Continual representation learning for evolving biomedical bipartite networks

2021 ◽  
Author(s):  
Kishlay Jha ◽  
Guangxu Xun ◽  
Aidong Zhang
Keyword(s):  
Network Structure ◽  
Learning Strategy ◽  
Structure Learning ◽  
Fundamental Problem ◽  
Representation Learning ◽  
Research Area ◽  
Bipartite Network ◽  
Bipartite Networks ◽  
Straightforward Application ◽  
Low Dimensional

Abstract Motivation Many real-world biomedical interactions such as ‘gene-disease’, ‘disease-symptom’ and ‘drug-target’ are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. Results In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach.

MVGCN: data integration through multi-view graph convolutional network for predicting links in biomedical bipartite networks

2021 ◽  
Author(s):  
Haitao Fu ◽  
Feng Huang ◽  
Xuan Liu ◽  
Yang Qiu ◽  
Wen Zhang
Keyword(s):  
Molecular Mechanisms ◽  
Learning Strategy ◽  
Information Aggregation ◽  
Supplementary Information ◽  
Bipartite Network ◽  
Bipartite Networks ◽  
Biomolecular Systems ◽  
Convolutional Network ◽  
Benchmark Datasets ◽  
Node Attributes

Abstract Motivation There are various interaction/association bipartite networks in biomolecular systems. Identifying unobserved links in biomedical bipartite networks helps to understand the underlying molecular mechanisms of human complex diseases and thus benefits the diagnosis and treatment of diseases. Although a great number of computational methods have been proposed to predict links in biomedical bipartite networks, most of them heavily depend on features and structures involving the bioentities in one specific bipartite network, which limits the generalization capacity of applying the models to other bipartite networks. Meanwhile, bioentities usually have multiple features, and how to leverage them has also been challenging. Results In this study, we propose a novel multi-view graph convolution network (MVGCN) framework for link prediction in biomedical bipartite networks. We first construct a multi-view heterogeneous network (MVHN) by combining the similarity networks with the biomedical bipartite network, and then perform a self-supervised learning strategy on the bipartite network to obtain node attributes as initial embeddings. Further, a neighborhood information aggregation (NIA) layer is designed for iteratively updating the embeddings of nodes by aggregating information from inter- and intra-domain neighbors in every view of the MVHN. Next, we combine embeddings of multiple NIA layers in each view, and integrate multiple views to obtain the final node embeddings, which are then fed into a discriminator to predict the existence of links. Extensive experiments show MVGCN performs better than or on par with baseline methods and has the generalization capacity on six benchmark datasets involving three typical tasks. Availability and implementation Source code and data can be downloaded from https://github.com/fuhaitao95/MVGCN. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Bayesian Network Structure Learning with Integer Programming: Polytopes, Facets and Complexity

2017 ◽  
Vol 58 ◽  
pp. 185-229 ◽  
Author(s):  
James Cussens ◽  
Matti Järvisalo ◽  
Janne H. Korhonen ◽  
Mark Bartlett
Keyword(s):  
Integer Programming ◽  
Bayesian Network ◽  
Graphical Models ◽  
Network Structure ◽  
Structure Learning ◽  
Theoretical Perspective ◽  
Separation Problem ◽  
Bayesian Network Structure ◽  
Bayesian Network Structure Learning ◽  
Low Dimensional

The challenging task of learning structures of probabilistic graphical models is an important problem within modern AI research. Recent years have witnessed several major algorithmic advances in structure learning for Bayesian networks - arguably the most central class of graphical models - especially in what is known as the score-based setting. A successful generic approach to optimal Bayesian network structure learning (BNSL), based on integer programming (IP), is implemented in the GOBNILP system. Despite the recent algorithmic advances, current understanding of foundational aspects underlying the IP based approach to BNSL is still somewhat lacking. Understanding fundamental aspects of cutting planes and the related separation problem is important not only from a purely theoretical perspective, but also since it holds out the promise of further improving the efficiency of state-of-the-art approaches to solving BNSL exactly. In this paper, we make several theoretical contributions towards these goals: (i) we study the computational complexity of the separation problem, proving that the problem is NP-hard; (ii) we formalise and analyse the relationship between three key polytopes underlying the IP-based approach to BNSL; (iii) we study the facets of the three polytopes both from the theoretical and practical perspective, providing, via exhaustive computation, a complete enumeration of facets for low-dimensional family-variable polytopes; and, furthermore, (iv) we establish a tight connection of the BNSL problem to the acyclic subgraph problem.

Identifying key players in bipartite networks

2020 ◽  
Vol 8 (1) ◽  
pp. 42-61
Author(s):  
Scott W. Duxbury
Keyword(s):  
Network Structure ◽  
The Other ◽  
Centrality Measures ◽  
Bipartite Network ◽  
Bipartite Networks ◽  
Key Players ◽  
Two Measures ◽  
The One

AbstractMeasures of bipartite network structure have recently gained attention from network scholars. However, there is currently no measure for identifying key players in two-mode networks. This article proposes measures for identifying key players in bipartite networks. It focuses on two measures: fragmentation and cohesion centrality. It extends the centrality measures to bipartite networks by considering (1) cohesion and fragmentation centrality within a one-mode projection, (2) cross-modal cohesion and fragmentation centrality, where a node in one mode is influential in the one-mode projection of the other mode, and (3) cohesion and fragmentation centrality across the entire bipartite structure. Empirical examples are provided for the Southern Women’s data and on the Ndrangheta mafia data.

scholarly journals ANRL: Attributed Network Representation Learning via Deep Neural Networks

2018 ◽  
Author(s):  
Zhen Zhang ◽  
Hongxia Yang ◽  
Jiajun Bu ◽  
Sheng Zhou ◽  
Pinggang Yu ◽  
...  
Keyword(s):  
Network Structure ◽  
Link Prediction ◽  
Deep Neural Networks ◽  
User Behavior ◽  
Representation Learning ◽  
Network Representation ◽  
Node Attribute ◽  
Attributed Network ◽  
Attribute Information ◽  
Low Dimensional

Network representation learning (RL) aims to transform the nodes in a network into low-dimensional vector spaces while preserving the inherent properties of the network. Though network RL has been intensively studied, most existing works focus on either network structure or node attribute information. In this paper, we propose a novel framework, named ANRL, to incorporate both the network structure and node attribute information in a principled way. Specifically, we propose a neighbor enhancement autoencoder to model the node attribute information, which reconstructs its target neighbors instead of itself. To capture the network structure, attribute-aware skip-gram model is designed based on the attribute encoder to formulate the correlations between each node and its direct or indirect neighbors. We conduct extensive experiments on six real-world networks, including two social networks, two citation networks and two user behavior networks. The results empirically show that ANRL can achieve relatively significant gains in node classification and link prediction tasks.

A performative network theory of attitudes

2020 ◽  
Author(s):  
Michael Quayle
Keyword(s):  
Attitude Change ◽  
Network Structure ◽  
Network Theory ◽  
Social Group ◽  
Group Structure ◽  
Social Identities ◽  
Bipartite Network ◽  
Identity Change ◽  
Multilayer Network ◽  
Dynamic Phenomena

In this paper I propose a network theory of attitudes where attitude agreements and disagreements forge a multilayer network structure that simultaneously binds people into groups (via attitudes) and attitudes into clusters (via people who share them). This theory proposes that people have a range of possible attitudes (like cards in a hand) but these only become meaningful when expressed (like a card played). Attitudes are expressed with sensitivity to their potential audiences and are socially performative: when we express attitudes, or respond to those expressed by others, we tell people who we are, what groups we might belong to and what to think of us. Agreement and disagreement can be modelled as a bipartite network that provides a psychological basis for perceived ingroup similarity and outgroup difference and, more abstractly, group identity. Opinion-based groups and group-related opinions are therefore co-emergent dynamic phenomena. Dynamic fixing occurs when particular attitudes become associated with specific social identities. The theory provides a framework for understanding identity ecosystems in which social group structure and attitudes are co-constituted. The theory describes how attitude change is also identity change. This has broad relevance across disciplines and applications concerned with social influence and attitude change.

scholarly journals Modelling community structure and temporal spreading on complex networks

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Vesa Kuikka
Keyword(s):  
Community Structure ◽  
Complex Networks ◽  
Community Detection ◽  
Network Structure ◽  
Network Connectivity ◽  
Network Models ◽  
Building Blocks ◽  
Detection Algorithm ◽  
Research Area ◽  
Detection Methods

AbstractWe present methods for analysing hierarchical and overlapping community structure and spreading phenomena on complex networks. Different models can be developed for describing static connectivity or dynamical processes on a network topology. In this study, classical network connectivity and influence spreading models are used as examples for network models. Analysis of results is based on a probability matrix describing interactions between all pairs of nodes in the network. One popular research area has been detecting communities and their structure in complex networks. The community detection method of this study is based on optimising a quality function calculated from the probability matrix. The same method is proposed for detecting underlying groups of nodes that are building blocks of different sub-communities in the network structure. We present different quantitative measures for comparing and ranking solutions of the community detection algorithm. These measures describe properties of sub-communities: strength of a community, probability of formation and robustness of composition. The main contribution of this study is proposing a common methodology for analysing network structure and dynamics on complex networks. We illustrate the community detection methods with two small network topologies. In the case of network spreading models, time development of spreading in the network can be studied. Two different temporal spreading distributions demonstrate the methods with three real-world social networks of different sizes. The Poisson distribution describes a random response time and the e-mail forwarding distribution describes a process of receiving and forwarding messages.

scholarly journals Low Dimensional State Representation Learning with Reward-shaped Priors

2021 ◽  
Author(s):  
Nicolo Botteghi ◽  
Ruben Obbink ◽  
Daan Geijs ◽  
Mannes Poel ◽  
Beril Sirmacek ◽  
...  
Keyword(s):  
Representation Learning ◽  
State Representation ◽  
Low Dimensional

scholarly journals Community Detection Based on Graph Representation Learning in Evolutionary Networks

2021 ◽  
Vol 11 (10) ◽  
pp. 4497
Author(s):  
Dongming Chen ◽  
Mingshuo Nie ◽  
Jie Wang ◽  
Yun Kong ◽  
Dongqi Wang ◽  
...  
Keyword(s):  
Community Detection ◽  
Network Structure ◽  
Clustering Algorithm ◽  
Laplacian Matrix ◽  
Representation Learning ◽  
Detection Algorithm ◽  
Graph Representation ◽  
Time Slice ◽  
Current Time ◽  
Evolutionary Networks

Aiming at analyzing the temporal structures in evolutionary networks, we propose a community detection algorithm based on graph representation learning. The proposed algorithm employs a Laplacian matrix to obtain the node relationship information of the directly connected edges of the network structure at the previous time slice, the deep sparse autoencoder learns to represent the network structure under the current time slice, and the K-means clustering algorithm is used to partition the low-dimensional feature matrix of the network structure under the current time slice into communities. Experiments on three real datasets show that the proposed algorithm outperformed the baselines regarding effectiveness and feasibility.

Sign in / Sign up

Export Citation Format

Share Document