44,598 Hits in 8.4 sec

Rule Learning from Knowledge Graphs Guided by Embedding Models [chapter]

Vinh Thinh Ho, Daria Stepanova, Mohamed H. Gad-Elrab, Evgeny Kharlamov, Gerhard Weikum
2018 Lecture Notes in Computer Science  
In particular, we iteratively extend rules induced from a KG by relying on feedback from a precomputed embedding model over the KG and external information sources including text corpora.  ...  Rules over a Knowledge Graph (KG) capture interpretable patterns in data and various methods for rule learning have been proposed.  ...  This requires major extensions for incorporating embedding models while avoiding scalability problems.  ... 
doi:10.1007/978-3-030-00671-6_5 fatcat:bikowhokvbes5na3ij7dtdrjyy

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [article]

Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen
2020 arXiv   pre-print
Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules.  ...  Thus, rich semantic knowledge of the relation labels is ignored. In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification.  ...  This work is funded by NSFC91846204/U19B2027/61473260, national key research program 2018YFB1402800/SQ2018YFC000004, Alibaba CangJingGe (Knowledge Engine) Research Plan.  ... 
arXiv:2010.16068v1 fatcat:32mls4yobvdr5lzyy3wd4o2ojq

A Survey of Knowledge Enhanced Pre-trained Models [article]

Jian Yang, Gang Xiao, Yulong Shen, Wei Jiang, Xinyu Hu, Ying Zhang, Jinghui Peng
2022 arXiv   pre-print
We first introduce the progress of pre-trained models and knowledge representation learning. Then we systematically categorize existing KEPTMs from three different perspectives.  ...  These models, however, suffer from poor robustness and lack of interpretability.  ...  Rule Guided KEPTMs As discussed above, presentation learning toward symbolic knowledge, like KGs, is a solution to bridge symbolic knowledge and pre-trained models.  ... 
arXiv:2110.00269v3 fatcat:b2g3ezuplvftfp7zlehvogd44m

Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning

TANG Caifang, RAO Yuan, YU Hualei, SUN Ling, CHENG Jiamin, WANG Yutian
2021 Chinese journal of electronics  
Based on the logic rules of knowledge and the role of adversarial learning in knowledge embedding, we proposes a model to improve the completion of knowledge graph: soft Rules and graph adversarial learning  ...  Firstly, the traditional knowledge graph embedding model is trained as generator and discriminator by using adversarial learning method, and high-quality negative samples are obtained.  ...  The model enables the embedding model to learn from labeled triples, unlabeled triples and soft rules iteratively.  ... 
doi:10.1049/cje.2021.05.004 fatcat:3pbeiup3ivgaljvggyucy7hmnm

Learning Rules from Incomplete KGs using Embeddings

Vinh Thinh Ho, Daria Stepanova, Mohamed H. Gad-Elrab, Evgeny Kharlamov, Gerhard Weikum
2018 International Semantic Web Conference  
In particular, we iteratively extend rules induced from a KG by relying on feedback from a precomputed embedding model over the KG and external information sources including text corpora.  ...  Rules over a Knowledge Graph (KG) capture interpretable patterns in data and various methods for rule learning have been proposed.  ...  We propose a rule learning approach guided by external sources, and show how to learn high-quality rules by utilizing feedback from embedding models.  ... 
dblp:conf/semweb/Ho0GKW18 fatcat:65ptz7siqrae3kvp6wtlw2acau

A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs [article]

Susheel Suresh, Jennifer Neville
2020 arXiv   pre-print
The problem of knowledge graph (KG) reasoning has been widely explored by traditional rule-based systems and more recently by knowledge graph embedding methods.  ...  Our method uses a cross feedback paradigm wherein, an embedding model is used to guide the search of a rule mining system to mine rules and infer new facts.  ...  ACKNOWLEDGMENT This research is supported by NSF under contract numbers CCF-1918483, IIS-1618690, and CCF-0939370.  ... 
arXiv:2009.10800v1 fatcat:jaipkweslvg6xaomiupgkmnjpu

Rule-Guided Compositional Representation Learning on Knowledge Graphs with Hierarchical Types

Yanying Mao, Honghui Chen
2021 Mathematics  
For rule path information, we mine Horn rules from the knowledge graph to guide the synthesis of relations in paths.  ...  The representation learning of the knowledge graph projects the entities and relationships in the triples into a low-dimensional continuous vector space.  ...  Conclusions In this paper, we propose the knowledge graph representation learning framework TRKRL, which combines rule path information and entity hierarchical type information.  ... 
doi:10.3390/math9161978 fatcat:lhisjpmn6jcxbe7gxqlx3upjj4

Guiding Graph Embeddings using Path-Ranking Methods for Error Detection innoisy Knowledge Graphs [article]

K. Bougiatiotis, R. Fasoulis, F. Aisopos, A. Nentidis, G. Paliouras
2020 arXiv   pre-print
noisy Knowledge Graphs.  ...  We compare different methods on two benchmarks and one real-world biomedical publications dataset, showcasing the potential of our approach and providing insights on graph embeddings when dealing with  ...  Acknowledgement This paper is supported by European Union's Horizon 2020 research and innovation programme under grant agreement No. 727658, project IASIS (Integration and analysis of heterogeneous big  ... 
arXiv:2002.08762v2 fatcat:rwexn7avpbaenhllmnpjnwmy2i

Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks [article]

Yun-Nung Chen, Dilek Hakkani-Tur, Gokhan Tur, Asli Celikyilmaz, Jianfeng Gao, Li Deng
2016 arXiv   pre-print
This paper introduces a novel model, knowledge-guided structural attention networks (K-SAN), a generalization of RNN to additionally incorporate non-flat network topologies guided by prior knowledge.  ...  There are two characteristics: 1) important substructures can be captured from small training data, allowing the model to generalize to previously unseen test data; 2) the model automatically figures out  ...  ., 2015) : predicts slots with sentence embeddings learned by an RNN model based on the tree structures of sentences.  ... 
arXiv:1609.03286v1 fatcat:ovmddipcgba7xiaujxymzfk6fm

Association Rules Enhanced Knowledge Graph Attention Network [article]

Zhenghao Zhang, Jianbin Huang, Qinglin Tan
2020 arXiv   pre-print
Most existing knowledge graphs suffer from incompleteness. Embedding knowledge graphs into continuous vector spaces has recently attracted increasing interest in knowledge base completion.  ...  In this manner, we learn embeddings compatible with triplets and rules, which are certainly more predictive for knowledge acquisition and inference.  ...  ACKNOWLEDGMENTS The work was supported by the National Natural Science Foundation of China [grant numbers: 61876138, 61602354].  ... 
arXiv:2011.08431v1 fatcat:l6sfja6ycng7bkszyclgih5qiu

Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs [article]

Daniel T. Chang
2022 arXiv   pre-print
The embodied representations are learned from molecular graphs, and the symbolic representations are learned from the corresponding Chemical knowledge graph (KG).  ...  We use the Chemical KG to enhance molecular graphs with symbolic (semantic) knowledge and generate their augmented molecular graphs.  ...  Chemical Knowledge Graphs Chemical knowledge graph embeddings can be generated from Chemical knowledge graphs (KGs).  ... 
arXiv:2205.06783v1 fatcat:ef5npq47p5aaxhxr5v6zx7dcui

A Survey of Knowledge Reasoning based on KG

Rui Lu, Zhiping Cai, Shan Zhao
2019 IOP Conference Series: Materials Science and Engineering  
KR based on Knowledge Graph(KG) is based on existing KG's facts.  ...  It uses some inference models and algorithms to infer new unknown knowledge and targets at improving the completeness and accuracy of KG.  ...  [44] proposed Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules; Ding B et al.  ... 
doi:10.1088/1757-899x/569/5/052058 fatcat:erpnnqzsy5hmhbgidjsb7dmplu

SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning [article]

Yushi Bai, Xin Lv, Juanzi Li, Lei Hou, Yincen Qu, Zelin Dai, Feiyu Xiong
2022 arXiv   pre-print
Multi-hop knowledge graph (KG) reasoning has been widely studied in recent years to provide interpretable predictions on missing links.  ...  Our model design brings about two benefits: (1) It can learn and predict in an end-to-end fashion, which gives better and faster convergence; (2) Our model does not rely on existing edges to generate the  ...  Related Work Knowledge graph embedding Knowledge graph embedding (KGE) methods map entities to vectors in a low-dimensional embedding space, and model relations as transformations between entity embeddings  ... 
arXiv:2201.06206v1 fatcat:ncgzi4oysrhudhwgo3jbaay6tm

KGClean: An Embedding Powered Knowledge Graph Cleaning Framework [article]

Congcong Ge, Yunjun Gao, Honghui Weng, Chong Zhang, Xiaoye Miao, Baihua Zheng
2020 arXiv   pre-print
KGClean first learns data representations by TransGAT, an effective knowledge graph embedding model, which gathers the neighborhood information of each data and incorporates the interactions among data  ...  We propose KGClean, a novel cleaning framework powered by knowledge graph embedding, to detect and repair the heterogeneous dirty data.  ...  KGClean employs the knowledge graph embedding model to automatically learn causalities, which could be considered as rules that can guide value cleaning in a knowledge graph.  ... 
arXiv:2004.14478v1 fatcat:nkbt75j46jfevbxyf5xzght27m

Towards Utilizing Knowledge Graph Embedding Models for Conceptual Clustering

Mohamed H. Gad-Elrab, Vinh Thinh Ho, Evgeny Levinkov, Trung-Kien Tran, Daria Stepanova
2020 International Semantic Web Conference  
We propose a framework to utilize Knowledge Graph (KG) embedding models for conceptual clustering, i.e., the task of clustering a given set of entities in a KG based on the quality of the resulting descriptions  ...  Specifically, prominent regions in the embedding space are detected using Multicut clustering algorithm, and then the queries describing/covering the entities within these regions are obtained by rule  ...  Another interesting direction is to investigate utilizing the learned rules for guiding the clustering process.  ... 
dblp:conf/semweb/Gad-ElrabHLTS20 fatcat:3idrwcvctrgrvmf5f3xmwaxrvm
« Previous Showing results 1 — 15 out of 44,598 results