scholarly journals Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning

2021 ◽  
Author(s):  
Shuoran Jiang ◽  
Qingcai Chen ◽  
Xin Liu ◽  
Baotian Hu ◽  
Lisai Zhang
Keyword(s):  
Chebyshev Approximation ◽  
High Order ◽  
Convolutional Network

scholarly journals Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge

2021 ◽  
Author(s):  
Shengqiong Wu ◽  
Hao Fei ◽  
Yafeng Ren ◽  
Donghong Ji ◽  
Jingye Li
Keyword(s):  
State Of The Art ◽  
Boundary Detection ◽  
High Order ◽  
Experimental Results ◽  
Convolutional Network ◽  
Syntactic Knowledge ◽  
Current State ◽  
Syntactic Features ◽  
Benchmark Datasets

In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion encoder for encoding syntactic features, including a label-aware graph convolutional network (LAGCN) for modeling the dependency edges and labels, as well as the POS tags unifiedly, and a local-attention module encoding POS tags for better term boundary detection. During pairing, we then adopt Biaffine and Triaffine scoring for high-order aspect-opinion term pairing, in the meantime re-harnessing the syntax-enriched representations in LAGCN for syntactic-aware scoring. Experimental results on four benchmark datasets demonstrate that our model outperforms current state-of-the-art baselines, meanwhile yielding explainable predictions with syntactic knowledge.

High-Order Joint Information Input For Graph Convolutional Network Based Action Recognition

2021 ◽  
Author(s):  
Wen-Nung Lie ◽  
Yong-Jhu Huang ◽  
Jui-Chiu Chiang ◽  
Zhen-Yu Fang
Keyword(s):  
Action Recognition ◽  
High Order ◽  
Convolutional Network ◽  
Information Input

scholarly journals Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Fangyuan Lei ◽  
Xun Liu ◽  
Zhengming Li ◽  
Qingyun Dai ◽  
Senhong Wang
Keyword(s):  
Computational Complexity ◽  
Information Fusion ◽  
Text Classification ◽  
State Of The Art ◽  
High Order ◽  
High Order Interaction ◽  
Convolutional Network ◽  
Graph Representations ◽  
Order Interaction ◽  
Different Order

Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.

scholarly journals Path Aggregation Model for Attributed Network Embedding with a Smart Random Walk

2021 ◽  
Vol 2082 (1) ◽  
pp. 012011
Author(s):  
Xiang Xiao ◽  
Kang Zhang ◽  
Shuang Qiu ◽  
Wei Liu
Keyword(s):  
Random Walk ◽  
High Order ◽  
Edge Weight ◽  
Task Graph ◽  
Network Embedding ◽  
Convolutional Network ◽  
Aggregation Model ◽  
Sample Paths ◽  
Attributed Network ◽  
Walk Algorithm

Abstract Network embedding has attracted a surge of attention recently. In this field, how to preserve high-order proximity has long been a difficult task. Graph convolutional network (GCN) and random walk-based approaches can preserve high-order proximity to a certain extent. However, they partially concentrate on the aggregation process and sampling process respectively. Path aggregation methods combine the merits of GCN and random walk, and thus can preserve more high-order information and achieve better performance. However, path aggregation framework has not been applied in attributed network embedding yet. In this paper, we propose a path aggregation model for attributed network embedding, with two main contributions. First, we claim that there always exists implicit edge weight in networks, and design a tweaked random walk algorithm to sample paths accordingly. Second, we propose a path aggregation framework dealing with both nodes and attributes. Extensive experimental results show that our proposal outperforms the cutting-edge baselines on downstream tasks, such as node clustering, node classification, and link prediction.

The Homotopy-Analysis Approach for the Dynamical Study of a Microbeam Modeled on the Basis of the Strain-Gradient Theory

2013 ◽  
Author(s):  
Pierpaolo Belardinelli ◽  
Stefano Lenci
Keyword(s):  
Strain Gradient ◽  
Nonlinear Partial Differential Equation ◽  
Gradient Elasticity ◽  
Chebyshev Approximation ◽  
High Order ◽  
Strain Gradient Theory ◽  
Gradient Theory ◽  
Nonlinear Phenomena ◽  
Dynamical Study ◽  
Homotopy Analysis

The purpose of this work is to investigate the nonlinear dynamics of a slender microbeam, modeled within the framework of the strain-gradient elasticity, adopting the homotopy analysis method (HAM). The microbeam is fixed at both edges and a geometric nonlinearity is also present accounting for the axial stretch. To attain an accurate and reliable model, so that the error is spread smoothly over the domain, a Chebyshev approximation for the nonlinear electric actuation term is introduced. A reduced-order model for the governing equation of motion, represented by an high-order nonlinear partial differential equation, is obtained. Then, the single-degree-of-freedom model is studied to find an analytical approximated solution. The free vibrations of the beam are investigated and the effects of several parameters, such as the applied axial load, are analyzed. Particular attention is also paid to find the influence of the high-order length scale material parameters, introduced by the non-classical theory, that progressively modify the oscillating behaviour. The results on the nonlinear phenomena, show both an hardening and a softening behaviour, in competition between them, varying the beam parameters. A numerical solution, obtained by a 4th order Runge Kutta algorithm, is also proposed as a benchmark for the analytical results.

Sign in / Sign up

Export Citation Format

Share Document