Fei Liu

Fei Liu, Lexing Ying

This paper presents an efficient preconditioner for the Lippmann-Schwinger equation that combines the ideas of the sparsifying and the sweeping preconditioners. Following first the idea of the sparsifying preconditioner, this new preconditioner starts by transforming the dense linear system of the Lippmann-Schwinger equation into a nearly sparse system. The key novelty is a newly designed perfectly matched layer (PML) stencil for the boundary degrees of freedoms. The resulting sparse system gives rise to fairly accurate solutions and hence can be viewed as an accurate discretization of the Helmholtz equation. This new PML stencil also paves the way for applying the moving PML sweeping preconditioner to invert the resulting sparse system approximately. When combined with the standard GMRES solver, this new preconditioner for the Lippmann-Schwinger equation takes only a few iterations to converge for both 2D and 3D problems, where the iteration numbers are almost independent of the frequency. To the best of our knowledge, this is the first method that achieves near-linear cost to solve the 3D Lippmann-Schwinger equation in high frequency cases.

Rui Luo, Fei Liu, Wenhao Liang et al.

In the field of intelligent education, knowledge tracing (KT) has attracted increasing attention, which estimates and traces students' mastery of knowledge concepts to provide high-quality education. In KT, there are natural graph structures among questions and knowledge concepts so some studies explored the application of graph neural networks (GNNs) to improve the performance of the KT models which have not used graph structure. However, most of them ignored both the questions' difficulties and students' attempts at questions. Actually, questions with the same knowledge concepts have different difficulties, and students' different attempts also represent different knowledge mastery. In this paper, we propose a difficulty and attempts boosted graph-based KT (DAGKT), using rich information from students' records. Moreover, a novel method is designed to establish the question similarity relationship inspired by the F1 score. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed DAGKT.

Steph-Yves Louis, Yong Zhao, Alireza Nasiri et al.

Machine learning (ML) methods have gained increasing popularity in exploring and developing new materials. More specifically, graph neural network (GNN) has been applied in predicting material properties. In this work, we develop a novel model, GATGNN, for predicting inorganic material properties based on graph neural networks composed of multiple graph-attention layers (GAT) and a global attention layer. Through the application of the GAT layers, our model can efficiently learn the complex bonds shared among the atoms within each atom's local neighborhood. Subsequently, the global attention layer provides the weight coefficients of each atom in the inorganic crystal material which are used to considerably improve our model's performance. Notably, with the development of our GATGNN model, we show that our method is able to both outperform the previous models' predictions and provide insight into the crystallization of the material.

Murtadha Talib AL-Sharuee, Fei Liu, Mahardhika Pratama

Products reviews are one of the major resources to determine the public sentiment. The existing literature on reviews sentiment analysis mainly utilizes supervised paradigm, which needs labeled data to be trained on and suffers from domain-dependency. This article addresses these issues by describes a completely automatic approach for sentiment analysis based on unsupervised ensemble learning. The method consists of two phases. The first phase is contextual analysis, which has five processes, namely (1) data preparation; (2) spelling correction; (3) intensifier handling; (4) negation handling and (5) contrast handling. The second phase comprises the unsupervised learning approach, which is an ensemble of clustering classifiers using a majority voting mechanism with different weight schemes. The base classifier of the ensemble method is a modified k-means algorithm. The base classifier is modified by extracting initial centroids from the feature set via using SentWordNet (SWN). We also introduce new sentiment analysis problems of Australian airlines and home builders which offer potential benchmark problems in the sentiment analysis field. Our experiments on datasets from different domains show that contextual analysis and the ensemble phases improve the clustering performance in term of accuracy, stability and generalization ability.