DySAT

Ashok, S.; Wu, Yanhong; Gou, Liang; Zhang, Wei; Yang, Hao

doi:10.1145/3336191.3371845

Cited by 370 publications

(85 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such as EvolveGCN [22] uses the RNN model to update the parameters of GCN for future snapshots. DySAT [23] combines graph structure and dynamic information to generate self-weighted node representations.…”

Section: Related Workmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Related Workmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…These networks differ from one another in the techniques used for processing both the structural information and the temporal dynamics of the STGs. DySAT [38] introduced a generalization of Graph Attention Network (GAT) [44] for STGs. First, it uses a self-attention mechanism to generate static node embeddings at each timestamp.…”

Section: Embedding Evolution Methodsmentioning

confidence: 99%

“…The domain of the function f LP is the set of all feasible pairs of nodes, since it is possible to predict the probability of future interactions between nodes that have been connected in the past or not, as well as the probability of missing edges in a past time. Most TGNN approaches for temporal link prediction focus on future predictions, forecasting the existence of an edge in a future timestamp between existing nodes (FT is the most common setting) [31,38,16,55,50,26,45,27,36,58], or unseen nodes (FI) [16,50,36]. The only model that investigates past temporal link prediction is [26], which devises a PI setting by masking some nodes and predicting the existence of a past edge between them.…”

Section: Link Predictionmentioning

confidence: 99%

“…Recently, GNNs have been successfully applied also to temporal graphs, achieving state-of-the-art results on tasks such as temporal link prediction [38], node classification [36] and edge classification [45], with approaches ranging from attention-based methods [50] to Variational Graph-Autoencoder (VGAE) [16]. However, despite the potential of GNN-based models for temporal graph processing and the variety of different approaches that emerged, a systematization of the literature is still missing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

Longa¹,

Lachi²,

Santin³

et al. 2023

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graphstructured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent years, GNNbased models for temporal graphs have emerged as a promising area of research to extend the capabilities of GNNs. In this work, we provide the first comprehensive overview of the current state-of-the-art of temporal GNN, introducing a rigorous formalization of learning settings and tasks and a novel taxonomy categorizing existing approaches in terms of how the temporal aspect is represented and processed. We conclude the survey with a discussion of the most relevant open challenges for the field, from both research and application perspectives.

show abstract

“…Given a sequence of knowledge graphs

built on the extracted entities and relations, we aim to learn rich node representations over time by encoding both temporal evolution patterns and structural neighbourhood information [ 58 ], which can be useful for monitoring the pandemics and identifying the risk factors. Specifically, we formulate the task into a time-series prediction problem.…”

Section: Methodsmentioning

confidence: 99%

COVID-19 Surveiller: toward a robust and effective pandemic surveillance system based on social media mining

Jiang

Zhou

Chen

et al. 2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

The outbreak of the novel coronavirus, COVID-19, has become one of the most severe pandemics in human history. In this paper, we propose to leverage social media users as social sensors to simultaneously predict the pandemic trends and suggest potential risk factors for public health experts to understand spread situations and recommend proper interventions. More precisely, we develop novel deep learning models to recognize important entities and their relations over time, thereby establishing dynamic heterogeneous graphs to describe the observations of social media users. A dynamic graph neural network model can then forecast the trends (e.g. newly diagnosed cases and death rates) and identify high-risk events from social media. Based on the proposed computational method, we also develop a web-based system for domain experts without any computer science background to easily interact with. We conduct extensive experiments on large-scale datasets of COVID-19 related tweets provided by Twitter, which show that our method can precisely predict the new cases and death rates. We also demonstrate the robustness of our web-based pandemic surveillance system and its ability to retrieve essential knowledge and derive accurate predictions across a variety of circumstances. Our system is also available at http://scaiweb.cs.ucla.edu/covidsurveiller/ . This article is part of the theme issue ‘Data science approachs to infectious disease surveillance’.

show abstract

DySAT

Cited by 370 publications

References 14 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

COVID-19 Surveiller: toward a robust and effective pandemic surveillance system based on social media mining

Contact Info

Product

Resources

About