Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction

Luo, Wenjuan; Zhang, Han; Yang, Xiaodi; Lin, Bo; Yang, Xiaoqing; Zang, Li; Qie, Xiaohu; Ye, Jieping

doi:10.1145/3394486.3403373

Cited by 49 publications

(20 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, DynamicGCN [2] was proposed to encode temporal text features into graphs for forecasting societal events and identifying their context graphs. Besides, REGNN [8] was proposed to learn the impact of historical actions and the surrounding environment on the current events for real-time event prediction.…”

Section: A Spatio-temporal Event Predictionmentioning

confidence: 99%

KatGCN: Knowledge-Aware Attention based Temporal Graph Convolutional Network for Multi-Event Prediction

Song¹

2021

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Social events are due to gradually changing relations between entities including citizens, organizations, and national governments. Predicting multiple co-occurring events of different types in the future can help analysts understand social dynamics better and make quick and accurate decisions in advance. However, due to the overlook of the knowledge (e.g., event actors and different relations between them), existing methods are insufficient to model the structural and temporal dependence of events with different types simultaneously to better realize the prediction of future multiple co-occurring events. In the paper, we propose a novel Knowledge-aware attention based temporal Graph Convolutional Network (KatGCN) for predicting multiple co-occurring events of different types. We model social events as temporal event graph and extract static features (e.g., event background, topic keywords) from event content to enhance semantic of event graph. We design knowledge-aware attention based graph aggregation method to capture the structure dependence of co-occurring events with different types. We apply temporal encoding to capture the temporal dependence between temporally adjacent events. Empirical results on five-country datasets show that KatGCN outperforms state-of-the-art methods. Further studies verify the effectiveness and interpretability of our model.

show abstract

Section: A Spatio-temporal Event Predictionmentioning

confidence: 99%

KatGCN: Knowledge-Aware Attention based Temporal Graph Convolutional Network for Multi-Event Prediction

Song¹

2021

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…In this paper, we discussed weighted graph, relational graph, and bipartite graphs; however, heterogeneous graphs are ubiquitous and have unique essential challenges for modeling and learning [22,24,[35][36][37]. We have been seeing heterogeneous GNNs [5,9,23,47] and heterogeneous attention networks for graphs [13,14,38,43,44].…”

Section: Related Work 61 Graph Neural Networkmentioning

confidence: 99%

Cross-Network Learning with Partially Aligned Graph Convolutional Networks

Jiang

2021

Preprint

View full text Add to dashboard Cite

Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data. Existing models were designed for the nodes on a single graph, which would not be able to utilize information across multiple graphs. The real world does have multiple graphs where the nodes are often partially aligned. For examples, knowledge graphs share a number of named entities though they may have different relation schema; collaboration networks on publications and awarded projects share some researcher nodes who are authors and investigators, respectively; people use multiple web services, shopping, tweeting, rating movies, and some may register the same email account across the platforms. In this paper, I propose partially aligned graph convolutional networks to learn node representations across the models. I investigate multiple methods (including model sharing, regularization, and alignment reconstruction) as well as theoretical analysis to positively transfer knowledge across the (small) set of partially aligned nodes. Extensive experiments on real-world knowledge graphs and collaboration networks show the superior performance of our proposed methods on relation classification and link prediction.

show abstract

“…In contrast, the graph structures remains unchanged for epidemiological networks, but the node features inevitably change with increased/decreased patient numbers. It is worth noting that dynamic heterogeneous graphs [14,15,16,17] can be treated as an instance of HTGs, where the dynamic nature comes from the evolving graph structures.…”

Section: Introductionmentioning

confidence: 99%

“…There exist some preliminary works. They could be roughly summarized into two categories: one first explores neural sequence models to process time-series features attached on each node, and then performs graph representation learning with the processed node features on the spatial domain [18,5,6,19]; the other first applies GNNs on each graph slice of a HTG, and then employs sequence models on the outputs of each slice to obtain the final representations [20,16,15]. Although these works could achieve satisfactory results, they are still faced with the following limitations: (1) The existing models are graph-dependent.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous Temporal Graph Neural Network

Yu¹,

Ju²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) have been broadly studied on dynamic graphs for their representation learning, majority of which focus on graphs with homogeneous structures in the spatial domain. However, many real-world graphs -i.e., heterogeneous temporal graphs (HTGs) -evolve dynamically in the context of heterogeneous graph structures. The dynamics associated with heterogeneity have posed new challenges for HTG representation learning. To solve this problem, in this paper, we propose heterogeneous temporal graph neural network (HTGNN) to integrate both spatial and temporal dependencies while preserving the heterogeneity to learn node representations over HTGs. Specifically, in each layer of HTGNN, we propose a hierarchical aggregation mechanism, including intra-relation, inter-relation, and across-time aggregations, to jointly model heterogeneous spatial dependencies and temporal dimensions. To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intrarelation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG. The proposed HTGNN is a holistic framework tailored heterogeneity with evolution in time and space for HTG representation learning. Extensive experiments are conducted on the HTGs built from different real-world datasets and promising results demonstrate the outstanding performance of HT-GNN by comparison with state-of-the-art baselines. Our built HTGs and code have been made publicly accessible at: https://github.com/YesLab-Code/HTGNN.

show abstract

Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction

Cited by 49 publications

References 14 publications

KatGCN: Knowledge-Aware Attention based Temporal Graph Convolutional Network for Multi-Event Prediction

KatGCN: Knowledge-Aware Attention based Temporal Graph Convolutional Network for Multi-Event Prediction

Cross-Network Learning with Partially Aligned Graph Convolutional Networks

Heterogeneous Temporal Graph Neural Network

Contact Info

Product

Resources

About