Filters








6,261 Hits in 7.6 sec

Deep Multi-attributed Graph Translation with Node-Edge Co-Evolution

Xiaojie Guo, Liang Zhao, Cameron Nowzari, Setareh Rafatirad, Houman Homayoun, Sai Manoj Pudukotai Dinakarrao
2019 2019 IEEE International Conference on Data Mining (ICDM)  
In this paper, we termed this generic problem "multi-attributed graph translation" and developed a novel framework integrating both node and edge translations seamlessly.  ...  Existing works are limited to either merely predicting the node attributes of graphs with fixed topology or predicting only the graph topology without considering node attributes, but cannot simultaneously  ...  This paper propose an Node-Edge Co-evolving Deep Graph Translator (NEC-DGT) with novel architecture and components for joint node and edge translation.  ... 
doi:10.1109/icdm.2019.00035 dblp:conf/icdm/Guo0NRHD19 fatcat:6bwixyecuvbirj4f55wwq6vsyu

Henshin: Advanced Concepts and Tools for In-Place EMF Model Transformations [chapter]

Thorsten Arendt, Enrico Biermann, Stefan Jurack, Christian Krause, Gabriele Taentzer
2010 Lecture Notes in Computer Science  
The Henshin transformation language has its roots in attributed graph transformations, which offer a formal foundation for validation of EMF model transformations.  ...  The transformation concepts are demonstrated using two case studies: EMF model refactoring and meta-model evolution.  ...  Neverthe-less, we give a practical idea how (semi-) automatic meta-model evolution can be realized with Henshin leading to an operator-based co-evolution approach.  ... 
doi:10.1007/978-3-642-16145-2_9 fatcat:klh76h4vqjhntji44euq2bgu7e

Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution [article]

Sankalp Garg, Navodita Sharma, Woojeong Jin, Xiang Ren
2020 arXiv   pre-print
Our framework, DArtNet, learns a static embedding for every node in the graph as well as a dynamic embedding which is dependent on the dynamic attribute value (time-series).  ...  Recently, there has been a focus on the application of deep representation learning on dynamic graphs.  ...  A Dynamic Attributed Graph (DAG) is a directed graph, where the edges are multi-relational with time stamp associated with each edge known as an event, and attributes associated with the nodes for that  ... 
arXiv:2003.03919v1 fatcat:ma3sqnpysbcqxa3xyslbj5xhly

Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding [article]

Jingya Zhou, Ling Liu, Wenqi Wei, Jianxi Fan
2021 arXiv   pre-print
With this unifying reference framework, we highlight the representative methods, models, and techniques used at different stages of the node embedding model learning process.  ...  Network representation learning (NRL) advances the conventional graph mining of social networks, knowledge graphs, and complex biomedical and physics information networks.  ...  multi-relation graphs with billions of nodes and trillions of edges.  ... 
arXiv:2110.07582v1 fatcat:gbjn3evwwzf4xkeobrsfo6hope

Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks [article]

Mario Lino, Chris Cantwell, Anil A. Bharath, Stathi Fotiadis
2021 arXiv   pre-print
Using graph representations, MultiScaleGNN can impose periodic boundary conditions as an inductive bias on the edges in the graphs, and achieve independence to the nodes' positions.  ...  Here we introduce MultiScaleGNN, a novel multi-scale graph neural network model for learning to infer unsteady continuum mechanics.  ...  Each edge k ∈ E l−1,l connects node s k ∈ V l−1 to its parent node r k ∈ V l , with edge attributes assigned as the relative position between child and parent nodes.  ... 
arXiv:2106.04900v1 fatcat:ojocrnre7favpalpd5quhoj7eu

REMuS-GNN: A Rotation-Equivariant Model for Simulating Continuum Dynamics [article]

Mario Lino, Stati Fotiadis, Anil A. Bharath, Chris Cantwell
2022 arXiv   pre-print
On the other hand, surrogate deep learning models, while accelerating simulations, often exhibit poor accuracy and ability to generalise.  ...  REMuS-GNN is designed to predict an output vector field from an input vector field on a physical domain discretised into an unstructured set of nodes.  ...  Before being fed to the network, all the edge attributes e ij and angle attributes a ij are encoded through independent multi-layer perceptrons (MLPs).  ... 
arXiv:2205.07852v1 fatcat:mixilvfay5dehgvaselcsrvvca

A Survey on Embedding Dynamic Graphs [article]

Claudio D. T. Barros, Matheus R. F. Mendonça, Alex B. Vieira, Artur Ziviani
2021 arXiv   pre-print
Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization.  ...  Afterward, we describe existing techniques and propose a taxonomy for dynamic graph embedding techniques based on algorithmic approaches, from matrix and tensor factorization to deep learning, random walks  ...  Moreover, this paper is dedicated to the memory of our dear co-worker Artur Ziviani, who passed away while this paper was being peer-reviewed. Artur was a brilliant researcher and dedicated advisor.  ... 
arXiv:2101.01229v2 fatcat:lqjkkksn45g7beizhcstakf6ry

A Systematic Survey on Deep Generative Models for Graph Generation [article]

Xiaojie Guo, Liang Zhao
2020 arXiv   pre-print
This article provides an extensive overview of the literature in the field of deep generative models for the graph generation.  ...  Firstly, the formal definition of deep generative models for the graph generation as well as preliminary knowledge is provided.  ...  Node-edge Co-transformation. The problem of node-edge co-transformation (NECT) is generating the node and edge attributes of the target graph conditioning on those of the input graph.  ... 
arXiv:2007.06686v2 fatcat:xox7apwdvbfhlgnsgrr3w3rv5m

Reward Prediction Error as an Exploration Objective in Deep RL

Riley Simmons-Edler, Ben Eisner, Daniel Yang, Anthony Bisulco, Eric Mitchell, Sebastian Seung, Daniel Lee
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We then propose a deep reinforcement learning method, QXplore, which exploits the temporal difference error of a Q-function to solve hard exploration tasks in high-dimensional MDPs.  ...  However, while state-novelty exploration methods are suitable for tasks where novel observations correlate well with improved reward, they may not explore more efficiently than epsilon-greedy approaches  ...  A Dynamic Attributed Graph (DAG) is a directed graph, where the edges are multi-relational with time stamp associated with each edge known as an event, and attributes associated with the nodes for that  ... 
doi:10.24963/ijcai.2020/386 dblp:conf/ijcai/GargSJR20 fatcat:skxk2hcxpbewxfewulsbqkm37a

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources [article]

Xiao Wang and Deyu Bo and Chuan Shi and Shaohua Fan and Yanfang Ye and Philip S. Yu
2020 arXiv   pre-print
space while preserving the heterogeneous structures and semantics for downstream tasks (e.g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent  ...  We first introduce the basic concepts of HG and discuss the unique challenges brought by the heterogeneity for HG embedding in comparison with homogeneous graph representation learning; and then we systemically  ...  IntentGC translates the original HG as a multi-relation graph of users and items and develops a multi-relation graph convolution method to learn node embeddings.  ... 
arXiv:2011.14867v1 fatcat:phfoxj7qsrfshfednomeok7pau

Pseudo2GO: A Graph-Based Deep Learning Method for Pseudogene Function Prediction by Borrowing Information From Coding Genes

Kunjie Fan, Yan Zhang
2020 Frontiers in Genetics  
Multiple features are incorporated into the model as the node attributes to enable the graph an attributed graph, including expression profiles, interactions with microRNAs, protein-protein interactions  ...  Graph convolutional networks are used to propagate node attributes across the graph to make classifications on pseudogenes.  ...  We also compare it with two machine learning models that are not based on graph information: support vector machine (SVM) and deep neural network (DNN), which use the same node attributes used in our method  ... 
doi:10.3389/fgene.2020.00807 pmid:33014009 pmcid:PMC7461887 fatcat:lqic3ihqg5eghdoct3wjezg6ze

Knowledge Graph Completion: A Review

Zhe Chen, Yuehan Wang, Bin Zhao, Jing Cheng, Xin Zhao, Zongtao Duan
2020 IEEE Access  
The latter further includes translation model based, semantic matching model based, representation learning based and other neural network model based methods.  ...  Knowledge graph completion (KGC) is a hot topic in knowledge graph construction and related applications, which aims to complete the structure of knowledge graph by predicting the missing entities or relationships  ...  SACN includes a weighted graph convolution network as a coder, aggregating relationship types of knowledge graph node structure, node attributes and edges, with learnable weights which adapts to information  ... 
doi:10.1109/access.2020.3030076 fatcat:jbimdngcmrbx3jhihsgrp62cxq

Graph Neural Networks in IoT: A Survey [article]

Guimin Dong, Mingyue Tang, Zhiyuan Wang, Jiechao Gao, Sikun Guo, Lihua Cai, Robert Gutierrez, Bradford Campbell, Laura E. Barnes, Mehdi Boukhechba
2022 arXiv   pre-print
Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data.  ...  With the recent development of sensor and communication technologies, IoT devices including smart wearables, cameras, smartwatches, and autonomous vehicles can accurately measure and perceive their surrounding  ...  Therefore, 𝐴 𝑖 𝑗 = 𝐴 𝑗𝑖 holds for every node in the graph and its adjacency matrix 𝐴 is symmetric. • Weighted/Unweighted Graphs: weighted graphs refer to graphs with attributed edges, which determine  ... 
arXiv:2203.15935v2 fatcat:jkqg5ukg5fezbewu5mr5hqsp4e

The Genome Conformation As an Integrator of Multi-Omic Data: The Example of Damage Spreading in Cancer

Fabio Tordini, Marco Aldinucci, Luciano Milanesi, Pietro Liò, Ivan Merelli
2016 Frontiers in Genetics  
Publicly available multi-omic databases, in particular if associated with medical annotations, are rich resources with the potential to lead a rapid transition from high-throughput molecular biology experiments  ...  Using this representation, we can describe how driver and passenger mutations accumulate during the development of diseases providing, for example, a tool able to characterize the evolution of cancer.  ...  FT and IM implemented the multi-layer model. MA, LM, and PL supported and supervised the work. IM and FT wrote the paper.  ... 
doi:10.3389/fgene.2016.00194 pmid:27895661 pmcid:PMC5108817 fatcat:5jjm7ann5fcyjptzuv3rpo5f4i

Graph embedding techniques, applications, and performance: A survey

Palash Goyal, Emilio Ferrara
2018 Knowledge-Based Systems  
Recently, methods which use the representation of graph nodes in vector space have gained traction from the research community.  ...  Graphs, such as social networks, word co-occurrence networks, and communication networks, occur naturally in various real-world applications.  ...  Similar to augmenting graph structure with node attributes for factorization based methods, GenVector [53] , Discriminative Deep Random Walk (DDRW) [54] , Tri-party Deep Network Representation (TriDNR  ... 
doi:10.1016/j.knosys.2018.03.022 fatcat:wpud5byxxndllmhqdnhkljvcga
« Previous Showing results 1 — 15 out of 6,261 results