Neural Embedding Propagation on Heterogeneous Networks

Yang, Carl; Zhang, Jieyu

doi:10.1109/icdm.2019.00080

Cited by 23 publications

(14 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our paper investigates network embedding through embedding propagation [Yang et al 2019], where we can take advantage of initial event embeddings using a BERT based pre-trained neural language model. The general problem for embedding propagation proposed in this paper is presented in Equation 1, inspired by a general graph regularization framework [Ji et al 2010].…”

Section: Trend Prediction On Heterogeneous Information Networkmentioning

confidence: 99%

Commodities trend link prediction on heterogeneous information networks

Carmo

Filho

Marcacini

2021

Anais Do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)

View full text Add to dashboard Cite

Events can be defined as an action or a series of actions that have a determined theme, time, and place. Event analysis tasks for knowledge extraction from news and social media have been explored in recent years. However, there are still few studies that aim to enrich predictive models using event data. In particular, agribusiness events have multiple components to be considered for a successful prediction model. For example, price trend predictions for commodities can be performed through time series analysis of prices, but we can also consider events that represent knowledge about external factors during the training step of predictive models. In this paper, we present a method for integrating events into trend prediction tasks. First, we propose to model events and time-series information through heterogeneous information networks (HIN) that allow multiple components to be directly modeled through multi-type nodes and edges. Second, we learn features from HIN through network embedding methods, i.e., network nodes are mapped to a dense vector of features. In particular, we propose a network embedding method that propagates the semantic of the pre-trained neural language models to a heterogeneous information network and evaluates its performance in a trend link prediction. We show that the use of our proposed model language-based embedding propagation is competitive with state-of-art network embeddings algorithms. Moreover, our proposal performs network embedding incrementally, thereby allowing new events to be inserted in the same semantic space without rebuilding the entire network embedding.

show abstract

Section: Trend Prediction On Heterogeneous Information Networkmentioning

confidence: 99%

Commodities trend link prediction on heterogeneous information networks

Carmo

Filho

Marcacini

2021

Anais Do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)

View full text Add to dashboard Cite

show abstract

“…We mainly compare with those on content-rich networks. For example, models like TADW [45], PTE [30], Planetoid [53], paper2vec [8], STNE [21], AutoPath [44] and NEP [48] have been designed to improve network embedding by incorporating node contents like types, a ributes and texts. Moreover, the convolution based models like GCN [17], GAT [34], GraphSage [10], CANE [33], Di Pool [54], JK-Net [42], FastGCN [6] and DGI [35] naturally take the input of both node features and links.…”

Section: Related Techniquesmentioning

confidence: 99%

Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders

Yang

Zhang

Wang

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

While node semantics have been extensively explored in social networks, li le research a ention has been paid to pro le edge semantics, i.e., social relations. Ideal edge semantics should not only show that two users are connected, but also why they know each other and what they share in common. However, relations in social networks are o en hard to pro le, due to noisy multi-modal signals and limited user-generated ground-truth labels.In this work, we aim to develop a uni ed and principled framework that can pro le user relations as edge semantics in social networks by integrating multi-modal signals in the presence of noisy and incomplete data. Our framework is also exible towards limited or missing supervision. Speci cally, we assume a latent distribution of multiple relations underlying each user link, and learn them with multi-modal graph edge variational autoencoders. We encode the network data with a graph convolutional network, and decode arbitrary signals with multiple reconstruction networks. Extensive experiments and case studies on two public DBLP author networks and two internal LinkedIn member networks demonstrate the superior e ectiveness and e ciency of our proposed model.

show abstract

“…Right on the intersection of heterogeneous networks and graph embedding, heterogeneous network embedding (HNE) recently has also received much research attention [8,85,108,16,66,67,27,22,90,35,104,57,52,99,7,98,32,83,95,82,41]. Due to the application favor of HNE, many algorithms have been separately developed in different application domains such as search and recommendations [23,63,6,89].…”

Section: Introductionmentioning

confidence: 99%