scholarly journals Heterogeneous Graph Information Bottleneck

2021 ◽  
Author(s):  
Liang Yang ◽  
Fan Wu ◽  
Zichen Zheng ◽  
Bingxin Niu ◽  
Junhua Gu ◽  
...  
Keyword(s):  
Mutual Information ◽  
Representation Learning ◽  
Specific Information ◽  
Heterogeneous Information ◽  
Heterogeneous Information Networks ◽  
Information Bottleneck ◽  
Homogeneous Network ◽  
Attributed Network ◽  
Graph Neural Networks ◽  
Attributed Networks

Most attempts on extending Graph Neural Networks (GNNs) to Heterogeneous Information Networks (HINs) implicitly take the direct assumption that the multiple homogeneous attributed networks induced by different meta-paths are complementary. The doubts about the hypothesis of complementary motivate an alternative assumption of consensus. That is, the aggregated node attributes shared by multiple homogeneous attributed networks are essential for node representations, while the specific ones in each homogeneous attributed network should be discarded. In this paper, a novel Heterogeneous Graph Information Bottleneck (HGIB) is proposed to implement the consensus hypothesis in an unsupervised manner. To this end, information bottleneck (IB) is extended to unsupervised representation learning by leveraging self-supervision strategy. Specifically, HGIB simultaneously maximizes the mutual information between one homogeneous network and the representation learned from another homogeneous network, while minimizes the mutual information between the specific information contained in one homogeneous network and the representation learned from this homogeneous network. Model analysis reveals that the two extreme cases of HGIB correspond to the supervised heterogeneous GNN and the infomax on homogeneous graph, respectively. Extensive experiments on real datasets demonstrate that the consensus-based unsupervised HGIB significantly outperforms most semi-supervised SOTA methods based on complementary assumption.

scholarly journals TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism

2018 ◽  
Author(s):  
Yang Fang ◽  
Xiang Zhao ◽  
Zhen Tan
Keyword(s):  
Large Scale ◽  
Representation Learning ◽  
Information Networks ◽  
Heterogeneous Information ◽  
Structure Information ◽  
Heterogeneous Information Networks ◽  
Network Representation ◽  
Meta Path ◽  
Translation Mechanism ◽  
Real World Datasets

In this paper, we propose a novel network representation learning model TransPath to encode heterogeneous information networks (HINs). Traditional network representation learning models aim to learn the embeddings of a homogeneous network. TransPath is able to capture the rich semantic and structure information of a HIN via meta-paths. We take advantage of the concept of translation mechanism in knowledge graph which regards a meta-path, instead of an edge, as a translating operation from the first node to the last node. Moreover, we propose a user-guided meta-path sampling strategy which takes users' preference as a guidance, which could explore the semantics of a path more precisely, and meanwhile improve model efficiency via the avoidance of other noisy and meaningless meta-paths. We evaluate our model on two large-scale real-world datasets DBLP and YELP, and two benchmark tasks similarity search and node classification. We observe that TransPath outperforms other state-of-the-art baselines consistently and significantly.

scholarly journals Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding

Algorithms ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 263
Author(s):  
Shuli Wang ◽  
Xuewen Li ◽  
Xiaomeng Kou ◽  
Jin Zhang ◽  
Shaojie Zheng ◽  
...  
Keyword(s):  
Long Range ◽  
Learning Sequence ◽  
Target Node ◽  
Convolutional Network ◽  
Heterogeneous Information ◽  
Heterogeneous Information Networks ◽  
Sequence Representation ◽  
Graph Neural Networks ◽  
Public Datasets ◽  
Item Representation

Predicting users’ next behavior through learning users’ preferences according to the users’ historical behaviors is known as sequential recommendation. In this task, learning sequence representation by modeling the pairwise relationship between items in the sequence to capture their long-range dependencies is crucial. In this paper, we propose a novel deep neural network named graph convolutional network transformer recommender (GCNTRec). GCNTRec is capable of learning effective item representation in a user’s historical behaviors sequence, which involves extracting the correlation between the target node and multi-layer neighbor nodes on the graphs constructed under the heterogeneous information networks in an end-to-end fashion through a graph convolutional network (GCN) with degree encoding, while the capturing long-range dependencies of items in a sequence through the transformer encoder model. Using this multi-dimensional vector representation, items related to the a user historical behavior sequence can be easily predicted. We empirically evaluated GCNTRec on multiple public datasets. The experimental results show that our approach can effectively predict subsequent relevant items and outperforms previous techniques.

Graph Community Infomax

2022 ◽  
Vol 16 (3) ◽  
pp. 1-21
Author(s):  
Heli Sun ◽  
Yang Li ◽  
Bing Lv ◽  
Wujie Yan ◽  
Liang He ◽  
...  
Keyword(s):  
Mutual Information ◽  
Representation Learning ◽  
Graph Representation ◽  
Network Embedding ◽  
Adversarial Network ◽  
Low Dimension ◽  
Community Information ◽  
Model Graph ◽  
Embedding Methods ◽  
Attributed Networks

Graph representation learning aims at learning low-dimension representations for nodes in graphs, and has been proven very useful in several downstream tasks. In this article, we propose a new model, Graph Community Infomax (GCI), that can adversarial learn representations for nodes in attributed networks. Different from other adversarial network embedding models, which would assume that the data follow some prior distributions and generate fake examples, GCI utilizes the community information of networks, using nodes as positive(or real) examples and negative(or fake) examples at the same time. An autoencoder is applied to learn the embedding vectors for nodes and reconstruct the adjacency matrix, and a discriminator is used to maximize the mutual information between nodes and communities. Experiments on several real-world and synthetic networks have shown that GCI outperforms various network embedding methods on community detection tasks.

Valuation mapping of hazards of the crisis natural and economic situations

2017 ◽  
Vol 929 (11) ◽  
pp. 40-49
Author(s):  
N.E. Krasnoshtanova ◽  
A.K. Cherkashin
Keyword(s):  
Spatial Data ◽  
Heterogeneous Information ◽  
Secondary Use ◽  
Raster Maps ◽  
Irkutsk Region ◽  
Homogeneous Network ◽  
Surrounding Areas ◽  
Integral Assessment ◽  
Multidimensional Statistics

An innovative technique for the secondary use of cartographic information for creating assessment hazard maps of crisis natural and economic situations and an integral assessment of the sustainability economic development and the quality of live is presented. Valuation mapping was carried for the Slyudyansky district of the Irkutsk region. A database has been created for homogeneous network of plots, which contains heterogeneous information about the nature and socio-economic environment of the district. Spatial data were processed using multidimensional statistics on the base of reliability theory models. An account of the environmental correction for each plots is an important aspect of the proposed technique of assessing and creating through maps. This makes it possible to reduce the evaluation function to an invariant form common to all locations and it is used in through way to create assessment maps for natural and socio-economic objects. As a result, a series of raster maps of through thematic content was made. The map of integral hazard of emergence of economic crisis situation displays the lowest hazard values for the territories of settlements and their surrounding areas, as well as areas along roads and railways. Additionally it allocates undeveloped valley of taiga rivers, advanced for economic use, primarily for recreational purposes.

W-MMP2Vec: Topic-driven network embedding model for link prediction in content-based heterogeneous information network

2021 ◽  
Vol 25 (3) ◽  
pp. 711-738
Author(s):  
Phu Pham ◽  
Phuc Do
Keyword(s):  
Link Prediction ◽  
Representation Learning ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Learning Framework ◽  
Novel Approach ◽  
Proposed Model ◽  
Meta Path

Link prediction on heterogeneous information network (HIN) is considered as a challenge problem due to the complexity and diversity in types of nodes and links. Currently, there are remained challenges of meta-path-based link prediction in HIN. Previous works of link prediction in HIN via network embedding approach are mainly focused on exploiting features of node rather than existing relations in forms of meta-paths between nodes. In fact, predicting the existence of new links between non-linked nodes is absolutely inconvincible. Moreover, recent HIN-based embedding models also lack of thorough evaluations on the topic similarity between text-based nodes along given meta-paths. To tackle these challenges, in this paper, we proposed a novel approach of topic-driven multiple meta-path-based HIN representation learning framework, namely W-MMP2Vec. Our model leverages the quality of node representations by combining multiple meta-paths as well as calculating the topic similarity weight for each meta-path during the processes of network embedding learning in content-based HINs. To validate our approach, we apply W-TMP2Vec model in solving several link prediction tasks in both content-based and non-content-based HINs (DBLP, IMDB and BlogCatalog). The experimental outputs demonstrate the effectiveness of proposed model which outperforms recent state-of-the-art HIN representation learning models.

Sign in / Sign up

Export Citation Format

Share Document