High-order Associations Research Articles

… thanks to high-order associations

L’Associationnisme Radical Unifié proposé par Arnaud Rey pose la question de la compréhension de la cognition complexe en termes d’apprentissage associatif au niveau des synapses. Mais les associations sont-elles des formes de connaissance suffisantes pour rendre compte du traitement complexe de l’information ? La cognition complexe, telle que la compréhension du langage ou le choix d’un comportement, s’appuierait sur des probabilités de transition par paire qui peuvent être apprises grâce à des règles d’apprentissage de type Hebbien. Les architectures de réseaux corticaux intégrant des matrices d’associations par paires se sont avérées efficaces pour rendre compte d’une riche phénoménologie des processus cognitifs, conformément à l’associationnisme radical unifié proposé par Arnaud Rey, selon lequel la cognition peut être expliquée par le fonctionnement de vastes réseaux de connaissances structurés par des associations, elles-mêmes apprises par une règle de type Hebbien. Cependant, certaines formes de connaissances impliquent non seulement des paires mais aussi des schémas de plus de deux stimuli et/ou actions. Les réponses comportementales associées à un stimulus donné dépendent également d’autres stimuli, motivations et objectifs. Une telle activation dépendante du contexte nécessite l’apprentissage de relations d’ordre supérieur entre plus de deux éléments. Cela implique une probabilité transitoire de second ordre qui peut être apprise par des architectures profondes multicouches ainsi que par des réseaux corticaux récurrents moins structurés qui utilisent une règle d’apprentissage multisynaptique. Cette règle est biologiquement réaliste et compatible avec les principes d’apprentissage de Hebbien. Elle permet à un contexte de sélectionner dynamiquement un sous-ensemble de paires qui peuvent s’activer mutuellement parmi toutes les paires possibles. Elle permet alors d’expliquer comment des connaissances (quelque peu) complexes peuvent être apprises et traitées, soutenant ainsi l’Associationnisme Radical Unifié proposé par Arnaud Rey : « Les associations sont tout ce dont nous avons besoin » …grâce aux associations d’ordre supérieur.

DSAMR: Dual-Stream Attention Multi-hop Reasoning for knowledge-based visual question answering

Knowledge-based visual question answering aims to associate external knowledge facts for answering questions about images. Most existing methods emphasize high-order associations between knowledge facts and questions, and fail to consider the negative effects of unnecessary knowledge facts in multi-hop reasoning. In this paper, we propose a Dual-Stream Attention Multi-hop Reasoning (DSAMR) architecture that constructs two different attention streams to mitigate unnecessary knowledge facts. This dual-stream mechanism enables the model to reduce the attention weights on unnecessary knowledge while gathering essential knowledge by learning the implicit correlations between knowledge facts and questions. In addition, we designed a hypergraph knowledge extraction module in the architecture to extract optimal knowledge facts by evaluating the relevance of each knowledge fact to the question. The experimental results demonstrate the effectiveness of our method not only on the knowledge-based visual question answering dataset KVQA, but also on the multi-hop question answering dataset PathQuestion.

Explainable and programmable hypergraph convolutional network for imaging genetics data fusion

Integrating multi-view information to gain a new understanding of complex disease like Alzheimer’s disease (AD) has great clinical value. Hypergraphs have unique advantages in modeling high-order associations, but current deep learning methods cannot fully utilize the structural information in hypergraphs and have limited application value due to the black-box nature. This paper improves the hypergraph learning in interpretability and programmability. Firstly, we fuse multi-view information by constructing brain region-gene hypergraphs. Secondly, a characteristic information aggregation model is constructed based on hypergraph structure, Finally, a characteristic information aggregation hypergraph convolutional network (CIA-HGCN) is proposed based on the idea of graph neural networks. Evaluated by clinical imaging genetics data, CIA-HGCN obtained accuracy of 88.3% in AD identification task and showed superior performance in characteristic extraction. This paper provides a practical and flexible deep learning method for AD research and clinical applications.

INFORMATION CONTENT OF HIGH-ORDER ASSOCIATIONS OF THE HUMAN GUT MICROBIOTA NETWORK.

The human gastrointestinal tract is an environment that hosts an ecosystem of microorganisms essential to human health. Vital biological processes emerge from fundamental inter- and intra-species molecular interactions that influence the assembly and composition of the gut microbiota ecology. Here we quantify the complexity of the ecological relationships within the human infant gut microbiota ecosystem as a function of the information contained in the nonlinear associations of a sequence of increasingly-specified maximum entropy representations of the system. Our paradigm frames the ecological state, in terms of the presence or absence of individual microbial ecological units that are identified by amplicon sequence variants (ASV) in the gut microenvironment, as a function of both the ecological states of its neighboring units and, in a departure from standard graphical model representations, the associations among the units within its neighborhood. We characterize the order of the system based on the relative quantity of statistical information encoded by high-order statistical associations of the infant gut microbiota.

A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity.

Brain connectivity alterations associated with mental disorders have been widely reported in both functional MRI (fMRI) and diffusion MRI (dMRI). However, extracting useful information from the vast amount of information afforded by brain networks remains a great challenge. Capturing network topology, graph convolutional networks (GCNs) have demonstrated to be superior in learning network representations tailored for identifying specific brain disorders. Existing graph construction techniques generally rely on a specific brain parcellation to define regions-of-interest (ROIs) to construct networks, often limiting the analysis into a single spatial scale. In addition, most methods focus on the pairwise relationships between the ROIs and ignore high-order associations between subjects. In this letter, we propose a mutual multi-scale triplet graph convolutional network (MMTGCN) to analyze functional and structural connectivity for brain disorder diagnosis. We first employ several templates with different scales of ROI parcellation to construct coarse-to-fine brain connectivity networks for each subject. Then, a triplet GCN (TGCN) module is developed to learn functional/structural representations of brain connectivity networks at each scale, with the triplet relationship among subjects explicitly incorporated into the learning process. Finally, we propose a template mutual learning strategy to train different scale TGCNs collaboratively for disease classification. Experimental results on 1,160 subjects from three datasets with fMRI or dMRI data demonstrate that our MMTGCN outperforms several state-of-the-art methods in identifying three types of brain disorders.

Cloud computing for detecting high-order genome-wide epistatic interaction via dynamic clustering

BackgroudTaking the advan tage of high-throughput single nucleotide polymorphism (SNP) genotyping technology, large genome-wide association studies (GWASs) have been considered to hold promise for unravelling complex relationships between genotype and phenotype. At present, traditional single-locus-based methods are insufficient to detect interactions consisting of multiple-locus, which are broadly existing in complex traits. In addition, statistic tests for high order epistatic interactions with more than 2 SNPs propose computational and analytical challenges because the computation increases exponentially as the cardinality of SNPs combinations gets larger.ResultsIn this paper, we provide a simple, fast and powerful method using dynamic clustering and cloud computing to detect genome-wide multi-locus epistatic interactions. We have constructed systematic experiments to compare powers performance against some recently proposed algorithms, including TEAM, SNPRuler, EDCF and BOOST. Furthermore, we have applied our method on two real GWAS datasets, Age-related macular degeneration (AMD) and Rheumatoid arthritis (RA) datasets, where we find some novel potential disease-related genetic factors which are not shown up in detections of 2-loci epistatic interactions.ConclusionsExperimental results on simulated data demonstrate that our method is more powerful than some recently proposed methods on both two- and three-locus disease models. Our method has discovered many novel high-order associations that are significantly enriched in cases from two real GWAS datasets. Moreover, the running time of the cloud implementation for our method on AMD dataset and RA dataset are roughly 2 hours and 50 hours on a cluster with forty small virtual machines for detecting two-locus interactions, respectively. Therefore, we believe that our method is suitable and effective for the full-scale analysis of multiple-locus epistatic interactions in GWAS.

Functional Imaging: Is the Resting Brain Resting?

It is often assumed that the human brain only becomes active to support overt behaviour. A new study challenges this concept by showing that multiple neural circuits are engaged even at rest. We highlight two complementary hypotheses which seek to explain the function of this resting activity.