inductive representation learning on temporal graph

View PDF Abstract: Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving ...

Introduction. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, as functions of time, should represent both the static node features and the evolving topological structures. We propose the temporal graph attention (TGAT) layer to efficiently aggregate temporal ...

The motivation for adapting self-attention to inductive representation learning on temporal graphs is to identify and capture relevant pieces of the temporal neighborhood information. Both graph con- volutional network (GCN) (Kipf & Welling, 2016a) and GAT are implicitly or explicitly assigning different weights to neighboring nodes ...

The temporal graph attention (TGAT) layer is proposed to efficiently aggregate temporal-topological neighborhood features as well as to learn the time-feature interactions by developing a novel functional time encoding technique based on the classical Bochner's theorem from harmonic analysis. Inductive representation learning on temporal graphs is an important step toward salable machine ...

Abstract: Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological ...

Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature ... Learning representations on temporal graphs is extremely challenging, and it is not until recently that several solutions are proposed (Nguyen et al., 2018; Li et al., 2018; Goyal et ...

Abstract: Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological ...

Abstract and Figures. Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal ...

Representation learning on temporal graphs is a hot topic in the community of graph learning, where researchers have devoted to mining temporal correlations from graphs and achieve great successes across different domains [6, 10, 15, 31].However, many methods [14, 30] only work for a fixed topology (transductive settings), while in product scenarios, a temporal graph usually evolves as new ...

To handle the aforementioned challenges, we propose Graph Temporal Edge Aggregation (GTEA) for inductive representation learning on TIGs based on Graph Neural Networks (GNN). Different from previous works, we present a new perspective to deal with TIGs. Instead of partitioning a temporal graph into multiple snapshots or grouping all related ...

Edit social preview. Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent ...

Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological structures.

Abstract: Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological ...

William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NeurIPS. 1024-1034. Google Scholar; Kaiwen He, Xu Chen, Qiong Wu, Shuai Yu, and Zhi Zhou. 2022. Graph Attention Spatial-Temporal Network With Collaborative Global-Local Learning for Citywide Mobile Traffic Prediction.

In this paper, we propose the Graph Temporal Edge Aggregation (GTEA) framework for inductive learning on Temporal Interaction Graphs (TIGs). Different from previous works, GTEA models the temporal dynamics of interaction sequences in the continuous-time space and simultaneously takes advantage of both rich node and edge/ interaction attributes in the graph.

Abstract. Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the ...

Finally, the obtained graph-level representations are fed into a temporal convolutional network (TCN) to extract the temporal dependencies between EEG frames. We evaluated our proposed ATGRNet on the SEED, DEAP and FACED datasets. The experimental findings show that the proposed ATGRNet surpasses the state-of-the-art graph-based mehtods for EEG ...

Achan, Kannan. Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both ...

<p>Knowledge representation learning (KRL) aims to encode entities and relationships in various knowledge graphs into low-dimensional continuous vectors. It is popularly used in knowledge graph completion (or link prediction) tasks. Translation-based knowledge representation learning methods perform well in knowledge graph completion (KGC). However, the translation principles adopted by these ...

Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. However, existing TKG approaches still face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. In this paper, we propose an ...

Temporal Knowledge Graph (TKG) reasoning often involves completing missing factual elements along the timeline. Although existing methods can learn good embeddings for each factual element in quadruples by integrating temporal information, they often fail to infer the evolution of temporal facts. This is mainly because of (1) insufficiently exploring the internal structure and semantic ...

Inductive Representation Learning on Large Graphs. Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings ...