scholarly journals Local hypergraph clustering using capacity releasing diffusion

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0243485
Author(s):  
Rania Ibrahim ◽  
David F. Gleich
Keyword(s):  
Graph Clustering ◽  
Learning Task ◽  
Higher Order ◽  
Spectral Graph Theory ◽  
Clustering Technique ◽  
Clustering Quality ◽  
Connected Cluster ◽  
Local Graph ◽  
Synthetic Datasets ◽  
Better Than

Local graph clustering is an important machine learning task that aims to find a well-connected cluster near a set of seed nodes. Recent results have revealed that incorporating higher order information significantly enhances the results of graph clustering techniques. The majority of existing research in this area focuses on spectral graph theory-based techniques. However, an alternative perspective on local graph clustering arises from using max-flow and min-cut on the objectives, which offer distinctly different guarantees. For instance, a new method called capacity releasing diffusion (CRD) was recently proposed and shown to preserve local structure around the seeds better than spectral methods. The method was also the first local clustering technique that is not subject to the quadratic Cheeger inequality by assuming a good cluster near the seed nodes. In this paper, we propose a local hypergraph clustering technique called hypergraph CRD (HG-CRD) by extending the CRD process to cluster based on higher order patterns, encoded as hyperedges of a hypergraph. Moreover, we theoretically show that HG-CRD gives results about a quantity called motif conductance, rather than a biased version used in previous experiments. Experimental results on synthetic datasets and real world graphs show that HG-CRD enhances the clustering quality.

On analyzing graphs with motif-paths

2021 ◽  
Vol 14 (6) ◽  
pp. 1111-1123
Author(s):  
Xiaodong Li ◽  
Reynold Cheng ◽  
Kevin Chen-Chuan Chang ◽  
Caihua Shan ◽  
Chenhao Ma ◽  
...  
Keyword(s):  
Link Prediction ◽  
Graph Clustering ◽  
Order Structure ◽  
Graph Analysis ◽  
High Order Structure ◽  
Node Ranking ◽  
Local Graph ◽  
Edge Based ◽  
Graph Motif ◽  
Better Than

Path-based solutions have been shown to be useful for various graph analysis tasks, such as link prediction and graph clustering. However, they are no longer adequate for handling complex and gigantic graphs. Recently, motif-based analysis has attracted a lot of attention. A motif, or a small graph with a few nodes, is often considered as a fundamental unit of a graph. Motif-based analysis captures high-order structure between nodes, and performs better than traditional "edge-based" solutions. In this paper, we study motif-path , which is conceptually a concatenation of one or more motif instances. We examine how motif-paths can be used in three path-based mining tasks, namely link prediction, local graph clustering and node ranking. We further address the situation when two graph nodes are not connected through a motif-path, and develop a novel defragmentation method to enhance it. Experimental results on real graph datasets demonstrate the use of motif-paths and defragmentation techniques improves graph analysis effectiveness.

scholarly journals Hyperspectral Image Classification with Localized Graph Convolutional Filtering

2021 ◽  
Vol 13 (3) ◽  
pp. 526
Author(s):  
Shengliang Pu ◽  
Yuanfeng Wu ◽  
Xu Sun ◽  
Xiaotong Sun
Keyword(s):  
Hyperspectral Image ◽  
Principal Component ◽  
Representation Learning ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Spectral Graph Theory ◽  
Feature Reduction ◽  
Graph Representation ◽  
Novel Method ◽  
Local Graph

The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors.

scholarly journals Local Graph Clustering with Network Lasso

2020 ◽  
pp. 1-1
Author(s):  
Alexander Jung ◽  
Yasmin Sarcheshmehpour
Keyword(s):  
Graph Clustering ◽  
Local Graph

scholarly journals Another bilingual advantage? Perception of talker-voice information

2017 ◽  
Vol 21 (3) ◽  
pp. 523-536 ◽  
Author(s):  
SUSANNAH V. LEVI
Keyword(s):  
Learning Task ◽  
Bilingual Children ◽  
Social Aspect ◽  
Older Children ◽  
Bilingual Advantage ◽  
Bilingual Speakers ◽  
Social Tasks ◽  
Processing Information ◽  
Voice Processing ◽  
Better Than

A bilingual advantage has been found in both cognitive and social tasks. In the current study, we examine whether there is a bilingual advantage in how children process information about who is talking (talker-voice information). Younger and older groups of monolingual and bilingual children completed the following talker-voice tasks with bilingual speakers: a discrimination task in English and German (an unfamiliar language), and a talker-voice learning task in which they learned to identify the voices of three unfamiliar speakers in English. Results revealed effects of age and bilingual status. Across the tasks, older children performed better than younger children and bilingual children performed better than monolingual children. Improved talker-voice processing by the bilingual children suggests that a bilingual advantage exists in a social aspect of speech perception, where the focus is not on processing the linguistic information in the signal, but instead on processing information about who is talking.

scholarly journals Consolidation of reward memory during sleep does not require dopaminergic activation

2019 ◽  
Author(s):  
M Alizadeh Asfestani ◽  
V Brechtmann ◽  
J Santiago ◽  
J Born ◽  
GB Feld
Keyword(s):  
Learning Task ◽  
Reward Learning ◽  
Nocturnal Sleep ◽  
Double Blind ◽  
Dopaminergic Neurotransmission ◽  
Long Duration ◽  
Differential Retention ◽  
Better Than ◽  
Dopaminergic Activation

AbstractSleep enhances memories, especially, if they are related to future rewards. Although dopamine has been shown to be a key determinant during reward learning, the role of dopaminergic neurotransmission for amplifying reward-related memories during sleep remains unclear. In the present study, we scrutinize the idea that dopamine is needed for the preferential consolidation of rewarded information. We blocked dopaminergic neurotransmission, thereby aiming to wipe out preferential sleep-dependent consolidation of high over low rewarded memories during sleep. Following a double-blind, balanced, crossover design 20 young healthy men received the dopamine d2-like receptor blocker Sulpiride (800 mg) or placebo, after learning a Motivated Learning Task. The task required participants to memorize 80 highly and 80 lowly rewarded pictures. Half of them were presented for a short (750 ms) and a long duration (1500 ms), respectively, which enabled to dissociate effects of reward on sleep-associated consolidation from those of mere encoding depth. Retrieval was tested after a retention interval of 20 h that included 8 h of nocturnal sleep. As expected, at retrieval, highly rewarded memories were remembered better than lowly rewarded memories, under placebo. However, there was no evidence for an effect of blocking dopaminergic neurotransmission with Sulpiride during sleep on this differential retention of rewarded information. This result indicates that dopaminergic activation is not required for the preferential consolidation of reward-associated memory. Rather it appears that dopaminergic activation only tags such memories at encoding for intensified reprocessing during sleep.

scholarly journals Consolidation of Reward Memory during Sleep Does Not Require Dopaminergic Activation

2020 ◽  
Vol 32 (9) ◽  
pp. 1688-1703 ◽  
Author(s):  
Marjan Alizadeh Asfestani ◽  
Valentin Brechtmann ◽  
João Santiago ◽  
Andreas Peter ◽  
Jan Born ◽  
...  
Keyword(s):  
Learning Task ◽  
Reward Learning ◽  
Nocturnal Sleep ◽  
Double Blind ◽  
Dopaminergic Neurotransmission ◽  
Msec Duration ◽  
Differential Retention ◽  
Better Than ◽  
Dopaminergic Activation

Sleep enhances memories, especially if they are related to future rewards. Although dopamine has been shown to be a key determinant during reward learning, the role of dopaminergic neurotransmission for amplifying reward-related memories during sleep remains unclear. In this study, we scrutinize the idea that dopamine is needed for the preferential consolidation of rewarded information. We impaired dopaminergic neurotransmission, thereby aiming to wipe out preferential sleep-dependent consolidation of high- over low-rewarded memories during sleep. Following a double-blind, balanced, crossover design, 17 young healthy men received the dopamine d2-like receptor blocker sulpiride (800 mg) or placebo, after learning a motivated learning task. The task required participants to memorize 80 highly and 80 lowly rewarded pictures. Half of them were presented for a short (750 msec) and a long (1500 msec) duration, respectively, which permitted dissociation of the effects of reward on sleep-associated consolidation from those of mere encoding depth. Retrieval was tested after a retention interval of approximately 22 hr that included 8 hr of nocturnal sleep. As expected, at retrieval, highly rewarded memories were remembered better than lowly rewarded memories, under placebo. However, there was no evidence for an effect of reducing dopaminergic neurotransmission with sulpiride during sleep on this differential retention of rewarded information. This result indicates that dopaminergic activation likely is not required for the preferential consolidation of reward-associated memory. Rather, it appears that dopaminergic activation only tags such memories at encoding for intensified reprocessing during sleep.

SAS Nonlinear Models or Artificial Higher Order Neural Network Nonlinear Models?

2021 ◽  
pp. 174-217
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Analysis ◽  
Learning Algorithm ◽  
Nonlinear Models ◽  
Higher Order ◽  
Model Order ◽  
Higher Order Neural Networks ◽  
Parameter Values ◽  
Better Than

This chapter delivers general format of higher order neural networks (HONNs) for nonlinear data analysis and six different HONN models. Then, this chapter mathematically proves that HONN models could converge and have mean squared errors close to zero. Moreover, this chapter illustrates the learning algorithm with update formulas. HONN models are compared with SAS nonlinear (NLIN) models, and results show that HONN models are 3 to 12% better than SAS nonlinear models. Finally, this chapter shows how to use HONN models to find the best model, order, and coefficients without writing the regression expression, declaring parameter names, and supplying initial parameter values.

scholarly journals Functional geometry of protein interactomes

2019 ◽  
Vol 35 (19) ◽  
pp. 3727-3734 ◽  
Author(s):  
Noël Malod-Dognin ◽  
Nataša Pržulj
Keyword(s):  
Functional Organization ◽  
Protein Complexes ◽  
Simplicial Complexes ◽  
Higher Order ◽  
Biological Information ◽  
Supplementary Information ◽  
Data Types ◽  
Ppi Networks ◽  
Functional Geometry ◽  
Better Than

Abstract Motivation Protein–protein interactions (PPIs) are usually modeled as networks. These networks have extensively been studied using graphlets, small induced subgraphs capturing the local wiring patterns around nodes in networks. They revealed that proteins involved in similar functions tend to be similarly wired. However, such simple models can only represent pairwise relationships and cannot fully capture the higher-order organization of protein interactomes, including protein complexes. Results To model the multi-scale organization of these complex biological systems, we utilize simplicial complexes from computational geometry. The question is how to mine these new representations of protein interactomes to reveal additional biological information. To address this, we define simplets, a generalization of graphlets to simplicial complexes. By using simplets, we define a sensitive measure of similarity between simplicial complex representations that allows for clustering them according to their data types better than clustering them by using other state-of-the-art measures, e.g. spectral distance, or facet distribution distance. We model human and baker’s yeast protein interactomes as simplicial complexes that capture PPIs and protein complexes as simplices. On these models, we show that our newly introduced simplet-based methods cluster proteins by function better than the clustering methods that use the standard PPI networks, uncovering the new underlying functional organization of the cell. We demonstrate the existence of the functional geometry in the protein interactome data and the superiority of our simplet-based methods to effectively mine for new biological information hidden in the complexity of the higher-order organization of protein interactomes. Availability and implementation Codes and datasets are freely available at http://www0.cs.ucl.ac.uk/staff/natasa/Simplets/. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document