Filters








107,740 Hits in 5.5 sec

Handling temporality of clinical events with application to Adverse Drug Event detection in Electronic Health Records: A scoping review [article]

Maria Bampa
2019 arXiv   pre-print
The rich heterogeneous and temporal data space stored in EHRs can be leveraged by machine learning models to capture the underlying information and make clinically relevant predictions.  ...  Yet there still exists a great deal of challenges that concerns the exploitation of the heterogeneous, data types with temporal information included in EHRs for predicting ADEs.  ...  A step towards a safer healthcare is to understand how events can evolve in time and how these can be exploited in the correct way to increase the predictive performance of classification methods.  ... 
arXiv:1904.04940v1 fatcat:hce6dhg3g5dl5j77nighkz5wpq

Time-Series Event Prediction with Evolutionary State Graph [article]

Wenjie Hu, Yang Yang, Ziqiang Cheng, Carl Yang, Xiang Ren
2020 arXiv   pre-print
of event predictions.  ...  The accurate and interpretable prediction of future events in time-series data often requires the capturing of representative patterns (or referred to as states) underpinning the observed data.  ...  for event predictions.  ... 
arXiv:1905.05006v4 fatcat:fnsrdkoj7vgrzmy5k2xrdxrjkm

Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs

Jingwei Ji, Ranjay Krishna, Li Fei-Fei, Juan Carlos Niebles
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Finally, we benchmark existing scene graph models on the new task of spatio-temporal scene graph prediction.  ...  Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition  ...  "moving towards the sofa"). Action Genome's dynamic scene graph representations capture both such types of events and as such, represent the prototypical unit.  ... 
doi:10.1109/cvpr42600.2020.01025 dblp:conf/cvpr/JiK0N20 fatcat:ri7uc45iqvc55hri55uwzydfb4

Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs [article]

Zhen Han, Yunpu Ma, Yuyi Wang, Stephan Günnemann, Volker Tresp
2020 arXiv   pre-print
To address this issue, we propose the Graph Hawkes Neural Network that can capture the dynamics of evolving graph sequences and can predict the occurrence of a fact in a future time instance.  ...  Extensive experiments on large-scale temporal multi-relational databases, such as temporal knowledge graphs, demonstrate the effectiveness of our approach.  ...  A possible way is to embed events in a temporal knowledge graph, which is a graph-structured multi-relational database that stores an event in the form of a quadruple.  ... 
arXiv:2003.13432v3 fatcat:gl5jdo3ggzcpdbykc4oyrxph4i

Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey [article]

Joakim Skarding, Bogdan Gabrys, Katarzyna Musial
2020 arXiv   pre-print
Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification  ...  We contribute: (i) a comprehensive dynamic network taxonomy, (ii) a survey of dynamic graph neural networks and (iii) an overview of how dynamic graph neural networks can be used for dynamic link prediction  ...  As the prediction methods optimize towards link prediction directly, an autoencoder optimizes towards recreation of the dynamic graph and also can be used and have been shown to perform well in link prediction  ... 
arXiv:2005.07496v1 fatcat:ditdpefszzd6bfh4enbcdkztna

Temporal Knowledge Graph Reasoning Triggered by Memories [article]

Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
2021 arXiv   pre-print
Inferring missing facts in temporal knowledge graphs is a critical task and has been widely explored.  ...  Extrapolation in temporal reasoning tasks is more challenging and gradually attracts the attention of researchers since no direct history facts for prediction.  ...  INTRODUCTION R EASONING on Temporal Knowledge Graphs (TKGs) aggregate the time-aware real-world scenarios to infer missing facts and is applied in various tasks, such as event prediction [1] , question  ... 
arXiv:2110.08765v2 fatcat:6ohd4z4whbg6bksofi7r3vrlzm

Action Genome: Actions as Composition of Spatio-temporal Scene Graphs [article]

Jingwei Ji, Ranjay Krishna, Li Fei-Fei, Juan Carlos Niebles
2019 arXiv   pre-print
Finally, we benchmark existing scene graph models on the new task of spatio-temporal scene graph prediction.  ...  Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition  ...  "moving towards the sofa"). Action Genome's dynamic scene graph representations capture both such types of events and as such, represent the prototypical unit.  ... 
arXiv:1912.06992v1 fatcat:6iap73ap2zbi7bxdkrtvkn66wi

Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey

Joakim Skardinga, Bogdan Gabrys, Katarzyna Musial
2021 IEEE Access  
INDEX TERMS Dynamic network models, graph neural networks, link prediction, temporal networks.  ...  Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification  ...  As the prediction methods optimize towards link prediction directly, an autoencoder optimizes towards the recreation of the dynamic graph.  ... 
doi:10.1109/access.2021.3082932 fatcat:4pbp2kn6ovf65pnm5pbv7idpim

Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs [article]

Rakshit Trivedi, Hanjun Dai, Yichen Wang, Le Song
2017 arXiv   pre-print
The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge.  ...  Reasoning over time in such dynamic knowledge graphs is not yet well understood.  ...  Acknowledgement This project was supported in part by NSF IIS-1218749, NIH BIGDATA 1R01GM108341, NSF CAREER IIS-1350983, NSF IIS-1639792 EAGER, ONR N00014-15-1-2340, NVIDIA, Intel and Amazon AWS.  ... 
arXiv:1705.05742v3 fatcat:ipr7szsdkfc5bpbttttogllkpy

Timestamping Documents and Beliefs [article]

Swayambhu Nath Ray
2021 arXiv   pre-print
In this paper we propose NeuralDater, a Graph Convolutional Network (GCN) based document dating approach which jointly exploits syntactic and temporal graph structures of document in a principled way.  ...  The knowledge of creation date of documents facilitates several tasks like summarization, event extraction, temporally focused information extraction etc.  ...  In order to suppress the noisy edges in the Temporal Graph and detect important edges for reasoning, we use attentive graph convolution [28] over the Event-Time graph.  ... 
arXiv:2106.14622v1 fatcat:ilx3xrcmszdm3fai55f2fxcaxi

From predictive to prescriptive process monitoring: Recommending the next best actions instead of calculating the next most likely events [chapter]

Sven Weinzierl, Friedrich-Alexander Universität Erlangen-Nürnberg, Digital Industrial Service Systems, Nuremberg, Germany, Sandra Zilker, Matthias Stierle, Martin Matzner, Gyunam Park, Pohang University of Science and Technology, Analytics & Information Management Lab, Pohang, South Korea
2020 WI2020 Zentrale Tracks  
In this paper, we argue that the next event prediction is insufficient for practitioners.  ...  Existing techniques are geared towards the outcome prediction and deal with alarms for interventions or interventions that do not represent process events.  ...  First, we evaluated the usefulness through the percentage of process instances that could comply with the temporal threshold for different prefix lengths (cf., the left graph in Figure 1) .  ... 
doi:10.30844/wi_2020_c12-weinzierl dblp:conf/wirtschaftsinformatik/WeinzierlZSMP20 fatcat:mbwpztwbwnfe7d344a2pnmaqzm

A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data [article]

Yijun Lin, Yao-Yi Chiang
2021 arXiv   pre-print
abnormal events.  ...  Also, the recorded abnormal events can be sparse.  ...  We flatten an input graph sequence in time and node dimensions to be a large vector for predicting event or non-event. • Graph Attention Encoder (GAT): We concatenate features along the temporal dimension  ... 
arXiv:2110.07660v1 fatcat:lohyfkxibjachmzoitengvg7jm

Towards Efficient Semantically Enriched Complex Event Processing and Pattern Matching

Syed Gillani
2014 International Semantic Web Conference  
This restricts the system to employ temporal reasoning at RDF level and use historical events to predict new situations.  ...  Management and recognition of event patterns is becoming thoroughly ingrained in many application areas of Semantically enabled Complex Event Processing (SCEP).  ...  We propose a new data model for events that enables the temporal reasoning of streams at RDF level including past and recent events.  ... 
dblp:conf/semweb/Gillani14 fatcat:bgu67crrsvc3pitstw4fh3uu2i

Multi-Scale Contrastive Co-Training for Event Temporal Relation Extraction [article]

Hao-Ren Yao, Luke Breitfeller, Aakanksha Naik, Chunxiao Zhou, Carolyn Rose
2022 arXiv   pre-print
Extracting temporal relationships between pairs of events in texts is a crucial yet challenging problem for natural language understanding.  ...  Depending on the distance between the events, models must learn to differently balance information from local and global contexts surrounding the event pair for temporal relation prediction.  ...  R-GAT Prediction Head Syntactic and temporal graphs express distinct types of discourse-level semantic information about events.  ... 
arXiv:2209.00568v1 fatcat:z634hthucvbsvo2p2ffevmd4pa

TeGraF

Shivshankar Reddy, Pranav Poduval, Anand Vir Singh Chauhan, Maneet Singh, Sangam Verma, Karamjit Singh, Tanmoy Bhowmik
2021 Proceedings of the Second ACM International Conference on AI in Finance  
The proposed algorithm operates at the intersection of two key research areas: Temporal Point Processes (TPPs) and Graph Neural Networks (GNNs).  ...  Detection of fraudulent transactions is an imperative research area in the financial domain, affecting the different entities involved in the payment process.  ...  In all the tasks above, graph structure and the temporal nature of the transaction has been studied in isolation.  ... 
doi:10.1145/3490354.3494383 fatcat:shlh7hmbnbc7fgk4yehmxfuuqy
« Previous Showing results 1 — 15 out of 107,740 results