Abstract
Event prediction is a vital and challenging task in temporal knowledge graphs (TKGs), which have played crucial roles in various applications. Recently, many graph neural networks based approaches are proposed to model the graph structure information in TKGs. However, these approaches only construct graphs based on quadruplets and model the pairwise correlation between entities, which fail to capture the high-order correlations among entities. To this end, we propose DHyper, a recurrent Dual Hypergraph neural network for event prediction in TKGs, which simultaneously models the influences of the high-order correlations among both entities and relations. Specifically, a dual hypergraph learning module is proposed to discover the high-order correlations among entities and among relations in a parameterized way. A dual hypergraph message passing network is introduced to perform the information aggregation and representation fusion on the entity hypergraph and the relation hypergraph. Extensive experiments on six real-world datasets demonstrate that DHyper achieves the state-of-the-art performances, outperforming the best baseline by an average of 13.09%, 4.26%, 17.60%, and 18.03% in MRR, Hits@1, Hits@3, and Hits@10, respectively.
- [1] . 2022. Time-aware path reasoning on knowledge graph for recommendation. ACM Transactions on Information Systems 41, 2 (2022), 1–26.Google ScholarDigital Library
- [2] . 2023. Preference-aware graph attention networks for cross-domain recommendations with collaborative knowledge graph. ACM Transactions on Information Systems 41, 3 (2023), 1–26.Google ScholarDigital Library
- [3] . 2022. DACHA: A dual graph convolution based temporal knowledge graph representation learning method using historical relation. ACM Transactions on Knowledge Discovery from Data 16, 3 (2022), 1–18.Google ScholarDigital Library
- [4] . 2018. HyTE: Hyperplane-based temporally aware knowledge graph embedding. In EMNLP 2001–2011.Google ScholarCross Ref
- [5] . 2020. Recommender systems leveraging multimedia content. ACM Computing Surveys 53, 5 (2020), 1–38.Google ScholarDigital Library
- [6] . 2020. Dynamic knowledge graph based multi-event forecasting. In KDD. 1585–1595.Google ScholarDigital Library
- [7] , . 2020. Optimizing DNN computation graph using graph substitutions. In VLDB, 13, 12 (2020), 2734–2746.Google ScholarDigital Library
- [8] . 2019. Hypergraph neural networks. In AAAI, 3558–3565.Google ScholarDigital Library
- [9] . 2022. HGNN+: General hypergraph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3181–3199.Google Scholar
- [10] . 2020. Recurrent event network: Autoregressive structure inference over temporal knowledge graphs. In EMNLP. 6669–6683.Google ScholarCross Ref
- [11] . 2015. Adam: A method for stochastic optimization. In ICLR. 1–15.Google Scholar
- [12] . 2018. Deriving validity time in knowledge graph. In WWW. 1771–1776.Google Scholar
- [13] . 2013. GDELT: Global data on events, location, and tone, 1979–2012. ISA Annual Convention 2, 4 (2013), 1–49.Google Scholar
- [14] . 2021. Temporal knowledge graph reasoning based on evolutional representation learning. In SIGIR. 408–417.Google ScholarDigital Library
- [15] . 2022. TiRGN: Time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning. In IJCAI. 2152–2158.Google ScholarCross Ref
- [16] . 2022. DA-Net: Distributed attention network for temporal knowledge graph reasoning. In CIKM. 1289–1298.Google ScholarDigital Library
- [17] . 2022. Social multi-role discovering with hypergraph embedding for location-based social networks. In ACIIDS. 675–687.Google ScholarDigital Library
- [18] . 2018. Modeling relational data with graph convolutional networks. In ESWC. 593–607.Google ScholarDigital Library
- [19] . 2021. TimeTraveler: Reinforcement learning for temporal knowledge graph forecasting. In EMNLP. 8306–8319.Google ScholarCross Ref
- [20] . 2019. Knowledge representation learning with entity descriptions, hierarchical types, and textual relations. Information Processing and Management 56, 3 (2019), 809–822.Google ScholarDigital Library
- [21] Xing Tang and Ling Chen. 2023. GTRL: An entity group-aware temporal knowledge graph representation learning method. IEEE Transactions on Knowledge and Data Engineering 99 (2023), 1--16.
DOI: Google ScholarCross Ref - [22] . 2017. Know-Evolve: Deep temporal reasoning for dynamic knowledge graphs. In ICML. 3462–3471.Google Scholar
- [23] . 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579–2605.Google Scholar
- [24] . 2020. Composition-based multi-relational graph convolutional networks. In ICLR, 1–16.Google Scholar
- [25] . 2020. Next-item recommendation with sequential hypergraphs. In SIGIR. 1101–1110.Google ScholarDigital Library
- [26] . 2020. TeMP: Temporal message passing for temporal knowledge graph completion. In EMNLP. 5730–5746.Google ScholarCross Ref
- [27] . 2022. Hypergraph contrastive collaborative filtering. In SIGIR. 70–79.Google ScholarDigital Library
- [28] . 2020. LBSN2Vec++: Heterogeneous hypergraph embedding for location-based social networks. IEEE Transactions on Knowledge and Data Engineering 34, 4 (2020), 1843–1855.Google Scholar
- [29] . 2022. Multi-behavior hypergraph-enhanced transformer for sequential recommendation. In KDD. 2263–2274.Google ScholarDigital Library
- [30] . 2020. Hypergraph convolutional recurrent neural network. In KDD. 3366–-3376.Google ScholarDigital Library
- [31] . 2022. Dynamic hypergraph convolutional network. In ICDE. 1621–1634.Google ScholarCross Ref
- [32] . 2018. Hierarchical graph representation learning with differentiable pooling. In NIPS. 4801–4811.Google Scholar
- [33] . 2017. Interconnections among the United States, Russia and China: Does Kissinger's American leadership formula apply? International Organizations Research Journal 12, 1 (2017), 81–109.Google ScholarCross Ref
- [34] . 2022. Temporal knowledge graph representation learning with local and global evolutions. Knowledge-Based Systems 251, 9 (2022), 1–13.Google Scholar
- [35] . 2022. Learnable hypergraph Laplacian for hypergraph learning. In ICASSP. 4503–4507.Google ScholarCross Ref
- [36] . 2021. Hierarchical multi-view graph pooling with structure learning. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2021), 545–559.Google Scholar
- [37] . 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification. In ICML. 1614–1623.Google Scholar
- [38] . 2015. Hyperopt: A python library for model selection and hyperparameter optimization. Computational Science and Discovery 8, 1 (2015), 1–25.Google ScholarCross Ref
- [39] . 2022. RLPath: A knowledge graph link prediction method using reinforcement learning based attentive relation path searching and representation learning. Applied Intelligence 52, 4 (2022), 4715–4726.Google ScholarDigital Library
- [40] . 2022. Adversarial auto-encoder domain adaptation for cold-start recommendation with positive and negative hypergraphs. ACM Transactions on Information Systems 41, 2 (2022), 1–25.Google ScholarDigital Library
- [41] . 2019. End-to-end structure-aware convolutional networks for knowledge base completion. In AAAI. 3060–3067.Google ScholarDigital Library
- [42] . 2021. Hierarchical hyperedge embedding-based representation learning for group recommendation. ACM Transactions on Information Systems 40, 1 (2021), 1–27.Google ScholarDigital Library
- [43] . 2017. Attention is all you need. In NIPS. 5998–6008.Google ScholarDigital Library
- [44] . 2019. Attention models in graphs: A survey. ACM Transactions on Knowledge Discovery from Data 13, 6 (2019), 1–25.Google ScholarDigital Library
- [45] . 2022. QueryFormer: A tree transformer model for query plan representation. In VLDB 15, 8 (2022), 1658–1670.Google ScholarDigital Library
- [46] . 2013. Translating embeddings for modeling multi-relational data. In NIPS. 2787–2795.Google ScholarDigital Library
- [47] Elizabeth Boschee, Jennifer Lautenschlager, Sean O'Brien, Steve Shellman, James Starz, and Michael Ward. 2015. ICEWS Coded Event Data. Harvard Dataverse.
DOI: Google ScholarCross Ref - [48] . 2019. Onto model-based anomalous link pattern mining on feature-rich social interaction networks. In Companion Proceedings of the 27th World Wide Web Conference. 1047–1050.Google ScholarDigital Library
- [49] . 2011. Temporal link prediction using matrix and tensor factorizations. ACM Transactions on Knowledge Discovery from Data 5, 2 (2011), 1–27.Google ScholarDigital Library
Index Terms
- DHyper: A Recurrent Dual Hypergraph Neural Network for Event Prediction in Temporal Knowledge Graphs
Recommendations
Hypergraph Convolutional Recurrent Neural Network
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIn this study, we present a hypergraph convolutional recurrent neural network (HGC-RNN), which is a prediction model for structured time-series sensor network data. Representing sensor networks in a graph structure is useful for expressing structural ...
Dominating sequences in graphs
A sequence of vertices in a graph G is called a legal dominating sequence if every vertex in the sequence dominates at least one vertex not dominated by those vertices that precede it, and at the end all vertices of G are dominated. While the length of ...
The Ramsey number for hypergraph cycles I
Let Cn denote the 3-uniform hypergraph loose cycle, that is the hypergraph with vertices v1.....,vn and edges v1v2v3, v3v4v5, v5v6v7,.....,vn-1vnv1. We prove that every red-blue colouring of the edges of the complete 3-uniform hypergraph with N vertices ...
Comments