswas, Mehwish Alam, Harald Sack
<span title="2020-05-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form of entities and relations.  ...  Hence, there arises the necessity for a representation able to map the high dimensional KGs into low dimensional spaces, i.e., embedding space, preserving structural as well as relational information.  ...  KBLRN works by combining relational (R), latent (L), and numerical (N) features together. The model is designed mainly for the purpose of KG completion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.12507v2">arXiv:1910.12507v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j3roq6x4jfahnikk3yc4zclmlu">fatcat:j3roq6x4jfahnikk3yc4zclmlu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528141452/https://arxiv.org/pdf/1910.12507v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.12507v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ProcK: Machine Learning for Knowledge-Intensive Processes [article]

Tobias Jacobs, Jingyi Yu, Julia Gastinger, Timo Sztyler
<span title="2021-09-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Components to extract inter-linked event logs and knowledge bases from relational databases are part of the pipeline.  ...  In contrast, the success of modern machine learning is based on models that take any available data as direct input and build layers of features automatically during training.  ...  While KBlrn is able to exploit the graph structure, numerical features of the nodes, and domain knowledge in the form of logical rules, we only rely on the graph structure.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.04881v1">arXiv:2109.04881v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f4nttdl5b5g2zmdaj7iej5j6nq">fatcat:f4nttdl5b5g2zmdaj7iej5j6nq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210917045926/https://arxiv.org/pdf/2109.04881v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/11/7d115d674a1f5cbd83bba98e8493b549759635e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.04881v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes [article]

Sumit Pai, Luca Costabello
<span title="2021-05-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Numeric values associated to edges of a knowledge graph have been used to represent uncertainty, edge importance, and even out-of-band knowledge in a growing number of scenarios, ranging from genetic data  ...  Experiments with publicly available numeric-enriched knowledge graphs show that our method outperforms traditional numeric-unaware baselines as well as the recent UKGE model.  ...  KBLRN combines latent, relational and numeric features using product of experts model [Garcia-Duran and Niepert, 2017] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.08683v1">arXiv:2105.08683v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7ebd46aqs5cwtljuurwbuqunsy">fatcat:7ebd46aqs5cwtljuurwbuqunsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210520042429/https://arxiv.org/pdf/2105.08683v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a5/54/a554a1451b0c65463885d630a94b9888afb06c90.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.08683v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Leveraging literals for knowledge graph embeddings

Genet Asefa Gesese
<span title="">2021</span>
Hence, the main focus of this thesis is to deal with the multimodality and multilinguality of literals when utilizing them for the representation learning of KGs.  ...  However, there is a huge computational and storage cost associated with these KG-based applications.  ...  Acknowledgements I would like to thank my supervisors Prof. Dr. Harald Sack and Dr. Mehwish Alam for their invaluable mentoring and support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5445/ir/1000141527">doi:10.5445/ir/1000141527</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pzp3nljrwfae5dfqk4mjq4xjl4">fatcat:pzp3nljrwfae5dfqk4mjq4xjl4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220203125935/https://publikationen.bibliothek.kit.edu/1000141527/137280809" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d3/52/d3523059a9ee053a8c36a5ce9036ea35e2b0fd2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5445/ir/1000141527"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes

Sumit Pai, Luca Costabello
<span title="">2021</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence </i> &nbsp; <span class="release-stage">unpublished</span>
Numeric values associated to edges of a knowledge graph have been used to represent uncertainty, edge importance, and even out-of-band knowledge in a growing number of scenarios, ranging from genetic data  ...  Experiments with publicly available numeric-enriched knowledge graphs show that our method outperforms traditional numeric-unaware baselines as well as the recent UKGE model.  ...  KBLRN combines latent, relational and numeric features using product of experts model [Garcia-Duran and Niepert, 2017] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2021/395">doi:10.24963/ijcai.2021/395</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a54oy67webf2fa2cn3sqevsbwu">fatcat:a54oy67webf2fa2cn3sqevsbwu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210813001719/https://www.ijcai.org/proceedings/2021/0395.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0c/9b/0c9bd5be60a03ff36a9088823ac01e1ce6cc1706.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2021/395"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>