Gated relational stacked denoising autoencoder with localized author embedding for global citation recommendation

•A novel neural model is proposed for global citation recommendation task. The proposed model is essentially a combination of three neural networks with latent variables.•A novel author embedding method that uses limited localized neighbors is developed. The extensibility of this method is verified....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Expert systems with applications Ročník 184; s. 115359
Hlavní autori: Dai, Tao, Yan, Wenjun, Zhang, Kaiqi, Qiu, Chen, Zhao, Xiangmo, Pan, Shirui
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Elsevier Ltd 01.12.2021
Elsevier BV
Predmet:
Algorithms
Artificial neural networks
Citation analysis
Citations
Computer architecture
Deep learning
Embedding
Global citation recommendation
Machine learning
Modules
Neural networks
Noise reduction
Recommender systems
Representations
Semantics
Stacked denoising autoencoder
Topic model
Deep learning
Stacked denoising autoencoder
Topic model
Global citation recommendation
Machine learning
ISSN:0957-4174, 1873-6793
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•A novel neural model is proposed for global citation recommendation task. The proposed model is essentially a combination of three neural networks with latent variables.•A novel author embedding method that uses limited localized neighbors is developed. The extensibility of this method is verified.•The learning algorithm of the proposed neural model is detailedly derived.•The time complexity for the learning algorithm is analyzed.•Extensive experiments manifest the superiority of the proposed model. Citation recommendation is an effective and efficient way to facilitate authors finding desired references. This paper presents a novel neural network based model, called gated relational probabilistic stacked denoising autoencoder with localized author (GRSLA) embedding, for global citation recommendation task. Our model is comprised of two modules with different neural network architecture. For each citing and cited papers, we use a gated paper embedding module, which is extended from probabilistic stacked denoising autoencoder (PSDAE) by adding gated units, to obtain their paper vectors. The added gated units are able to utilize text information of cited paper to refine the vector representation of citing paper in multiple semantic levels. For an author in papers, we first apply topic model to obtain his/her semantic neighbors, and then use a localized author embedding (LAE) module to excavate author vector representation from semantic and explicit neighbors. Unlike most graph convolutional network (GCN) based methods, the LAE module is able to avoid computing global Laplacian in whole graph by taking limited neighbors. Moreover, the LAE module can also be stacked to absorb more neighbors, which makes our model have high extendibility. Based on the generation process of GRSLA, we also derive a learning algorithm of our model by maximum a posteriori (MAP) estimation. We conduct experiments on the AAN, DBLP and CORD-19 datasets, and the results show that GRSLA model works well than previous global citation recommendation methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2021.115359