scholarly journals An Automorphic Distance Metric and Its Application to Node Embedding for Role Mining

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Víctor Martínez ◽  
Fernando Berzal ◽  
Juan-Carlos Cubero
Keyword(s):  
Equivalence Class ◽  
State Of The Art ◽  
Equivalence Classes ◽  
Network Node ◽  
Distance Metric ◽  
Role Mining ◽  
And Function ◽  
Vector Representations ◽  
Automorphic Equivalence ◽  
Node Embeddings

Role is a fundamental concept in the analysis of the behavior and function of interacting entities in complex networks. Role discovery is the task of uncovering the hidden roles of nodes within a network. Node roles are commonly defined in terms of equivalence classes. Two nodes have the same role if they fall within the same equivalence class. Automorphic equivalence, where two nodes are equivalent when they can swap their labels to form an isomorphic graph, captures this notion of role. The binary concept of equivalence is too restrictive, and nodes in real-world networks rarely belong to the same equivalence class. Instead, a relaxed definition in terms of similarity or distance is commonly used to compute the degree to which two nodes are equivalent. In this paper, we propose a novel distance metric called automorphic distance, which measures how far two nodes are from being automorphically equivalent. We also study its application to node embedding, showing how our metric can be used to generate role-preserving vector representations of nodes. Our experiments confirm that the proposed automorphic distance metric outperforms a state-of-the-art automorphic equivalence-based metric and different state-of-the-art techniques for the generation of node embeddings in different role-related tasks.

scholarly journals A Graphical Criterion for Effect Identification in Equivalence Classes of Causal Diagrams

2018 ◽  
Author(s):  
Amin Jaber ◽  
Jiji Zhang ◽  
Elias Bareinboim
Keyword(s):  
Observational Data ◽  
Equivalence Class ◽  
State Of The Art ◽  
Causal Structure ◽  
Learning Algorithms ◽  
Equivalence Classes ◽  
Data Driven ◽  
Current State ◽  
Causal Diagrams ◽  
Necessary And Sufficient

Computing the effects of interventions from observational data is an important task encountered in many data-driven sciences. The problem is addressed by identifying the post-interventional distribution with an expression that involves only quantities estimable from the pre-interventional distribution over observed variables, given some knowledge about the causal structure. In this work, we relax the requirement of having a fully specified causal structure and study the identifiability of effects with a singleton intervention (X), supposing that the structure is known only up to an equivalence class of causal diagrams, which is the output of standard structural learning algorithms (e.g., FCI). We derive a necessary and sufficient graphical criterion for the identifiability of the effect of X on all observed variables. We further establish a sufficient graphical criterion to identify the effect of X on a subset of the observed variables, and prove that it is strictly more powerful than the current state-of-the-art result on this problem.

scholarly journals RLC-GNN: An Improved Deep Architecture for Spatial-Based Graph Neural Network with Application to Fraud Detection

2021 ◽  
Vol 11 (12) ◽  
pp. 5656
Author(s):  
Yufan Zeng ◽  
Jiashan Tang
Keyword(s):  
Numerical Experiments ◽  
State Of The Art ◽  
Single Layer ◽  
Fraud Detection ◽  
Layer By Layer ◽  
Residual Structure ◽  
Detection Algorithms ◽  
Deep Architecture ◽  
Graph Neural Networks ◽  
Node Embeddings

Graph neural networks (GNNs) have been very successful at solving fraud detection tasks. The GNN-based detection algorithms learn node embeddings by aggregating neighboring information. Recently, CAmouflage-REsistant GNN (CARE-GNN) is proposed, and this algorithm achieves state-of-the-art results on fraud detection tasks by dealing with relation camouflages and feature camouflages. However, stacking multiple layers in a traditional way defined by hop leads to a rapid performance drop. As the single-layer CARE-GNN cannot extract more information to fix the potential mistakes, the performance heavily relies on the only one layer. In order to avoid the case of single-layer learning, in this paper, we consider a multi-layer architecture which can form a complementary relationship with residual structure. We propose an improved algorithm named Residual Layered CARE-GNN (RLC-GNN). The new algorithm learns layer by layer progressively and corrects mistakes continuously. We choose three metrics—recall, AUC, and F1-score—to evaluate proposed algorithm. Numerical experiments are conducted. We obtain up to 5.66%, 7.72%, and 9.09% improvements in recall, AUC, and F1-score, respectively, on Yelp dataset. Moreover, we also obtain up to 3.66%, 4.27%, and 3.25% improvements in the same three metrics on the Amazon dataset.

scholarly journals Significance of Mast Cell Formed Extracellular Traps in Microbial Defense

2021 ◽  
Author(s):  
Daniel Elieh Ali Komi ◽  
Wolfgang M. Kuebler
Keyword(s):  
State Of The Art ◽  
Extracellular Dna ◽  
Cellular Mechanisms ◽  
Extracellular Traps ◽  
Synthetic Chemicals ◽  
Dna Strands ◽  
Associated Proteins ◽  
Microbial Defense ◽  
And Function ◽  
Insight Into

AbstractMast cells (MCs) are critically involved in microbial defense by releasing antimicrobial peptides (such as cathelicidin LL-37 and defensins) and phagocytosis of microbes. In past years, it has become evident that in addition MCs may eliminate invading pathogens by ejection of web-like structures of DNA strands embedded with proteins known together as extracellular traps (ETs). Upon stimulation of resting MCs with various microorganisms, their products (including superantigens and toxins), or synthetic chemicals, MCs become activated and enter into a multistage process that includes disintegration of the nuclear membrane, release of chromatin into the cytoplasm, adhesion of cytoplasmic granules on the emerging DNA web, and ejection of the complex into the extracellular space. This so-called ETosis is often associated with cell death of the producing MC, and the type of stimulus potentially determines the ratio of surviving vs. killed MCs. Comparison of different microorganisms with specific elimination characteristics such as S pyogenes (eliminated by MCs only through extracellular mechanisms), S aureus (removed by phagocytosis), fungi, and parasites has revealed important aspects of MC extracellular trap (MCET) biology. Molecular studies identified that the formation of MCET depends on NADPH oxidase-generated reactive oxygen species (ROS). In this review, we summarize the present state-of-the-art on the biological relevance of MCETosis, and its underlying molecular and cellular mechanisms. We also provide an overview over the techniques used to study the structure and function of MCETs, including electron microscopy and fluorescence microscopy using specific monoclonal antibodies (mAbs) to detect MCET-associated proteins such as tryptase and histones, and cell-impermeant DNA dyes for labeling of extracellular DNA. Comparing the type and biofunction of further MCET decorating proteins with ETs produced by other immune cells may help provide a better insight into MCET biology in the pathogenesis of autoimmune and inflammatory disorders as well as microbial defense.

scholarly journals From Exosome Glycobiology to Exosome Glycotechnology, the Role of Natural Occurring Polysaccharides

2021 ◽  
Vol 2 (2) ◽  
pp. 311-338
Author(s):  
Giulia Della Rosa ◽  
Clarissa Ruggeri ◽  
Alessandra Aloisi
Keyword(s):  
State Of The Art ◽  
Cell Communication ◽  
Pathological Conditions ◽  
New Findings ◽  
Cell Type Specific ◽  
New Perspective ◽  
And Function ◽  
And Personalized Medicine ◽  
Innate Ability

Exosomes (EXOs) are nano-sized informative shuttles acting as endogenous mediators of cell-to-cell communication. Their innate ability to target specific cells and deliver functional cargo is recently claimed as a promising theranostic strategy. The glycan profile, actively involved in the EXO biogenesis, release, sorting and function, is highly cell type-specific and frequently altered in pathological conditions. Therefore, the modulation of EXO glyco-composition has recently been considered an attractive tool in the design of novel therapeutics. In addition to the available approaches involving conventional glyco-engineering, soft technology is becoming more and more attractive for better exploiting EXO glycan tasks and optimizing EXO delivery platforms. This review, first, explores the main functions of EXO glycans and associates the potential implications of the reported new findings across the nanomedicine applications. The state-of-the-art of the last decade concerning the role of natural polysaccharides—as targeting molecules and in 3D soft structure manufacture matrices—is then analysed and highlighted, as an advancing EXO biofunction toolkit. The promising results, integrating the biopolymers area to the EXO-based bio-nanofabrication and bio-nanotechnology field, lay the foundation for further investigation and offer a new perspective in drug delivery and personalized medicine progress.

scholarly journals Chi-Squared Distance Metric Learning for Histogram Data

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Wei Yang ◽  
Luhui Xu ◽  
Xiaopan Chen ◽  
Fengbin Zheng ◽  
Yang Liu
Keyword(s):  
Nearest Neighbor ◽  
State Of The Art ◽  
Metric Learning ◽  
Nearest Neighbors ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Projected Gradient Method ◽  
Proper Distance ◽  
Chi Squared ◽  
Real World Datasets

Learning a proper distance metric for histogram data plays a crucial role in many computer vision tasks. The chi-squared distance is a nonlinear metric and is widely used to compare histograms. In this paper, we show how to learn a general form of chi-squared distance based on the nearest neighbor model. In our method, the margin of sample is first defined with respect to the nearest hits (nearest neighbors from the same class) and the nearest misses (nearest neighbors from the different classes), and then the simplex-preserving linear transformation is trained by maximizing the margin while minimizing the distance between each sample and its nearest hits. With the iterative projected gradient method for optimization, we naturally introduce thel2,1norm regularization into the proposed method for sparse metric learning. Comparative studies with the state-of-the-art approaches on five real-world datasets verify the effectiveness of the proposed method.

scholarly journals Relevance-guided Supervision for OpenQA with ColBERT

2021 ◽  
Vol 9 ◽  
pp. 929-944
Author(s):  
Omar Khattab ◽  
Christopher Potts ◽  
Matei Zaharia
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Training Data ◽  
Coarse Grained ◽  
Retrieval Model ◽  
Open Domain ◽  
Weak Supervision ◽  
Fine Grained ◽  
Vector Representations ◽  
Large Corpus

Abstract Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned component that uses coarse-grained vector representations of questions and passages. We argue that this modeling choice is insufficiently expressive for dealing with the complexity of natural language questions. To address this, we define ColBERT-QA, which adapts the scalable neural retrieval model ColBERT to OpenQA. ColBERT creates fine-grained interactions between questions and passages. We propose an efficient weak supervision strategy that iteratively uses ColBERT to create its own training data. This greatly improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA, and the resulting system attains state-of-the-art extractive OpenQA performance on all three datasets.

scholarly journals MSA Transformer

2021 ◽  
Author(s):  
Roshan Rao ◽  
Jason Liu ◽  
Robert Verkuil ◽  
Joshua Meier ◽  
John F. Canny ◽  
...  
Keyword(s):  
Structure Learning ◽  
State Of The Art ◽  
Language Model ◽  
Language Modeling ◽  
Language Models ◽  
Multiple Sequence ◽  
Wide Margin ◽  
Current State ◽  
Individual Sequences ◽  
And Function

AbstractUnsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins. Protein language models studied to date have been trained to perform inference from individual sequences. The longstanding approach in computational biology has been to make inferences from a family of evolutionarily related sequences by fitting a model to each family independently. In this work we combine the two paradigms. We introduce a protein language model which takes as input a set of sequences in the form of a multiple sequence alignment. The model interleaves row and column attention across the input sequences and is trained with a variant of the masked language modeling objective across many protein families. The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models.

scholarly journals Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks

2019 ◽  
Vol 9 (18) ◽  
pp. 3908 ◽  
Author(s):  
Jintae Kim ◽  
Shinhyeok Oh ◽  
Oh-Woog Kwon ◽  
Harksoo Kim
Keyword(s):  
Performance Measures ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Generative Adversarial Networks ◽  
Training Method ◽  
Adversarial Networks ◽  
Proposed Model ◽  
Previous State ◽  
Vector Representations

To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without considering contextual importance. To mitigate this problem, we propose a multi-turn chatbot model in which previous utterances participate in response generation using different weights. The proposed model calculates the contextual importance of previous utterances by using an attention mechanism. In addition, we propose a training method that uses two types of Wasserstein generative adversarial networks to improve the quality of responses. In experiments with the DailyDialog dataset, the proposed model outperformed the previous state-of-the-art models based on various performance measures.

Sign in / Sign up

Export Citation Format

Share Document