MV-GCN: Multi-View Graph Convolutional Networks for Link Prediction

Zhao, Li; Liu, Zhan‐Lin; Huang, Jiaming; Tang, Geyu; Duan, Yucong; Zhang, Zhiqiang; Yang, Yifan

doi:10.1109/access.2019.2957306

Cited by 34 publications

(13 citation statements)

References 43 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The representative work of Graph Embedding is DeepWalk (Perozzi et al, 2014), LINE (Tang et al, 2015), Node2Vec (Grover and Leskovec, 2016), SDNE (Wang et al, 2016), and Struc2Vec (Ribeiro et al, 2017). The obtained expression vectors can be used for downstream tasks, such as node classification (Ye et al, 2018;Gong and Ai, 2019), link prediction (Li et al, 2019a), or visualization (Liu et al, 2020). In the field of biomedicine, graphs are often used to predict drug interactions and predict drug target proteins.…”

Section: Graph Embeddingmentioning

confidence: 99%

Explainable Prediction of Medical Codes With Knowledge Graphs

Teng

Yang

Chen

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

International Classification of Diseases (ICD) is an authoritative health care classification system of different diseases. It is widely used for disease and health records, assisted medical reimbursement decisions, and collecting morbidity and mortality statistics. The most existing ICD coding models only translate the simple diagnosis descriptions into ICD codes. And it obscures the reasons and details behind specific diagnoses. Besides, the label (code) distribution is uneven. And there is a dependency between labels. Based on the above considerations, the knowledge graph and attention mechanism were expanded into medical code prediction to improve interpretability. In this study, a new method called G_Coder was presented, which mainly consists of Multi-CNN, graph presentation, attentional matching, and adversarial learning. The medical knowledge graph was constructed by extracting entities related to ICD-9 from freebase. Ontology contains 5 entity classes, which are disease, symptom, medicine, surgery, and examination. The result of G_Coder on the MIMIC-III dataset showed that the micro-F1 score is 69.2% surpassing the state of art. The following conclusions can be obtained through the experiment: G_Coder integrates information across medical records using Multi-CNN and embeds knowledge into ICD codes. Adversarial learning is used to generate the adversarial samples to reconcile the writing styles of doctor. With the knowledge graph and attention mechanism, most relevant segments of medical codes can be explained. This suggests that the knowledge graph significantly improves the precision of code prediction and reduces the working pressure of the human coders.

show abstract

Section: Graph Embeddingmentioning

confidence: 99%

Explainable Prediction of Medical Codes With Knowledge Graphs

Teng

Yang

Chen

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…Recently, graph neural networks (GNNs), which learn node representations via convolution over node features and graph topology, have emerged as a prevalent modeling paradigm for graph data. GNNs have shown promising results on several graph learning tasks, such as node classification [16,24], link prediction [30,61] and social network analysis [43,49,57]. However, their direct application for our problem is impeded by a few factors: (i) Most prior work in GNNs focuses on node and graph classification [16,24,54]; although a few works tackle prediction of missing links [60,61], this is a different context than ours, which involves ranking over existing links.…”

Section: Introductionmentioning

confidence: 99%

Friend Story Ranking with Edge-Contextual Local Graph Convolutions

Tang

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Social platforms have paved the way in creating new, modern ways for users to communicate with each other. In recent years, multiple platforms have introduced "Stories" features, which enable broadcasting of ephemeral multimedia content. Specifically, "Friend Stories, " or Stories meant to be consumed by one's close friends, are a popular feature, promoting significant user-user interactions by allowing people to see (visually) what their friends and family are up to. A key challenge in surfacing Friend Stories for a given user, is in ranking over each viewing user's friends to efficiently prioritize and route limited user attention. In this work, we explore the novel problem of Friend Story Ranking from a graph representation learning perspective. More generally, our problem is a link ranking task, where inferences are made over existing links (relations), unlike common node or graph-based tasks, or link prediction tasks, where the goal is to make inferences about non-existing links. We propose ELR, an edge-contextual approach which carefully considers local graph structure, differences between local edge types and directionality, and rich edge attributes, building on the backbone of graph convolutions. ELR handles social sparsity challenges by considering and attending over neighboring nodes, and incorporating multiple edge types in local surrounding egonet structures. We validate ELR on two large country-level datasets with millions of users and tens of millions of links from Snapchat. ELR shows superior performance over alternatives by ≈ 8% and ≈ 5% error reduction measured by MSE and MAE correspondingly. Further generality, data efficiency and ablation experiments confirm the advantages of ELR.

show abstract

“…To resolve the above problems, graph embedding aims to learn a project from graph data in the original topological space to low-dimensional vector space while encoding structural and semantic information. The vector representation obtained could effectively support extensive graph analysis tasks including node classification [7] [8], node clustering [9] [10], link prediction [11] [12], graph classification [13], etc. Because of the universality of the embedding vectors, graph embedding technology can be applied to many fields and tasks such as social networks and recommender systems [14] by using the off-the-shelf machine learning method.…”

Section: Introductionmentioning

confidence: 99%