Filters








32,471 Hits in 3.9 sec

Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings

Remzi Celebi, Huseyin Uyar, Erkan Yasar, Ozgur Gumus, Oguz Dikenelli, Michel Dumontier
2019 BMC Bioinformatics  
Methods for prediction of DDIs have the tendency to report high accuracy but still have little impact on translational research due to systematic biases induced by networked/paired data.  ...  We also tested RDF2Vec on various drug knowledge graphs such as DrugBank, PharmGKB and KEGG to predict unknown drug-drug interactions.  ...  Emre Guney for providing his feedback on proposed cross-validation method.  ... 
doi:10.1186/s12859-019-3284-5 pmid:31852427 pmcid:PMC6921491 fatcat:qd7ugkxhpzhszmk6dtv6dt63qm

Interaction Prediction Problems in Link Streams [chapter]

Thibaud Arnoux, Lionel Tabourier, Matthieu Latapy
2019 SpringerBriefs in Statistics  
Predicting future interactions is a crucial question in all these contexts, but the problem is traditionally addressed by merging interactions into a graph or series of graphs, called snapshots [7, 9,  ...  First, one designs a model in order to make a prediction based on the fundamental assumption that future behaviors can be predicted from past observations.  ...  Pairwise likeliness functions for prediction tasks From now on, we suppose that the prediction problem and its evaluation method are set, and we focus on the prediction model.  ... 
doi:10.1007/978-3-030-14683-2_6 fatcat:ljqkjhcwjnd6herze67kuskhu4

Learning to Detect Human-Object Interactions With Knowledge

Bingjie Xu, Yongkang Wong, Junnan Li, Qi Zhao, Mohan S. Kankanhalli
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In particular, we construct a knowledge graph based on the ground-truth annotations of training dataset and external source.  ...  The recent advances in instance-level detection tasks lay a strong foundation for automated visual scenes understanding. However, the ability to fully comprehend a social scene still eludes us.  ...  Works have been done for learning to detect HOIs with constraints from interacting object locations [13, 15] , pairwise spatial configuration [5] to scene context of instances [10, 33] .  ... 
doi:10.1109/cvpr.2019.00212 dblp:conf/cvpr/XuWLZK19 fatcat:5vvxz2yilrg47i4qlnqnv2xy4i

Local and Global Context-Based Pairwise Models for Sentence Ordering [article]

Ruskin Raj Manku, Aditya Jyoti Paul
2021 arXiv   pre-print
For this task, most previous approaches have explored global context-based end-to-end methods using Sequence Generation techniques.  ...  a much better understanding of the functioning of pairwise models.  ...  However, the main motivation behind proposing this model for the pair order prediction task is because of a different pre-training task than BERT.  ... 
arXiv:2110.04291v1 fatcat:ilwqxxl4pjcutkuojvx7dcw6b4

xPACE and TASC Modeler: Tool support for data-driven context modeling [article]

Rodrigo Falcão, Rafael King, Antônio Lázaro Carvalho
2022 arXiv   pre-print
From a requirements engineering point of view, the elicitation of context-aware functionalities calls for context modeling, an early step that aims at understanding the application contexts and how it  ...  To improve this situation, we implemented xPACE and TASC Modeler, which are tools that support the automation of context modeling based on existing contextual data.  ...  The second part of the strategy takes the list of pairwise relations and builds a graph G by treating each pair as an edge of the graph.  ... 
arXiv:2204.06247v1 fatcat:cfdckfszjnbkxdgycsz5v5ibda

Neural Ranking Models for Document Retrieval [article]

Mohamed Trabelsi, Zhiyu Chen, Brian D. Davison, Jeff Heflin
2021 arXiv   pre-print
These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features.  ...  A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking.  ...  Abcnn: Attention-based convolutional neural network for modeling sentence pairs. Transactions of the Association for Computational Linguistics, 4, 259-272.  ... 
arXiv:2102.11903v1 fatcat:zc2otf456rc2hj6b6wpcaaslsa

Constructing Narrative Event Evolutionary Graph for Script Event Prediction [article]

Zhongyang Li, Xiao Ding, Ting Liu
2018 arXiv   pre-print
To solve the inference problem on NEEG, we present a scaled graph neural network (SGNN) to model event interactions and learn better event representations.  ...  Previous models based on event pairs or event chains cannot make full use of dense event connections, which may limit their capability of event prediction.  ...  The authors would like to thank the anonymous reviewers for the insightful comments. They also thank Haochen Chen and Yijia Liu for the helpful discussion.  ... 
arXiv:1805.05081v2 fatcat:ar5udtjjonahvd6c2lscnnszzi

Constructing Narrative Event Evolutionary Graph for Script Event Prediction

Zhongyang Li, Xiao Ding, Ting Liu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
To solve the inference problem on NEEG, we present a scaled graph neural network (SGNN) to model event interactions and learn better event representations.  ...  Previous models based on event pairs or event chains cannot make full use of dense event connections, which may limit their capability of event prediction.  ...  The authors would like to thank the anonymous reviewers for the insightful comments. They also thank Haochen Chen and Yijia Liu for the helpful discussion.  ... 
doi:10.24963/ijcai.2018/584 dblp:conf/ijcai/LiDL18 fatcat:xbbe2mysofhflit5dqbm6gf2tm

Cartesian Kernel: An Efficient Alternative to the Pairwise Kernel

Hisashi KASHIMA, Satoshi OYAMA, Yoshihiro YAMANISHI, Koji TSUDA
2010 IEICE transactions on information and systems  
The pairwise kernel has been proposed for those purposes by several research groups independently, and has been used successfully in several fields.  ...  While the existing pairwise kernel (which we refer to as the Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can  ...  Models for pairwise prediction should take a pair of in-stances as input, and output a relationship between the two instances.  ... 
doi:10.1587/transinf.e93.d.2672 fatcat:lsdwk4uwvnc6pge3igfnwine5m

Protein Interaction Networks: Protein Domain Interaction and Protein Function Prediction [chapter]

Yanjun Qi, William Stafford Noble
2011 Handbook of Statistical Bioinformatics  
These inferences are based on the premise that the function of a protein may be discovered by studying its interaction with one or more proteins of known functions.  ...  Most of a cell's functional processes involve interactions among proteins, and a key challenge in proteomics is to better understand these complex interaction graphs at a systems level.  ...  (b) Global model based on pairwise kernel approach, where each edge is treated independently. (c) Local model for protein v 2 .  ... 
doi:10.1007/978-3-642-16345-6_21 fatcat:whl2kgd3rbfcjm3ljkd56tj7vq

Context-Aware Zero-Shot Recognition [article]

Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang
2019 arXiv   pre-print
The results on Visual Genome (VG) dataset show that our model significantly boosts performance with the additional visual context compared to traditional methods.  ...  The proposed algorithm is evaluated on both zero-shot region classification and zero-shot detection tasks.  ...  Zero-shot detection results We extend our region classification model for detection task by adding a background detector.  ... 
arXiv:1904.09320v3 fatcat:kpida5rvhbdsbge5lolzezszoq

Contextual Heterogeneous Graph Network for Human-Object Interaction Detection [article]

Hai Wang, Wei-Shi Zheng, Ling Yingbiao
2020 arXiv   pre-print
Human-object interaction(HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene.  ...  In addition, a graph attention mechanism based on the intra-class context and inter-class context is exploited to improve the learning.  ...  We evaluate our model on two HOI datasets: Metric. We adopt the mean average precision (mAP), which is generally used in detection tasks, for our evaluation.  ... 
arXiv:2010.10001v1 fatcat:myic6juxajgvdct7eh2tw5tzsa

Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions [article]

Fang Wu, Siyuan Li, Lirong Wu, Dragomir Radev, Qiang Zhang, Stan Z. Li
2022 arXiv   pre-print
To investigate the underlying mechanism, we explore the capacity of GNNs to capture pairwise interactions between nodes under contexts with different complexities, especially for their graph-level and  ...  To overcome that, we propose a novel graph rewiring approach based on the pairwise interaction strengths to adjust the reception fields of each node dynamically.  ...  For example, FC-graphs consist of all pairwise relations, while in KNN-graphs, some pairs of entities possess a relation and others do not.  ... 
arXiv:2205.07266v3 fatcat:mcplu5mksrerxaf5j76nn3i4lq

Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach [article]

M. Maruf, Anuj Karpatne
2021 arXiv   pre-print
Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as "cohesion") by maintaining positive and negative corpus  ...  Our approach can be used in conjunction with any GRL algorithm and we demonstrate the efficacy of our approach over baseline negative sampling methods over downstream node classification tasks on a number  ...  Overall, for small networks (CiteSeer, Cora, PPI and Synthetic networks), each training epochs on average takes one minute, whereas, for medium-size networks (PubMed), each training epochs take around  ... 
arXiv:2007.01423v2 fatcat:yqpujnmabbeghgrsldrkqdqnba

Evaluating Modules in Graph Contrastive Learning [article]

Ganqu Cui, Yufeng Du, Cheng Yang, Jie Zhou, Liang Xu, Xing Zhou, Xingyi Cheng, Zhiyuan Liu
2022 arXiv   pre-print
Based on this framework, we conduct controlled experiments over a wide range of architectural designs and hyperparameter settings on node and graph classification tasks.  ...  performance on graph classification.  ...  From this perspective, we try to investigate how the modules interact with each other and find out the bestperforming pairs. (3) Full model.  ... 
arXiv:2106.08171v2 fatcat:t3ruixdbazepndw2jk4cyl3yde
« Previous Showing results 1 — 15 out of 32,471 results