Temporal Heterogeneous Information Network Embedding

Huang, Hong; Shi, Ruize; Zhou, Wei; Wang, Xiao; Jin, Hai; Fu, Xiaoming

doi:10.24963/ijcai.2021/203

Cited by 19 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other feasible and commonly used approach is to utilize knowledge graph embedding (KGE) techniques to train a low-dimensional vector for each entity and relation, while maintaining the inherent structure of the IKG. The resulting vectors obtained through KGE can then be utilized to enhance the representations of entities in the IKG [13][14][15][16][17]. However, it is noted that although KGE is specifically tailored for tasks related to knowledge graphs, it is not optimized for applications in industrial settings.…”

Section: Knowledge Graph Embeddingmentioning

confidence: 99%

Pretrained Language–Knowledge Graph Model Benefits Both Knowledge Graph Completion and Industrial Tasks: Taking the Blast Furnace Ironmaking Process as an Example

Huang,

Yang

2024

Electronics

View full text Add to dashboard Cite

Industrial knowledge graphs (IKGs) have received widespread attention from researchers in recent years; they are intuitive to humans and can be understood and processed by machines. However, how to update the entity triples in the graph based on the continuous production data to cover as much knowledge as possible, while applying a KG to meet the needs of different industrial tasks, are two difficulties. This paper proposes a two-stage model construction strategy to benefit both knowledge graph completion and industrial tasks. Firstly, this paper summarizes the specific forms of multi-source data in industry and provides processing methods for each type of data. The core is to vectorize the data and align it conceptually, thereby achieving the fusion modeling of multi-source data. Secondly, this paper defines two interrelated subtasks to construct a pretrained language–knowledge graph model based on multi-task learning. At the same time, considering the dynamic characteristics of the production process, a dynamic expert network structure is adopted for different tasks combined with the pretrained model. In the knowledge completion task, the proposed model achieved an accuracy of 91.25%, while in the self-healing control task of a blast furnace, the proposed model reduced the incorrect actions rate to 0 and completed self-healing control for low stockline fault in 278 min. The proposed framework has achieved satisfactory results in experiments, which verifies the effectiveness of introducing knowledge into industry.

show abstract

Section: Knowledge Graph Embeddingmentioning

confidence: 99%

Pretrained Language–Knowledge Graph Model Benefits Both Knowledge Graph Completion and Industrial Tasks: Taking the Blast Furnace Ironmaking Process as an Example

Huang,

Yang

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Although these methods can learn graph dynamics of the THG to some extent, the temporal information within the same snapshot is usually ignored, and the scale of snapshots needs to be predetermined in advance. Recently, researchers have proposed continuous-time dynamic graph (CTDG [14]) approaches [19][20][21][22][23][24] to capture dynamics via passing information between different interactions, or using continuoustime functions to generate temporal embedding. In regard to the new nodes, inductive graph representation learning methods [5,22,23,25] recognize structural features of node neighborhood by learning trainable aggregation functions, so that rapidly generate node embeddings in new subgraphs.…”

Section: Examplementioning

confidence: 99%

“…Recent studies [19][20][21][22][23]30] have shown the superior performance of continuous-time methods in dealing with temporal graphs. JODIE [21] uses RNNs to propagate information in interactions and update node representations smoothly at different timesteps.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Memory-Enhanced Transformer for Representation Learning on Temporal Heterogeneous Graphs

Duan

Wang

et al. 2023

Data Sci. Eng.

View full text Add to dashboard Cite

Temporal heterogeneous graphs can model lots of complex systems in the real world, such as social networks and e-commerce applications, which are naturally time-varying and heterogeneous. As most existing graph representation learning methods cannot efficiently handle both of these characteristics, we propose a Transformer-like representation learning model, named THAN, to learn low-dimensional node embeddings preserving the topological structure features, heterogeneous semantics, and dynamic patterns of temporal heterogeneous graphs, simultaneously. Specifically, THAN first samples heterogeneous neighbors with temporal constraints and projects node features into the same vector space, then encodes time information and aggregates the neighborhood influence in different weights via type-aware self-attention. To capture long-term dependencies and evolutionary patterns, we design an optional memory module for storing and evolving dynamic node representations. Experiments on three real-world datasets demonstrate that THAN outperforms the state-of-the-arts in terms of effectiveness with respect to the temporal link prediction task.

show abstract

“…TDGNN [30] introduces a temporal aggregator for GNNs to aggregate historical information of neighbor nodes and edges. Hawkes process [15,60] is also applied to simulate the evolution of graphs. Furthermore, DyRep [40] leverages recurrent neural networks to update node representations over time.…”

Section: Introductionmentioning

confidence: 99%

HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction

Bai

Nie

Zhang

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

Temporal link prediction, aiming to predict future edges between paired nodes in a dynamic graph, is of vital importance in diverse applications. However, existing methods are mainly built upon uniform Euclidean space, which has been found to be conflict with the power-law distributions of real-world graphs and unable to represent the hierarchical connections between nodes effectively. With respect to the special data characteristic, hyperbolic geometry offers an ideal alternative due to its exponential expansion property. In this paper, we propose HGWaveNet, a novel hyperbolic graph neural network that fully exploits the fitness between hyperbolic spaces and data distributions for temporal link prediction. Specifically, we design two key modules to learn the spatial topological structures and temporal evolutionary information separately. On the one hand, a hyperbolic diffusion graph convolution (HDGC) module effectively aggregates information from a wider range of neighbors. On the other hand, the internal order of causal correlation between historical states is captured by hyperbolic dilated causal convolution (HDCC) modules. The whole model is built upon the hyperbolic spaces to preserve the hierarchical structural information in the entire data flow. To prove the superiority of HG-WaveNet, extensive experiments are conducted on six real-world graph datasets and the results show a relative improvement by up to 6.67% on AUC for temporal link prediction over SOTA methods.

show abstract

Temporal Heterogeneous Information Network Embedding

Cited by 19 publications

References 13 publications

Pretrained Language–Knowledge Graph Model Benefits Both Knowledge Graph Completion and Industrial Tasks: Taking the Blast Furnace Ironmaking Process as an Example

Pretrained Language–Knowledge Graph Model Benefits Both Knowledge Graph Completion and Industrial Tasks: Taking the Blast Furnace Ironmaking Process as an Example

Memory-Enhanced Transformer for Representation Learning on Temporal Heterogeneous Graphs

HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction

Contact Info

Product

Resources

About