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.

scholarly journals Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 186
Author(s):  
Hanlin Sun ◽  
Wei Jie ◽  
Jonathan Loo ◽  
Liang Chen ◽  
Zhongmin Wang ◽  
...  
Keyword(s):  
Game Theory ◽  
Community Structure ◽  
State Of The Art ◽  
Representation Learning ◽  
Network Embedding ◽  
Network Representation ◽  
Low Dimension ◽  
Community Information ◽  
Model Community ◽  
Series Of Experiments

Presently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity and low parallelizability because of the nature of complicated interconnected structure of their nodes. Network representation learning, also called network embedding, provides a practical and promising way to solve these issues. One of the foremost requirements of network embedding is preserving network topology properties in learned low-dimension representations. Community structure is a prominent characteristic of complex networks and thus should be well maintained. However, the difficulty lies in the fact that the properties of community structure are multivariate and complicated; therefore, it is insufficient to model community structure using a predefined model, the way that is popular in most state-of-the-art network embedding algorithms explicitly considering community structure preservation. In this paper, we introduce a multi-process parallel framework for network embedding that is enhanced by found partial community information and can preserve community properties well. We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information. A series of experiments are conducted to evaluate the performance of our methods and six state-of-the-art algorithms. The results demonstrate that our methods can effectively preserve community properties of networks in their low-dimension representations. Specifically, compared to the involved baselines, our algorithms behave the best and are the runners-up on networks with high overlapping diversity and density.

scholarly journals JANE: Jointly Adversarial Network Embedding

2020 ◽  
Author(s):  
Liang Yang ◽  
Yuexue Wang ◽  
Junhua Gu ◽  
Chuan Wang ◽  
Xiaochun Cao ◽  
...  
Keyword(s):  
Link Prediction ◽  
Real Data ◽  
Semantic Space ◽  
Network Embedding ◽  
Generative Adversarial Network ◽  
Adversarial Learning ◽  
Adversarial Network ◽  
Node Clustering ◽  
Topology Information ◽  
Embedding Methods

Motivated by the capability of Generative Adversarial Network on exploring the latent semantic space and capturing semantic variations in the data distribution, adversarial learning has been adopted in network embedding to improve the robustness. However, this important ability is lost in existing adversarially regularized network embedding methods, because their embedding results are directly compared to the samples drawn from perturbation (Gaussian) distribution without any rectification from real data. To overcome this vital issue, a novel Joint Adversarial Network Embedding (JANE) framework is proposed to jointly distinguish the real and fake combinations of the embeddings, topology information and node features. JANE contains three pluggable components, Embedding module, Generator module and Discriminator module. The overall objective function of JANE is defined in a min-max form, which can be optimized via alternating stochastic gradient. Extensive experiments demonstrate the remarkable superiority of the proposed JANE on link prediction (3% gains in both AUC and AP) and node clustering (5% gain in F1 score).

scholarly journals ACE: Ant Colony Based Multi-Level Network Embedding for Hierarchical Graph Representation Learning

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 73970-73982 ◽  
Author(s):  
Jianming Lv ◽  
Jiajie Zhong ◽  
Jintao Liang ◽  
Zhenguo Yang
Keyword(s):  
Representation Learning ◽  
Ant Colony ◽  
Graph Representation ◽  
Network Embedding ◽  
Hierarchical Graph ◽  
Multi Level

scholarly journals Learning Network Embedding with Community Structural Information

2019 ◽  
Author(s):  
Yu Li ◽  
Ying Wang ◽  
Tingting Zhang ◽  
Jiawei Zhang ◽  
Yi Chang
Keyword(s):  
Community Structure ◽  
Link Prediction ◽  
Structural Information ◽  
Representation Learning ◽  
Network Embedding ◽  
Learning Network ◽  
Optimization Framework ◽  
Vertex Representation ◽  
Low Dimensional ◽  
Embedding Methods

Network embedding is an effective approach to learn the low-dimensional representations of vertices in networks, aiming to capture and preserve the structure and inherent properties of networks. The vast majority of existing network embedding methods exclusively focus on vertex proximity of networks, while ignoring the network internal community structure. However, the homophily principle indicates that vertices within the same community are more similar to each other than those from different communities, thus vertices within the same community should have similar vertex representations. Motivated by this, we propose a novel network embedding framework NECS to learn the Network Embedding with Community Structural information, which preserves the high-order proximity and incorporates the community structure in vertex representation learning. We formulate the problem into a principled optimization framework and provide an effective alternating algorithm to solve it. Extensive experimental results on several benchmark network datasets demonstrate the effectiveness of the proposed framework in various network analysis tasks including network reconstruction, link prediction and vertex classification.

scholarly journals A Structural Representation Learning for Multi-relational Networks

2017 ◽  
Author(s):  
Lin Liu ◽  
Xin Li ◽  
William K. Cheung ◽  
Chengcheng Xu
Keyword(s):  
Representation Learning ◽  
Stochastic Gradient Descent ◽  
Network Embedding ◽  
Structural Representation ◽  
Relational Networks ◽  
Fundamental Limitations ◽  
Gradient Descent Algorithm ◽  
Scalable Learning ◽  
Relational Network ◽  
Embedding Methods

Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard-constraint commonly adopted by most of the network embedding methods is inaccurate by design, we propose a novel representation learning model for multi-relational networks which can alleviate both fundamental limitations. Scalable learning algorithms are derived using the stochastic gradient descent algorithm and negative sampling. Extensive experiments on real multi-relational network datasets of WordNet and Freebase demonstrate the efficacy of the proposed model when compared with the state-of-the-art embedding methods.

scholarly journals Discrete Embedding for Latent Networks

2020 ◽  
Author(s):  
Hong Yang ◽  
Ling Chen ◽  
Minglong Lei ◽  
Lingfeng Niu ◽  
Chuan Zhou ◽  
...  
Keyword(s):  
Real World ◽  
Representation Learning ◽  
Mixed Integer ◽  
Information Cascades ◽  
Integer Optimization ◽  
Network Embedding ◽  
Structure Information ◽  
Proximity Matrix ◽  
Real World Datasets ◽  
Embedding Methods

Discrete network embedding emerged recently as a new direction of network representation learning. Compared with traditional network embedding models, discrete network embedding aims to compress model size and accelerate model inference by learning a set of short binary codes for network vertices. However, existing discrete network embedding methods usually assume that the network structures (e.g., edge weights) are readily available. In real-world scenarios such as social networks, sometimes it is impossible to collect explicit network structure information and it usually needs to be inferred from implicit data such as information cascades in the networks. To address this issue, we present an end-to-end discrete network embedding model for latent networks DELN that can learn binary representations from underlying information cascades. The essential idea is to infer a latent Weisfeiler-Lehman proximity matrix that captures node dependence based on information cascades and then to factorize the latent Weisfiler-Lehman matrix under the binary node representation constraint. Since the learning problem is a mixed integer optimization problem, an efficient maximal likelihood estimation based cyclic coordinate descent (MLE-CCD) algorithm is used as the solution. Experiments on real-world datasets show that the proposed model outperforms the state-of-the-art network embedding methods.

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 GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures

2021 ◽  
Vol 11 (7) ◽  
pp. 3239
Author(s):  
Shicheng Cheng ◽  
Liang Zhang ◽  
Bo Jin ◽  
Qiang Zhang ◽  
Xinjiang Lu ◽  
...  
Keyword(s):  
Mutual Information ◽  
Link Prediction ◽  
Drug Target ◽  
State Of The Art ◽  
Target Prediction ◽  
Representation Learning ◽  
Graph Representation ◽  
Operating Characteristics ◽  
Information Index ◽  
Drug Target Prediction

The prediction of drug–target interactions is always a key task in the field of drug redirection. However, traditional methods of predicting drug–target interactions are either mediocre or rely heavily on data stacking. In this work, we proposed our model named GraphMS. We merged heterogeneous graph information and obtained effective node information and substructure information based on mutual information in graph embeddings. We then learned high quality representations for downstream tasks, and proposed an end–to–end auto–encoder model to complete the task of link prediction. Experimental results show that our method outperforms several state–of–the–art models. The model can achieve the area under the receiver operating characteristics (AUROC) curve of 0.959 and area under the precise recall curve (AUPR) of 0.847. We found that the mutual information between the substructure and graph–level representations contributes most to the mutual information index in a relatively sparse network. And the mutual information between the node–level and graph–level representations contributes most in a relatively dense network.

Sign in / Sign up

Export Citation Format

Share Document