Temporal Network Representation Learning via Historical Neighborhoods Aggregation

  title={Temporal Network Representation Learning via Historical Neighborhoods Aggregation},
  author={Shixun Huang and Zhifeng Bao and Guoliang Li and Yanghao Zhou and J. Shane Culpepper},
  journal={2020 IEEE 36th International Conference on Data Engineering (ICDE)},
  • Shixun Huang, Z. Bao, J. Culpepper
  • Published 30 March 2020
  • Computer Science
  • 2020 IEEE 36th International Conference on Data Engineering (ICDE)
Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes… 

Temporal network embedding framework with causal anonymous walks representations

This work provides the first comprehensive comparison framework for temporal network representation learning for graph machine learning problems involving node classification and link prediction in every available setting and outperforms state-of-the-art baseline models.

Temporal Graph Network Embedding with Causal Anonymous Walks Representations

This work provides the first comprehensive comparison framework for temporal network representation learning in every available setting for graph machine learning problems involving node classification and link prediction and justifies the difference between them based on evaluation in various transductive/inductive edge/node classification tasks.

TI-GCN: A Dynamic Network Embedding Method with Time Interval Information

This paper proposes a model to learn dynamic network embedding named TI-GCN (Time Interval Graph Convolutional Networks), and comes up with a heuristic framework to update network embeddings with theembeddings inherited from the previous snapshot, so that the network embeds are more traceable, which complements mining the evolving patterns.

A Survey on Graph Representation Learning Methods

An overview of non-GNN graph embedding methods, which are based on techniques such as random walks, temporal point processes and neural network learning methods, and GNN-based methods which are the application of deep learning on graph data are provided.

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.



Embedding Temporal Network via Neighborhood Formation

Experiments on three large-scale real-life networks demonstrate that the embeddings learned from the proposed HTNE model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction, and embedding visualization.

node2vec: Scalable Feature Learning for Networks

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.

Dynamic Network Embedding by Modeling Triadic Closure Process

This paper presents a novel representation learning approach, DynamicTriad, to preserve both structural information and evolution patterns of a given network, and demonstrates that, compared with several state-of-the-art techniques, this approach achieves substantial gains in several application scenarios.

LINE: Large-scale Information Network Embedding

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.

Continuous-Time Dynamic Network Embeddings

The proposed framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks and indicates that modeling temporal dependencies in graphs is important for learning appropriate and meaningful network representations.

PME: Projected Metric Embedding on Heterogeneous Networks for Link Prediction

A novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way is proposed and the experimental results show superiority of the proposed PME model in terms of prediction accuracy and scalability.

Representation Learning on Graphs: Methods and Applications

A conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks are provided.

Inductive Representation Learning on Large Graphs

GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.

Exploiting Centrality Information with Graph Convolutions for Network Representation Learning

A generalizable model, namely GraphCSC, is proposed that utilizes both linkage information and centrality information to learn low-dimensional vector representations for network vertices and achieves better performance on several benchmark tasks compared with recent state-of-the-art network embedding methods.

A Survey on Network Embedding

This survey focuses on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions, covering the structure- and property-preserving network embeding methods, the network embedded methods with side information, and the advanced information preserving network embedting methods.