634
Views
74
Downloads
5
Crossref
N/A
WoS
1
Scopus
N/A
CSCD
Dynamic heterogeneous graphs comprise different types of events with temporal labels. In many real-world scenarios, the temporal order of different types of events possibly implies causal relationships between these event types. However, existing methods designed to model dynamic heterogeneous graphs neglect the underlying causal relationships between event types. For instance, the determination of the occurrence of a new event is misled by irrelevant historical events considering the type and could lead to performance degradation. First, this paper explicitly defines the causality of event types by the heterogeneous causality graph to utilize such causality from the perspective of the graph structure to tackle the aforementioned issue. Second, this paper proposes the event type causality based continuous-time heterogeneous attention network (ECHN) to model dynamic heterogeneous graphs. ECHN aggregates features based on the strength of different causal relationships between event types in the prediction process to utilize the causality of event types from the perspective of the modeling algorithm. The utilities of event type causality weaken the negative effect of irrelevant events. Experimental results demonstrate that ECHN outperforms state-of-the-arts in the link prediction task. The authors believe that this paper is the first study to model the causality of event types in dynamic heterogeneous graphs explicitly.
Dynamic heterogeneous graphs comprise different types of events with temporal labels. In many real-world scenarios, the temporal order of different types of events possibly implies causal relationships between these event types. However, existing methods designed to model dynamic heterogeneous graphs neglect the underlying causal relationships between event types. For instance, the determination of the occurrence of a new event is misled by irrelevant historical events considering the type and could lead to performance degradation. First, this paper explicitly defines the causality of event types by the heterogeneous causality graph to utilize such causality from the perspective of the graph structure to tackle the aforementioned issue. Second, this paper proposes the event type causality based continuous-time heterogeneous attention network (ECHN) to model dynamic heterogeneous graphs. ECHN aggregates features based on the strength of different causal relationships between event types in the prediction process to utilize the causality of event types from the perspective of the modeling algorithm. The utilities of event type causality weaken the negative effect of irrelevant events. Experimental results demonstrate that ECHN outperforms state-of-the-arts in the link prediction task. The authors believe that this paper is the first study to model the causality of event types in dynamic heterogeneous graphs explicitly.
X. Wang, L. Chen, T. Ban, M. Usman, Y. Guan, S. Liu, T. Wu, and H. Chen, Knowledge graph quality control: A survey, Fundamental Research, vol. 1, no. 5, pp. 607–626, 2021.
B. Jiang, H. Chen, B. Yuan, and X. Yao, Scalable graph-based semi-supervised learning through sparse bayesian model, IEEE Transactions on Knowledge and Data Engineering, vol. 29, no. 12, pp. 2758–2771, 2017.
L. Chen, J. Cao, H. Chen, W. Liang, H. Tao, and G. Zhu, Attentive multi-task learning for group itinerary recommendation, Knowledge and Information Systems, vol. 63, pp. 1687–1716, 2021.
L. Ding, B. Han, S. Wang, X. Li, and B. Song, User-centered recommendation using US-ELM based on dynamic graph model in E-commerce, International Journal of Machine Learning and Cybernetics, vol. 10, pp. 693–703, 2019.
Y. Wang, J. Cao, Z. Bu, J. Jiang, and H. Chen, Proximity-based group formation game model for community detection in social network, Knowledge-Based Systems, vol. 214, p. 106670, 2021.
X. Wu, B. Jiang, K. Yu, and H. Chen, Separation and recovery markov boundary discovery and its application in EEG-based emotion recognition, Information Sciences, vol. 571, pp. 262–278, 2021.
W. Shu, Y. Yao, S. Lyu, J. Li, and H. Chen, Short isometric shapelet transform for binary time series classification, Knowledge and Information Systems, vol. 63, pp. 2023–2051, 2021.
Z. Gong, H. Chen, B. Yuan, and X. Yao, Multiobjective learning in the model space for time series classification, IEEE Transactions on Cybernetics, vol. 49, no. 3, pp. 918–932, 2018.
X. Wu, B. Jiang, K. Yu, and H. Chen, Accurate markov boundary discovery for causal feature selection, IEEE Transactions on Cybernetics, vol. 50, no. 12, pp. 4983–4996, 2019.
X. Wu, B. Jiang, K. Yu, H. Chen, and C. Miao, Multi-label causal feature selection, Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 4, pp. 6430–6437, 2020.
S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
S. Sajadmanesh, S. Bazargani, J. Zhang, and H. R. Rabiee, Continuous-time relationship prediction in dynamic heterogeneous information networks, ACM Transactions on Knowledge Discovery from Data(TKDD), vol. 13, no. 4, pp. 1–31, 2019.
H. Chen, P. Tiňo, and X. Yao, Probabilistic classification vector machines, IEEE Transactions on Neural Networks, vol. 20, no. 6, pp. 901–914, 2009.
H. Chen, P. Tiňo, and X. Yao, Efficient probabilistic classification vector machine with incremental basis function selection, IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 2, pp. 356–369, 2014.
This work was supported by National Natural Science Foundation of China (Nos. 62176245 and 62137002), Anhui Province (Nos. 202104a05020011 and 202103a07020002), and the Fundamental Research Funds for the Central Universities.
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).