scholarly journals Structural Patterns and Generative Models of Real-world Hypergraphs

2020 ◽  
Author(s):  
Manh Tuan Do ◽  
Se-eun Yoon ◽  
Bryan Hooi ◽  
Kijung Shin
Keyword(s):  
Real World ◽  
Generative Models ◽  
Structural Patterns

scholarly journals Link Prediction through Deep Generative Model

2018 ◽  
Author(s):  
Xu-Wen Wang ◽  
Yize Chen ◽  
Yang-Yu Liu
Keyword(s):  
Complex Networks ◽  
Real World ◽  
Link Prediction ◽  
Prediction Method ◽  
Generative Models ◽  
Generative Model ◽  
Superior Performance ◽  
Prediction Problem ◽  
Structural Patterns ◽  
Domain Specific

AbstractInferring missing links or predicting future ones based on the currently observed network is known as link prediction, which has tremendous real-world applications in biomedicine1–3, e-commerce4, social media5 and criminal intelligence6. Numerous methods have been proposed to solve the link prediction problem7–9. Yet, many of these existing methods are designed for undirected networks only. Moreover, most methods are based on domain-specific heuristics10, and hence their performances differ greatly for networks from different domains. Here we developed a new link prediction method based on deep generative models11 in machine learning. This method does not rely on any domain-specific heuristic and works for general undirected or directed complex networks. Our key idea is to represent the adjacency matrix of a network as an image and then learn hierarchical feature representations of the image by training a deep generative model. Those features correspond to structural patterns in the network at different scales, from small subgraphs to mesoscopic communities12. Conceptually, taking into account structural patterns at different scales all together should outperform any domain-specific heuristics that typically focus on structural patterns at a particular scale. Indeed, when applied to various real-world networks from different domains13–17, our method shows overall superior performance against existing methods. Moreover, it can be easily parallelized by splitting a large network into several small subnetworks and then perform link prediction for each subnetwork in parallel. Our results imply that deep learning techniques can be effectively applied to complex networks and solve the classical link prediction problem with robust and superior performance.SummaryWe propose a new link prediction method based on deep generative models.

scholarly journals Curriculum Learning for Natural Answer Generation

2018 ◽  
Author(s):  
Cao Liu ◽  
Shizhu He ◽  
Kang Liu ◽  
Jun Zhao
Keyword(s):  
Full Advantage ◽  
Real World ◽  
Large Scale ◽  
Question Answering ◽  
Generative Models ◽  
The Internet ◽  
Basic Model ◽  
The Arts ◽  
Learning Data

By reason of being able to obtain natural language responses, natural answers are more favored in real-world Question Answering (QA) systems. Generative models learn to automatically generate natural answers from large-scale question answer pairs (QA-pairs). However, they are suffering from the uncontrollable and uneven quality of QA-pairs crawled from the Internet. To address this problem, we propose a curriculum learning based framework for natural answer generation (CL-NAG), which is able to take full advantage of the valuable learning data from a noisy and uneven-quality corpus. Specifically, we employ two practical measures to automatically measure the quality (complexity) of QA-pairs. Based on the measurements, CL-NAG firstly utilizes simple and low-quality QA-pairs to learn a basic model, and then gradually learns to produce better answers with richer contents and more complete syntaxes based on more complex and higher-quality QA-pairs. In this way, all valuable information in the noisy and uneven-quality corpus could be fully exploited. Experiments demonstrate that CL-NAG outperforms the state-of-the-arts, which increases 6.8% and 8.7% in the accuracy for simple and complex questions, respectively.

Detecting communities in networks using a Bayesian nonparametric method

2014 ◽  
Vol 28 (28) ◽  
pp. 1450199
Author(s):  
Shengze Hu ◽  
Zhenwen Wang
Keyword(s):  
Community Structure ◽  
Community Detection ◽  
Real World ◽  
Detection Method ◽  
Generative Models ◽  
Detection Methods ◽  
Model Parameters ◽  
Nonparametric Method ◽  
Bayesian Nonparametric ◽  
New Community

In the real world, a large amount of systems can be described by networks where nodes represent entities and edges the interconnections between them. Community structure in networks is one of the interesting properties revealed in the study of networks. Many methods have been developed to extract communities from networks using the generative models which give the probability of generating networks based on some assumption about the communities. However, many generative models require setting the number of communities in the network. The methods based on such models are lack of practicality, because the number of communities is unknown before determining the communities. In this paper, the Bayesian nonparametric method is used to develop a new community detection method. First, a generative model is built to give the probability of generating the network and its communities. Next, the model parameters and the number of communities are calculated by fitting the model to the actual network. Finally, the communities in the network can be determined using the model parameters. In the experiments, we apply the proposed method to the synthetic and real-world networks, comparing with some other community detection methods. The experimental results show that the proposed method is efficient to detect communities in networks.

scholarly journals Weakly Supervised Disentanglement by Pairwise Similarities

2020 ◽  
Vol 34 (04) ◽  
pp. 3495-3502 ◽  
Author(s):  
Junxiang Chen ◽  
Kayhan Batmanghelich
Keyword(s):  
Real World ◽  
Latent Variables ◽  
Generative Models ◽  
Experimental Results ◽  
New Method ◽  
Weak Supervision ◽  
Real World Problem ◽  
Variational Autoencoder ◽  
Weakly Supervised

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered (Locatello et al. 2018). Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.

scholarly journals Discovering simple heuristics from mental simulation

2017 ◽  
Author(s):  
Frederick Callaway ◽  
Jessica Hamrick ◽  
Tom Griffiths
Keyword(s):  
Cognitive Science ◽  
Real World ◽  
Mental Simulation ◽  
Generative Models ◽  
The Other ◽  
Wide Range ◽  
The World ◽  
History Of ◽  
Simple Heuristics ◽  
Relevant Outcome

In the history of cognitive science, there have been two competing philosophies regarding how people reason about the world. In one, people rely on rich, generative models to make predictions about a wide range of scenarios; while in the other, people have a large “bag of tricks”, idiosyncratic heuristics that tend to work well in practice. In this paper, we suggest that rather than being in opposition to one another, these two ideas complement each other. We argue that people’s capacity for mental simulation may support their ability to learn new cue- based heuristics, and demonstrate this phenomenon in two experiments. However, our results also indicate that participants are far less likely to learn a heuristic when there is no logical or explicitly conveyed relationship between the cue and the relevant outcome. Furthermore, simulation—while a potentially useful tool—is no substitute for real world experience.

Synthesizing Designs With Interpart Dependencies Using Hierarchical Generative Adversarial Networks

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Wei Chen ◽  
Mark Fuge
Keyword(s):  
Constraint Satisfaction ◽  
Real World ◽  
Generative Models ◽  
Dependency Graph ◽  
Generative Adversarial Networks ◽  
Engineering Systems ◽  
Adversarial Networks ◽  
Latent Space ◽  
Branching Factor ◽  
Low Dimensional

Abstract Real-world designs usually consist of parts with interpart dependencies, i.e., the geometry of one part is dependent on one or multiple other parts. We can represent such dependency in a part dependency graph. This paper presents a method for synthesizing these types of hierarchical designs using generative models learned from examples. It decomposes the problem of synthesizing the whole design into synthesizing each part separately but keeping the interpart dependencies satisfied. Specifically, this method constructs multiple generative models, the interaction of which is based on the part dependency graph. We then use the trained generative models to synthesize or explore each part design separately via a low-dimensional latent representation, conditioned on the corresponding parent part(s). We verify our model on multiple design examples with different interpart dependencies. We evaluate our model by analyzing the constraint satisfaction performance, the synthesis quality, the latent space quality, and the effects of part dependency depth and branching factor. This paper’s techniques for capturing dependencies among parts lay the foundation for learned generative models to extend to more realistic engineering systems where such relationships are widespread.

Synthesizing Designs With Inter-Part Dependencies Using Hierarchical Generative Adversarial Networks

2018 ◽  
Author(s):  
Wei Chen ◽  
Ashwin Jeyaseelan ◽  
Mark Fuge
Keyword(s):  
Real World ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Design Exploration ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Latent Space ◽  
Latent Representations

Real-world designs usually consist of parts with hierarchical dependencies, i.e., the geometry of one component (a child shape) is dependent on another (a parent shape). We propose a method for synthesizing this type of design. It decomposes the problem of synthesizing the whole design into synthesizing each component separately but keeping the inter-component dependencies satisfied. This method constructs a two-level generative adversarial network to train two generative models for parent and child shapes, respectively. We then use the trained generative models to synthesize or explore parent and child shapes separately via a parent latent representation and infinite child latent representations, each conditioned on a parent shape. We evaluate and discuss the disentanglement and consistency of latent representations obtained by this method. We show that shapes change consistently along any direction in the latent space. This property is desirable for design exploration over the latent space.

scholarly journals Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254057
Author(s):  
Mark D. Humphries ◽  
Javier A. Caballero ◽  
Mat Evans ◽  
Silvia Maggi ◽  
Abhinav Singh
Keyword(s):  
Community Structure ◽  
Real World ◽  
Spectral Estimation ◽  
Null Model ◽  
Generative Models ◽  
Detection Methods ◽  
Dimensional Structure ◽  
Spectral Approach ◽  
Low Dimensional ◽  
Noise Nodes

Discovering low-dimensional structure in real-world networks requires a suitable null model that defines the absence of meaningful structure. Here we introduce a spectral approach for detecting a network’s low-dimensional structure, and the nodes that participate in it, using any null model. We use generative models to estimate the expected eigenvalue distribution under a specified null model, and then detect where the data network’s eigenspectra exceed the estimated bounds. On synthetic networks, this spectral estimation approach cleanly detects transitions between random and community structure, recovers the number and membership of communities, and removes noise nodes. On real networks spectral estimation finds either a significant fraction of noise nodes or no departure from a null model, in stark contrast to traditional community detection methods. Across all analyses, we find the choice of null model can strongly alter conclusions about the presence of network structure. Our spectral estimation approach is therefore a promising basis for detecting low-dimensional structure in real-world networks, or lack thereof.

scholarly journals Hypernetwork science via high-order hypergraph walks

2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Sinan G. Aksoy ◽  
Cliff Joslyn ◽  
Carlos Ortiz Marrero ◽  
Brenda Praggastis ◽  
Emilie Purvine
Keyword(s):  
Real World ◽  
Network Science ◽  
Generative Models ◽  
Closeness Centrality ◽  
High Order ◽  
Structured Data ◽  
Graph Distance ◽  
Connected Component ◽  
Generalize Graph ◽  
Clustering Coefficients

Abstract We propose high-order hypergraph walks as a framework to generalize graph-based network science techniques to hypergraphs. Edge incidence in hypergraphs is quantitative, yielding hypergraph walks with both length and width. Graph methods which then generalize to hypergraphs include connected component analyses, graph distance-based metrics such as closeness centrality, and motif-based measures such as clustering coefficients. We apply high-order analogs of these methods to real world hypernetworks, and show they reveal nuanced and interpretable structure that cannot be detected by graph-based methods. Lastly, we apply three generative models to the data and find that basic hypergraph properties, such as density and degree distributions, do not necessarily control these new structural measurements. Our work demonstrates how analyses of hypergraph-structured data are richer when utilizing tools tailored to capture hypergraph-native phenomena, and suggests one possible avenue towards that end.

scholarly journals A semi-parametric statistical test to compare complex networks

2019 ◽  
Vol 8 (2) ◽  
Author(s):  
Andre Fujita ◽  
Eduardo Silva Lira ◽  
Suzana de Siqueira Santos ◽  
Silvia Yumi Bando ◽  
Gabriela Eleuterio Soares ◽  
...  
Keyword(s):  
Complex Networks ◽  
Random Process ◽  
Real World ◽  
Regulatory Networks ◽  
Generative Models ◽  
Real World Data ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Functional Brain Networks ◽  
Parametric Statistical Test

Abstract The modelling of real-world data as complex networks is ubiquitous in several scientific fields, for example, in molecular biology, we study gene regulatory networks and protein–protein interaction (PPI)_networks; in neuroscience, we study functional brain networks; and in social science, we analyse social networks. In contrast to theoretical graphs, real-world networks are better modelled as realizations of a random process. Therefore, analyses using methods based on deterministic graphs may be inappropriate. For example, verifying the isomorphism between two graphs is of limited use to decide whether two (or more) real-world networks are generated from the same random process. To overcome this problem, in this article, we introduce a semi-parametric approach similar to the analysis of variance to test the equality of generative models of two or more complex networks. We measure the performance of the proposed statistic using Monte Carlo simulations and illustrate its usefulness by comparing PPI networks of six enteric pathogens.

Sign in / Sign up

Export Citation Format

Share Document