Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling

• URL: http://arxiv.org/abs/2211.06590v1
• Date: Sat, 12 Nov 2022 06:56:36 GMT
• Title: Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling
• Authors: Jiayun Wu, Tao Jia, Yansong Wang, Li Tao
• Abstract summary: Temporal networks are suitable for modeling complex evolving systems. This paper proposes Significant Ties Graph Neural Networks (STGNN), a novel framework that captures and describes significant ties.
• Score: 8.870188183999852
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal networks are suitable for modeling complex evolving systems. It has a wide range of applications, such as social network analysis, recommender systems, and epidemiology. Recently, modeling such dynamic systems has drawn great attention in many domains. However, most existing approaches resort to taking discrete snapshots of the temporal networks and modeling all events with equal importance. This paper proposes Significant Ties Graph Neural Networks (STGNN), a novel framework that captures and describes significant ties. To better model the diversity of interactions, STGNN introduces a novel aggregation mechanism to organize the most significant historical neighbors' information and adaptively obtain the significance of node pairs. Experimental results on four real networks demonstrate the effectiveness of the proposed framework.

Related papers

• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [67.25782152459851]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks [1.213512753726579]
  It is difficult to identify critical nodes because the network structure changes over time in temporal networks. This paper proposes a novel and effective learning framework based on the combination of special GCNs and RNNs. Experimental results on four real-world temporal networks demonstrate that the proposed method outperforms both traditional and deep learning benchmark methods.
  arXiv  Detail & Related papers  (2021-06-19T04:16:18Z)
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series [77.47313102926017]
  Radflow is a novel model for networks of time series that influence each other. It embodies three key ideas: a recurrent neural network to obtain node embeddings that depend on time, the aggregation of the flow of influence from neighboring nodes with multi-head attention, and the multi-layer decomposition of time series. We show that Radflow can learn different trends and seasonal patterns, that it is robust to missing nodes and edges, and that correlated temporal patterns among network neighbors reflect influence strength.
  arXiv  Detail & Related papers  (2021-02-15T00:57:28Z)
• Mutually exciting point process graphs for modelling dynamic networks [0.0]
  A new class of models for dynamic networks is proposed, called mutually exciting point process graphs (MEG) MEG is a scalable network-wide statistical model for point processes with dyadic marks, which can be used for anomaly detection. The model is tested on simulated graphs and real world computer network datasets, demonstrating excellent performance.
  arXiv  Detail & Related papers  (2021-02-11T10:14:55Z)
• Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [79.28094304325116]
  Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points. We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
  arXiv  Detail & Related papers  (2020-11-14T11:09:51Z)
• Continuous-in-Depth Neural Networks [107.47887213490134]
  We first show that ResNets fail to be meaningful dynamical in this richer sense. We then demonstrate that neural network models can learn to represent continuous dynamical systems. We introduce ContinuousNet as a continuous-in-depth generalization of ResNet architectures.
  arXiv  Detail & Related papers  (2020-08-05T22:54:09Z)
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey [11.18312489268624]
  We establish a foundation of dynamic networks with consistent, detailed terminology and notation. We present a comprehensive survey of dynamic graph neural network models using the proposed terminology.
  arXiv  Detail & Related papers  (2020-05-13T23:56:38Z)
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN [16.362525151483084]
  We propose a novel dynamic heterogeneous network embedding method, termed as DyHATR. It uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction.
  arXiv  Detail & Related papers  (2020-04-01T17:16:47Z)
• NEW: A Generic Learning Model for Tie Strength Prediction in Networks [5.834475036139535]
  Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks. We propose a new computational framework called Neighborhood Estimating Weight (NEW) NEW is purely driven by the basic structure information of the network and has the flexibility for adapting to diverse types of networks.
  arXiv  Detail & Related papers  (2020-01-15T13:02:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.