Variational Graph Recurrent Neural Networks

Hajiramezanali, Ehsan; Hasanzadeh, Arman; Duffield, Nick; Narayanan, Krishna R; Zhou, Mingyuan; Qian, Xiaoning

doi:10.48550/arxiv.1908.09710

Cited by 7 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another line of work on temporal (knowledge) graph reasoning uses message passing networks to capture intra-graph neighborhood information, which is sometimes combined with temporal recurrence or attention mechanisms (Manessi et al, 2020;Kumar et al, 2018;Pareja et al, 2019;Chen et al, 2018;Jin et al, 2019;Sankar et al, 2020;Hajiramezanali et al, 2019). Orthogonal to our work, Trivedi et al (2017Trivedi et al ( , 2019; Han et al (2020) explore using temporal point processes.…”

Section: Related Workmentioning

confidence: 94%

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

Cao²,

Cheung

et al. 2020

Preprint

View full text Add to dashboard Cite

Inferring missing facts in temporal knowledge graphs (TKGs) is a fundamental and challenging task. Previous works have approached this problem by augmenting methods for static knowledge graphs to leverage time-dependent representations. However, these methods do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions. Additionally, prior work does not explicitly address the temporal sparsity and variability of entity distributions in TKGs. We propose the Temporal Message Passing (TeMP) framework to address these challenges by combining graph neural networks, temporal dynamics models, data imputation and frequency-based gating techniques. Experiments 1 on standard TKG tasks show that our approach provides substantial gains compared to the previous state of the art, achieving a 10.7% average relative improvement in Hits@10 across three standard benchmarks. Our analysis also reveals important sources of variability both within and across TKG datasets, and we introduce several simple but strong baselines that outperform the prior state of the art in certain settings.

show abstract

Section: Related Workmentioning

confidence: 94%

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

Cao²,

Cheung

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Since dynamic graph representations append the time dimension on the static ones, the RNN-based DGNNs [18,28] are considered to summarize temporal information over time. However, the computation of RNN-based DGNNs is expensive because RNNs need a large amount of graph data for training.…”

Section: Dynamic Graph Neural Networkmentioning

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

“…GGNN (Li et al, 2015) is another time-and-graph application where node attributes do not change, thus it does not have the GNN in part that most other time-and-graph methods have (see Equation ( 9)). There are also variational autoencoder works (Hajiramezanali et al, 2019) and generative adversarial works (Lei et al, 2019;Xiong et al, 2019), which are extensions of time-and-graph works introduced earlier, e.g., putting time-and-graph as the encoder of generative adversarial framework.…”

Section: E Related Workmentioning

confidence: 99%

On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions

Gao¹,

Ribeiro²

2021

Preprint

View full text Add to dashboard Cite

In this work we formalize the (pure observational) task of predicting node attribute evolution in temporal graphs. We show that node representations of temporal graphs can be cast into two distinct frameworks: (a) The de-facto standard approach, which we denote time-and-graph, where equivariant graph (e.g., GNN) and sequence (e.g., RNN) representations are intertwined to represent the temporal evolution of the graph; and (b) an approach that we denote time-then-graph, where the sequences describing the node and edge dynamics are represented first (e.g., RNN), then fed as node and edge attributes into a (static) equivariant graph representation that comes after (e.g., GNN). In real-world datasets, we show that our time-then-graph framework achieves the same prediction performance as state-of-the-art time-and-graph methods. Interestingly, time-then-graph representations have an expressiveness advantage over time-and-graph representations when both use component GNNs that are not most-expressive (e.g., 1-Weisfeiler-Lehman GNNs). We introduce a task where this expressiveness advantage allows time-then-graph methods to succeed while state-of-the-art time-and-graph methods fail.

show abstract

Variational Graph Recurrent Neural Networks

Cited by 7 publications

References 19 publications

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

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

On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions

Contact Info

Product

Resources

About