Filters

2,555 Hits in 4.8 sec

### On the Equivalence of Holographic and Complex Embeddings for Link Prediction [article]

Katsuhiko Hayashi, Masashi Shimbo
<span title="2017-09-22">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show the equivalence of two state-of-the-art link prediction/knowledge graph completion methods: Nickel et al's holographic embedding and Trouillon et al.'s complex embedding.  ...  Conversely, any complex embedding can be converted to an equivalent holographic embedding.  ...  Conversely, given a set of complex embeddings for entities and relations, we can construct their equivalent holographic embeddings, in the sense that f ComplEx (r, s, o) = c f HolE (r, s, o) for every  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05563v3">arXiv:1702.05563v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wqmbtkife5gffarmkrsecuvhsi">fatcat:wqmbtkife5gffarmkrsecuvhsi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826183135/https://arxiv.org/pdf/1702.05563v3.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/53/9b/539b8888b008aad7aec558277ff77ca129b6b284.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05563v3" 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>

### On the Equivalence of Holographic and Complex Embeddings for Link Prediction

Katsuhiko Hayashi, Masashi Shimbo
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</a> </i> &nbsp;
We show the equivalence of two stateof-the-art models for link prediction/ knowledge graph completion: Nickel et al's holographic embeddings and Trouillon et al.'s complex embeddings.  ...  Conversely, any set of complex embeddings can be converted to a set of equivalent holographic embeddings.  ...  Acknowledgments We thank the anonymous reviewers for helpful comments. This work was partially supported by JSPS Kakenhi Grants 26730126 and 15H02749.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p17-2088">doi:10.18653/v1/p17-2088</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/HayashiS17.html">dblp:conf/acl/HayashiS17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zdtjgt66ajg6fiahafpeswhsda">fatcat:zdtjgt66ajg6fiahafpeswhsda</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305150043/https://www.aclweb.org/anthology/P17-2088.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/e2/c6/e2c69421f18d26b7dfb77fb948d59f0160c7e96e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p17-2088"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

### Complex and Holographic Embeddings of Knowledge Graphs: A Comparison [article]

Théo Trouillon, Maximilian Nickel
<span title="2017-07-23">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Embeddings of knowledge graphs have received significant attention due to their excellent performance for tasks like link prediction and entity resolution.  ...  In this short paper, we are providing a comparison of two state-of-the-art knowledge graph embeddings for which their equivalence has recently been established, i.e., ComplEx and HolE [Nickel, Rosasco,  ...  Acknowledgments This work was supported in part by the Association Nationale de la Recherche et de la Technologie through the CIFRE grant 2014/0121.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.01475v2">arXiv:1707.01475v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/23bvsysxc5akjpp5zdram7kfou">fatcat:23bvsysxc5akjpp5zdram7kfou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191016152501/https://arxiv.org/pdf/1707.01475v2.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/9c/cb/9ccb11a33b4516c51f0d48678fe02624cbe38786.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.01475v2" 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>

### Holographic Embeddings of Knowledge Graphs [article]

Maximilian Nickel, Lorenzo Rosasco, Tomaso Poggio
<span title="2015-12-07">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In extensive experiments we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction in knowledge graphs and relational learning benchmark datasets.  ...  Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs.  ...  The code for models and experiments used in this paper is available at https://github.com/ mnick/holographic-embeddings.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1510.04935v2">arXiv:1510.04935v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fzduf75wenezbp26ohyy4emqxa">fatcat:fzduf75wenezbp26ohyy4emqxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910042625/https://arxiv.org/pdf/1510.04935v2.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/bb/75/bb75de5280ff9b0bbdd74633b9887d10fbe0ae10.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1510.04935v2" 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>

### CirE: Circular Embeddings of Knowledge Graphs [chapter]

Zhijuan Du, Zehui Hao, Xiaofeng Meng, Qiuyue Wang
<span title="">2017</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Extensive experiments show that CirE outperforms state-of-the-art baselines in link prediction and entity classification, justifying the efficiency and the scalability of CirE.  ...  The embedding representation technology provides convenience for machine learning on knowledge graphs (KG), which encodes entities and relations into continuous vector spaces and then constructs entity  ...  Link Prediction The role of link prediction is to predict the missing h or t for a given fact (h, r, t) [1, 2] . We evaluate our CirE on WN18 and FB15K, the results are shown in Table 4 .  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-55753-3_10">doi:10.1007/978-3-319-55753-3_10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/me27e2z4hjhg5keimfyuem4wjy">fatcat:me27e2z4hjhg5keimfyuem4wjy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190219222511/http://pdfs.semanticscholar.org/1f9e/8400a7924bee6a21aa840a43a0d5efcc5345.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/1f/9e/1f9e8400a7924bee6a21aa840a43a0d5efcc5345.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-55753-3_10"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

### Holographic Factorization Machines for Recommendation

Yi Tay, Shuai Zhang, Anh Tuan Luu, Siu Cheung Hui, Lina Yao, Tran Dang Quang Vinh
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
This paper proposes Holographic Factorization Machines (HFM), a new novel method of enhancing the representation capability of FMs without increasing its parameter size.  ...  Factorization Machines (FMs) are a class of popular algorithms that have been widely adopted for collaborative filtering and recommendation tasks.  ...  (Hayashi and Shimbo 2017) showed the equivalence of HRRs with complex-valued inner product, drawing parallels with HOLE and ComplEx, a complex-valued embedding model for link prediction (Trouillon et  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33015143">doi:10.1609/aaai.v33i01.33015143</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gytn74wgunhwrprnme4cgtbfxe">fatcat:gytn74wgunhwrprnme4cgtbfxe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305123318/https://www.aaai.org/ojs/index.php/AAAI/article/download/4448/4326" 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/ef/e9/efe9c4bd52d90c45b26fb0339ba6e33a08cd7bb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33015143"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

### Context-Aware Holographic Communication Based on Semantic Knowledge Extraction

Agata Manolova, Krasimir Tonchev, Vladimir Poulkov, Sudhir Dixir, Peter Lindgren
<span title="2021-06-03">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5ldpa66mwbhejga74di7sle7j4" style="color: black;">Wireless personal communications</a> </i> &nbsp;
The goal of the paper is to present a model of a context-aware holographic architecture for real time communication based on semantic knowledge extraction.  ...  This architecture will require analyzing, combining and developing methods and algorithms for: 3D human body model acquisition; semantic knowledge extraction with deep neural networks to predict human  ...  The purpose of the registration is to find the transformations that link the data from the individual images and thus bring the shared regions into one aggregate model.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11277-021-08560-7">doi:10.1007/s11277-021-08560-7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jx7fyfjqcne7xo7jz6ezjrrbbe">fatcat:jx7fyfjqcne7xo7jz6ezjrrbbe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718080707/https://link.springer.com/content/pdf/10.1007/s11277-021-08560-7.pdf?error=cookies_not_supported&amp;code=b7753e84-6ec0-41d5-8733-419cef01b020" 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/77/2d/772d18e8c5a87d0a659d89f120f65eb44f73f252.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11277-021-08560-7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

### Inverse magnetic catalysis in bottom-up holographic QCD

Nick Evans, Carlisson Miller, Marc Scott
<span title="2016-10-21">2016</span> <i title="American Physical Society (APS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/m2dr5bxn6ne7tmkwh3btn7xxhu" style="color: black;">Physical Review D</a> </i> &nbsp;
Bottom up holography is a form of effective field theory and we use it to explore the dependence on the coefficients of the two lowest order terms linking the magnetic field and the quark condensate.  ...  This behaviour is due to the separation of the meson melting and chiral transitions in the holographic framework.  ...  Acknowledgements: NE and MS are grateful for the support of STFC. CM thanks CAPES (Proc. 9397/2014-0).  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevd.94.074034">doi:10.1103/physrevd.94.074034</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jxoqfmoofvchfdycxpgtojg25u">fatcat:jxoqfmoofvchfdycxpgtojg25u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180722145756/https://eprints.soton.ac.uk/401891/1/__soton.ac.uk_UDE_PersonalFiles_Users_skr1c15_mydocuments_eprints_Theory_Evans_IMC_prd3.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/0f/8a/0f8af382b1dba02d4b60e5efc9e99e2fb3d59b12.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevd.94.074034"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> aps.org </button> </a>

### Complex Embeddings for Simple Link Prediction [article]

Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard
<span title="2016-06-20">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the  ...  However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations.  ...  Acknowledgements This work was supported in part by the Paul Allen Foundation through an Allen Distinguished Investigator grant and in part by a Google Focused Research Award.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.06357v1">arXiv:1606.06357v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kk7npreevfetfj27cwh7m4nek4">fatcat:kk7npreevfetfj27cwh7m4nek4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903092437/https://arxiv.org/pdf/1606.06357v1.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/1606.06357v1" 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>

### Drug target discovery using knowledge graph embeddings

Sameh K. Mohamed, Aayah Nounu, Vít Nováček
<span title="">2019</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/uo6yx5jpgnf2zl7mkrumytd4ti" style="color: black;">Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing - SAC &#39;19</a> </i> &nbsp;
In this work, we introduce a novel computational approach for predicting drug target proteins. We approach the problem as a link prediction task on knowledge graphs.  ...  Specifically, the method predicts drug target links with mean reciprocal rank (MRR) of 0.78 and Hits@10 of 0.88.  ...  They showed that despite the equivalence of both the ComplEx and the Holographic embedding (HolE) [24] models, they vary in accuracy due to their dependency on different training loss objectives.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3297280.3297282">doi:10.1145/3297280.3297282</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sac/MohamedNN19.html">dblp:conf/sac/MohamedNN19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/syou44fq4bgthfynq245wzsgwa">fatcat:syou44fq4bgthfynq245wzsgwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200307194612/https://aran.library.nuigalway.ie/bitstream/handle/10379/15065/paper-drugtar.pdf;jsessionid=55E7A501E9E51D138F091295A150F399?sequence=1" 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/88/8e/888efba4f0032fc11e83113636e90ce710e0300e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3297280.3297282"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

### Complex Embedding with Type Constraints for Link Prediction

Xiaohui Li, Zhiliang Wang, Zhaohui Zhang
<span title="2022-02-25">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4d3elkqvznfzho6ki7a35bt47u" style="color: black;">Entropy</a> </i> &nbsp;
, and type constraints were integrated into complex representational embeddings for improving link prediction.  ...  Experimental results on benchmark datasets showed that CHolE outperformed previous state-of-the-art methods, and the impartment of type constraints improved its performance on link prediction effectively  ...  Acknowledgments: The authors express their thanks for the technical guidance and support of Xie, R. for the dataset processing. Conflicts of Interest: The authors declare no conflict of interest.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e24030330">doi:10.3390/e24030330</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35327841">pmid:35327841</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8947114/">pmcid:PMC8947114</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c5tkpl5ycjfw5fepxgobii3kgu">fatcat:c5tkpl5ycjfw5fepxgobii3kgu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220505101916/https://mdpi-res.com/d_attachment/entropy/entropy-24-00330/article_deploy/entropy-24-00330-v2.pdf?version=1646123052" 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/00/63/00632b421cd095a93a566b6f26c940968541771d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e24030330"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947114" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

### Knowledge Graph Embedding with Multiple Relation Projections [article]

Kien Do, Truyen Tran, Svetha Venkatesh
<span title="2018-01-26">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experimental results on the canonical link prediction task show that our proposed model outperforms competing rivals by a large margin and achieves state-of-the-art performance.  ...  Especially, TransF improves by 9%/5% in the head/tail entity prediction task for N-to-1/1-to-N relations over the best performing translation-based method.  ...  II PREDICTION RESULTS ON WN18, FB15K, WN18RR AND FB15K-237. *: THE RESULT OF DISTMULT AND COMPLEX ON WN18RR AND FB15K-237 ARE TAKEN FROM [11] .  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.08641v1">arXiv:1801.08641v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tksyzqblknbifn4nmyoyb6etwq">fatcat:tksyzqblknbifn4nmyoyb6etwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907174220/https://arxiv.org/pdf/1801.08641v1.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/dc/eb/dceb5648d71776efa0cb9230d2470e4f3d92126a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.08641v1" 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>

### Poincaré Embeddings for Learning Hierarchical Representations [article]

Maximilian Nickel, Douwe Kiela
<span title="2017-05-26">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincar\'e embeddings outperform Euclidean embeddings significantly on data with  ...  However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property  ...  Reconstruction and Link Prediction on network data.  ...
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.08039v2">arXiv:1705.08039v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ywwlc2um4bg3nccz6gk2wqfwma">fatcat:ywwlc2um4bg3nccz6gk2wqfwma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191026153007/https://arxiv.org/pdf/1705.08039v2.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/65/99/6599ceebab0a3a1ca36e5aacba87af8ab25e7438.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.08039v2" 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>