K-Core based Temporal Graph Convolutional Network for Dynamic Graphs

  title={K-Core based Temporal Graph Convolutional Network for Dynamic Graphs},
  author={Jingxin Liu and Chang Xu and Chang Yin and Weiqiang Wu and You Song},
  journal={IEEE Trans. Knowl. Data Eng.},
  • Jingxin Liu, Chang Xu, You Song
  • Published 22 March 2020
  • Computer Science
  • IEEE Trans. Knowl. Data Eng.
Graph representation learning is a fundamental task in various applications that strives to learn low-dimensional embeddings for nodes that can preserve graph topology information. However, many existing methods focus on static graphs while ignoring evolving graph patterns. Inspired by the success of graph convolutional networks(GCNs) in static graph embedding, we propose a novel k-core based temporal graph convolutional network, the CTGCN, to learn node representations for dynamic graphs. In… 
CGC: Contrastive Graph Clustering forCommunity Detection and Tracking
This work develops CGC, a novel end-to-end framework for graph clustering, which fundamentally differs from existing methods, and extends CGC for time-evolving data, where temporalgraph clustering is performed in an incremental learning fashion, with the ability to detect change points.
DRAGON: Dynamic Recurrent Accelerator for Graph Online Convolution
This work proposes and implements a novel efficient architecture, capable of producing similar speed-up and performance than baseline but at a fraction of its hardware requirements and power consumption, and demonstrates the unique functional qualities of the approach as a flexible and fault-tolerant solution that makes it an interesting alternative for an anthology of applicative scenarios.
Learning User Interface Semantics from Heterogeneous Networks with Multimodal and Positional Attributes
The novel Heterogeneous Attention-based Multimodal Positional Positional (HAMP) graph neural network model, which combines graph neural networks with the scaled dot-product attention used in transformers to learn the embeddings of heterogeneous nodes and associated multimodal and positional attributes in a unified manner is proposed.
A Topological Centrality Measure for Directed Networks
A new metric for computing centrality in directed weighted networks, namely the quasi-centrality measure is introduced and a method that gives a hierarchical representation of the topological influences of nodes in a directed network is introduced.
TEGDetector: A Phishing Detector that Knows Evolving Transaction Behaviors
TEGDetector is proposed, a dynamic graph classifier that learns the evolving behavior features from transaction evolution graphs(TEGs) and achieves state-of-the-art detection performance on the large-scale Ethereum transaction dataset.
ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
A two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories and introduces a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information.
Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction
A novel backdoor attack framework on DLP is proposed, denoted as Dyn-Backdoor, which generates diverse initial-triggers by a generative adversarial network (GAN) so as to reduce the size of triggers and improve the concealment of the attack.
Survey on graph embeddings and their applications to machine learning problems on graphs
This survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description, and presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.
Hierarchical Graph Convolutional Network for Data Evaluation of Dynamic Graphs
This work proposes a novel hierarchical graph convolutional network for the data evaluation of dynamic graphs, following the anomaly detection paradigm, and provides a more powerful tool for processing dynamic graphs.
Survey on graph embeddings and their applications to machine learning problems on graphs
This survey covers a new rapidly growing family of automated graph feature engineering techniques, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.


Antibodies to the conserved cytoplasmic domain of the integrin beta 1 subunit react with proteins in vertebrates, invertebrates, and fungi
An antibody against a synthetic peptide corresponding to the COOH-terminal domain of the chicken integrin beta 1 subunit that reacts with beta subunits from a variety of vertebrates, invertebrates, and fungi is raised, demonstrating strong evolutionary conservation of sequences in this domain.
Fetal alcohol effects--incidence and understanding in the Cape.
  • C. Palmer
  • Medicine
    South African medical journal = Suid-Afrikaanse tydskrif vir geneeskunde
  • 1985
Distinct mechanisms of cell cycle arrest control the decision between differentiation and senescence in human neuroblastoma cells
It is proposed that rapid inhibition of cdks by RA in NB leads to early cell cycle arrest, prevents neuronal differentiation, and results in a senescence-like state.
A CAD-augmented Reality Integrated Environment for Assembly Sequence Check and Interactive Validation
The new combined software and hardware equipment may be considered a step ahead in the support of true concurrent engineering and remote collaboration, strongly improving this latter through a better heterogeneous task integration.
A Gestalt theoretic perspective on the user experience of location-based services
This paper argues that describing the user experience of location-based services through Gestalt theory's principles of proximity, closure, symmetry, continuity, and similarity can help explain how people make sense of small and fragmented pieces of information on mobile devices in context.
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
This work proposes EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings, and captures the dynamism of the graph sequence through using an RNN to evolve the GCN parameters.
DeepWalk: online learning of social representations
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
The proposed model combines convolutional neural networks on graphs to identify spatial structures and RNN to find dynamic patterns in data structured by an arbitrary graph.
Recurrent Event Network : Global Structure Inference Over Temporal Knowledge Graph
Recurrent Event Network is presented, a novel autoregressive architecture for modeling temporal sequences of multi-relational graphs (e.g., temporal knowledge graph), which can perform sequential, global structure inference over future time stamps to predict new events.
A continuously variable zoom for navigating large hierarchical networks
The continuous zoom is presented, a distorted view method for displaying hierarchically-organized, two-dimensional networks, suitable for large networks, such as those found in interfaces to complex supervisory control systems.