Filters








40,275 Hits in 2.5 sec

Embedding Uncertain Knowledge Graphs

Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge  ...  In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space.  ...  Uncertain Knowledge Graph Embedding Problem.  ... 
doi:10.1609/aaai.v33i01.33013363 fatcat:vqxhhyj3e5cfli5thjehdld5ga

Weighted MUSE for Frequent Sub-Graph Pattern Finding in Uncertain DBLP Data

Shawana Jamil, Azam Khan, Zahid Halim, A. Rauf Baig
2011 2011 International Conference on Internet Technology and Applications  
This paper focus on investigation of mining frequent sub-graph patterns in DBLP uncertain graph data using an approximation based method.  ...  Studies shows that finding frequent sub-graphs in uncertain graphs database is an NP complete problem.  ...  It will help to reduce computational cost and also in scanning of edges incident on the vertices while finding embeddings of S in the uncertain graphs, which also contributes in the finding of subgraph  ... 
doi:10.1109/itap.2011.6006415 fatcat:kglhmiqdcrabndrvuhgu5n2oha

Frequent subgraph pattern mining on uncertain graph data

Zhaonian Zou, Jianzhong Li, Hong Gao, Shuo Zhang
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
Mining uncertain graph data is semantically different from and computationally more challenging than mining exact graph data.  ...  This paper investigates the problem of mining frequent subgraph patterns from uncertain graph data.  ...  If S can be output, then output S and generate all direct superpatterns of S based on the embeddings of S in the uncertain graphs in D.  ... 
doi:10.1145/1645953.1646028 dblp:conf/cikm/ZouLGZ09 fatcat:oqeaypns5rga7f2nsogb7am2ey

SUKE: Embedding Model for Prediction in Uncertain Knowledge Graph

Jingbin Wang, Kuan Nie, Xinyuan Chen, Jing Lei
2020 IEEE Access  
Experimental results show that SUKE performs better than mainstream embedding methods. The model proposed in this paper can help advance the research on the embedding of uncertain knowledge graphs.  ...  Graph embedding models are widely used in knowledge graph completion (KGC) task.  ...  We also choose UKGE rect and UKGE logi in the uncertain graph embedding models as benchmarks.  ... 
doi:10.1109/access.2020.3047086 fatcat:4nlgpj524bedtkizz2oom4hpzm

Embedding Uncertain Knowledge Graphs [article]

Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
2019 arXiv   pre-print
Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge  ...  UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results on these tasks, and consistently outperforms baselines on these tasks.  ...  Uncertain Knowledge Graph Embedding Problem.  ... 
arXiv:1811.10667v2 fatcat:joig6esu7jgqvfgnys3grohxt4

A Relational-learning Perspective to Multi-label Chest X-ray Classification [article]

Anjany Sekuboyina, Daniel Oñoro-Rubio, Jens Kleesiek, Brandon Malone
2021 arXiv   pre-print
When tested on a publicly-available radiograph dataset (CheXpert), our relational-reformulation using a naive knowledge graph outperforms the state-of-art by achieving an area-under-ROC curve of 83.5%,  ...  Specifically, we construct a multi-modal knowledge graph out of the chest X-ray images and its labels and pose multi-label classification as a link prediction problem.  ...  A graph based on the co-occurrence of the labels is used to enrich the feature representations learnt by a naive convolutional neural network (CNN) working on images.  ... 
arXiv:2103.06220v1 fatcat:gdvd2dy5znhlfotuyttsuhrr3a

Improving Question Answering over Knowledge Graphs Using Graph Summarization [article]

Sirui Li, Kok Kai Wong, Dengya Zhu, Chun Che Fung
2022 arXiv   pre-print
Recently, Graph Convolutional Network (GCN) has shown to be excellent in providing entity embeddings.  ...  Previous KGQAs have attempted to represent entities using Knowledge Graph Embedding (KGE) and Deep Learning (DL) methods.  ...  Answer Selection Module Given a question and the summary graph embedding, the answer selection module selects one supernode that best answers the question.  ... 
arXiv:2203.13570v1 fatcat:wdqxdlz6gzgrxktlau72osqrta

Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels [article]

Daizong Liu, Shuangjie Xu, Pan Zhou, Kun He, Wei Wei, Zichuan Xu
2020 arXiv   pre-print
Experimental results on two popular chest X-ray (CXR) datasets show that our prediction accuracy outperforms state-of-the-arts, and the learned graph adjacency matrix establishes the correlation representations  ...  adjacency matrix in graph structure to improve the diagnosis accuracy.  ...  [5] exploited GCN to build up graph nodes with word embedding inputs to propagate features between multiple labels, and then made the classification depending on the constant correlation matrix initialized  ... 
arXiv:2002.11629v2 fatcat:cx4qsl6rmfd6dgjrjuh7usywia

Efficient subgraph similarity search on large probabilistic graph databases

Ye Yuan, Guoren Wang, Lei Chen, Haixun Wang
2012 Proceedings of the VLDB Endowment  
Different from previous works assuming that edges in an uncertain graph are independent of each other, we study the uncertain graphs where edges' occurrences are correlated.  ...  Therefore, in this paper, we study subgraph similarity search on large probabilistic graph databases.  ...  Zou et al [42, 43] studied frequent subgraph mining on uncertain graph data under the probability and expectation semantics respectively.  ... 
doi:10.14778/2311906.2311908 fatcat:p7bts6w4bra2jj4x6yijuv5h5u

Efficient Subgraph Similarity Search on Large Probabilistic Graph Databases [article]

Ye Yuan, Guoren Wang, Lei Chen, Haixun Wang
2012 arXiv   pre-print
Different from previous works assuming that edges in an uncertain graph are independent of each other, we study the uncertain graphs where edges' occurrences are correlated.  ...  Therefore, in this paper, we study subgraph similarity search on large probabilistic graph databases.  ...  Zou et al [42, 43] studied frequent subgraph mining on uncertain graph data under the probability and expectation semantics respectively.  ... 
arXiv:1205.6692v1 fatcat:5zk3zbjkqbaolbqze45tzufztm

Embedding Vector Differences Can Be Aligned With Uncertain Intensional Logic Differences [article]

Ben Goertzel, Mike Duncan, Debbie Duong, Nil Geisweiller, Hedra Seid, Abdulrahman Semrie, Man Hin Leung, Matthew Ikle'
2020 arXiv   pre-print
This relationship hints at a broader functorial mapping between uncertain intensional logic and vector arithmetic, and opens the door for using embedding vector algebra to guide intensional inference control  ...  to probabilistic inference regarding the causes of longevity based on data from biological ontologies and genomic analyses.  ...  Introduction Graph embedding algorithms assign vectors to nodes of a graph, with elegant properties such as: Nodes which are similar according to the graph topology and geometry get similar embedding vectors  ... 
arXiv:2005.12535v1 fatcat:a6itbwrxbzb2liw7gmbcytocf4

Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning [article]

Xuelu Chen, Michael Boratko, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li, Andrew McCallum
2021 arXiv   pre-print
To address these shortcomings, we propose BEUrRE, a novel uncertain knowledge graph embedding method with calibrated probabilistic semantics.  ...  Knowledge bases are also often incomplete, prompting the use of embedding methods to generalize from known facts, however, existing embedding methods only model triple-level uncertainty, and reasoning  ...  Uncertain Knowledge Graphs A UKG consists of a set of weighted triples G = {(l, s l )}.  ... 
arXiv:2104.04597v1 fatcat:s4n52rfflng4ji2oilba6poqla

A Comparative Study Of Frequent Subgraph Mining Algorithms

K Lakshmi
2012 International Journal of Advanced Information Technology  
Mining patterns from graph databases is challenging since graph related operations, such as subgraph testing, generally have higher time complexity than the corresponding operations on itemsets, sequences  ...  A graph is a general model to represent data and has been used in many domains like cheminformatics and bioinformatics.  ...  The third on the correctness of the graph data where it can be accurate or uncertain.  ... 
doi:10.5121/ijitcs.2012.2203 fatcat:qpsc44az4nhafmuekhbngp2eci

A new Graph Gaussian embedding method for analyzing the effects of cognitive training

Mengjia Xu, Zhijiang Wang, Haifeng Zhang, Dimitrios Pantazis, Huali Wang, Quanzheng Li
2020 PLoS Computational Biology  
We present a quantitative method for functional brain network analysis of fMRI data based on the multi-graph unsupervised Gaussian embedding method (MG2G).  ...  However, due to complex and uncertain brain connectivity features in the cognitive domains, it remains challenging to quantify functional brain connectomic changes during non-pharmacological interventions  ...  Most of the existing graph embedding methods focused only on a single and binary graph embedding. However, the human brain network is in the form of a weighted graph.  ... 
doi:10.1371/journal.pcbi.1008186 pmid:32941425 pmcid:PMC7524000 fatcat:clk2sbamwrcutpqjoy7gtplai4

Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction

Gun-Hee Lee, Seong-Whan Lee
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Our approach successfully employs Graph CNN and GAN for mesh decoder along with an uncertainty-aware image encoder to reconstruct shape and texture in high fidelity.  ...  Ablation Study on Uncertainty We conduct an experiment to study the effects of uncertainty embedding compared to the most recent 3D face reconstruction methods, which use deterministic embedding.  ...  Deterministic embeddings represent face as a point estimate without considering uncertain features. Figure 3 : 3 Figure 3: The framework of the proposed method.  ... 
doi:10.1109/cvpr42600.2020.00614 dblp:conf/cvpr/LeeL20a fatcat:oddsrwqawndgdeby55tal5a6ly
« Previous Showing results 1 — 15 out of 40,275 results