GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction

Chen, Jinyin; Wang, Xueke; Xu, Xuanheng

doi:10.48550/arxiv.1812.04206

Cited by 25 publications

(35 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GCN [20] and GraphSage [23] are supervised methods that include static graph structure and node attributes; they both ignore temporal information. GC-LSTM [24] is another supervised method that utilizes the temporal information of both graphs and node attributes. RNNGCN [2] employed a 2-layer GCN and introduced a decay weight as a learnable parameter; information from each timestep was multiplied by this weight, which decayed over time, and the resulting linear combination over time was used for classification.…”

Section: B Baselines and Metricsmentioning

confidence: 99%

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

Fan¹,

Yao²,

Joe‐Wong³

2021

Preprint

View full text Add to dashboard Cite

Graph Convolutional Networks (GCNs) are a popular method from graph representation learning that have proved effective for tasks like node classification tasks. Although typical GCN models focus on classifying nodes within a static graph, several recent variants propose node classification in dynamic graphs whose topologies and node attributes change over time, e.g., social networks with dynamic relationships, or literature citation networks with changing co-authorships. These works, however, do not fully address the challenge of flexibly assigning different importance to snapshots of the graph at different times, which depending on the graph dynamics may have more or less predictive power on the labels. We address this challenge by proposing a new method, GCN-SE, that attaches a set of learnable attention weights to graph snapshots at different times, inspired by Squeeze and Excitation Net (SE-Net). We show that GCN-SE outperforms previously proposed node classification methods on a variety of graph datasets. To verify the effectiveness of the attention weight in determining the importance of different graph snapshots, we adapt perturbation-based methods from the field of explainable machine learning to graphical settings and evaluate the correlation between the attention weights learned by GCN-SE and the importance of different snapshots over time. These experiments demonstrate that GCN-SE can in fact identify different snapshots' predictive power for dynamic node classification.

show abstract

Section: B Baselines and Metricsmentioning

confidence: 99%

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

Fan¹,

Yao²,

Joe‐Wong³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The purpose of GNN is to apply deep neural network model to graph representation learning, and map graphs to low-dimensional vector spaces for downstream tasks, such as link prediction [35,4], node classification [23,1], recommendation [22,36,7], etc. The notion of graph neural networks is initially outlined in [10], then Franco et al [24] extended recursive neural networks to graph learning task and Li et al [18] treated the neighborhood information as the time step input of gated recurrent units.…”

Section: Graph Neural Networkmentioning

confidence: 99%

HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning

Cai,

Shang,

Hao

et al. 2021

Preprint

View full text Add to dashboard Cite

Many real-world data can be represented as heterogeneous graphs with different types of nodes and connections. Heterogeneous graph neural network model aims to embed nodes or subgraphs into low-dimensional vector space for various downstream tasks such as node classification, link prediction, etc. Although several models were proposed recently, they either only aggregate information from the same type of neighbors, or just indiscriminately treat homogeneous and heterogeneous neighbors in the same way. Based on these observations, we propose a new heterogeneous graph neural network model named HMSG to comprehensively capture structural, semantic and attribute information from both homogeneous and heterogeneous neighbors. Specifically, we first decompose the heterogeneous graph into multiple metapath-based homogeneous and heterogeneous subgraphs, and each subgraph associates specific semantic and structural information. Then message aggregation methods are applied to each subgraph independently, so that information can be learned in a more targeted and efficient manner. Through a type-specific attribute transformation, node attributes can also be transferred among different types of nodes. Finally, we fuse information from subgraphs together to get the complete representation. Extensive experiments on several datasets for node classification, node clustering and link prediction tasks show that HMSG achieves the best performance in all evaluation metrics than state-of-the-art baselines.

show abstract

“…In order to deal with the complicated time-varied graphs, it is necessary and crucial to preprocess the raw dynamic graph representations, which record all continuous evolution of the graph over time, such as node emerging/disappearing and link addition/deletion [9,10,11,12,13]. Current researches [14,15,16,17,18,19,20] refine the raw dynamic representations to two main branches, dynamic continuous and discrete graphs. For the former graphs, the raw representations are projected to a single 2D temporal graph, storing most information in graph evolution.…”

Section: Introductionmentioning

confidence: 99%

“…It is crucial to have an efficient and powerful network under specific tasks in this step. Some researches [16,19,20] utilize recurrent neural networks (RNNs) to scrutinize representations on the sequence of dynamic graphs. However, RNNbased DGNNs are more time-consuming and inadequately handle sequential time-dependent embedding with increasing moments of time-steps.…”

Section: Introductionmentioning

confidence: 99%

Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network

Yan¹,

Liu²

2022

Preprint

View full text Add to dashboard Cite

GStatic graph neural networks have been widely used in modeling and representation learning of graph structure data. However, many real-world problems, such as social networks, financial transactions, recommendation systems, etc., are dynamic, that is, nodes and edges are added or deleted over time. Therefore, in recent years, dynamic graph neural networks have received more and more attention from researchers. In this work, we propose a novel dynamic graph neural network, Efficient-Dyn. It adaptively encodes temporal information into a sequence of patches with an equal amount of temporal-topological structure. Therefore, while avoiding the use of snapshots to cause information loss, it also achieves a finer time granularity, which is close to what continuous networks could provide. In addition, we also designed a lightweight module, Sparse Temporal Transformer, to compute node representations through both structural neighborhoods and temporal dynamics. Since the fully-connected attention conjunction is simplified, the computation cost is far lower than the current state-of-the-arts. Link prediction experiments are conducted on both continuous and discrete graph datasets. Through comparing with several state-of-the-art graph embedding baselines, the experimental results demonstrate that Efficient-Dyn has a faster inference speed while having competitive performance.

show abstract

GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction

Cited by 25 publications

References 40 publications

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs

HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning

Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network

Contact Info

Product

Resources

About