检索结果-内蒙古大学图书馆

Meta-Path Hierarchical Heterogeneous Graph Convolution network for High Potential Scholar Recognition

学校读者我要写书评

暂无评论

Meta-Path Hierarchical Heterogeneous Graph Convolution Netwo...

IEEE International Conference on data Mining (ICDM)

作者： Yiqing Wu Ying Sun Fuzhen Zhuang Deqing Wang Xiangliang Zhang Qing He Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University China King Abdullah University of Science and Technology Saudi Arabia

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Recognizing high potential scholars has become an important problem in recent years. However, conventional scholar evaluating methods based on hand-crafted metrics can not profile the scholars in a dynamic and comprehensive way. With the development of online academic databases, large-scale academic activity data become available, which implies detailed information on the scholars' achievement and academic activities. Inspired by the recent success of deep graph neural networks (GNNs), we propose a novel solution to recognize high potential scholars on the dynamic heterogeneous academic network. Specifically, we propose a novel Mate-path Hierarchical Heterogeneous Graph Convolution network (MHHGCN) to effectively model the heterogeneous graph information. MHHGCN hierarchically aggregates entity and relational information on a set of meta-paths, and can alleviate the information loss problem in the previous heterogenous GNN models. Then to capture the dynamic scholar feature, we combine MHHGCN with Long Short Term Memory (LSTM) network with attention mechanism to model the temporal information and predict the potential scholar. Extensive experimental results on real-world high potential scholar data demonstrate the effectiveness of our approach. Moreover, the model shows high interpretability by visualization of the attention layers.

关键词： Measurement Convolution Aggregates data visualization Predictive models Graph neural networks Long short term memory

Dynamic MCMC sampling

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Feng, Weiming He, Kun Sun, Xiaoming Yin, Yitong State Key Laboratory for Novel Software Technology Nanjing University CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

The Markov chain Monte Carlo (MCMC) methods are the primary tools for sampling from Gibbs distributions arising by various graphical models, e.g. Markov random fields (MRF). Traditional MCMC sampling algorithms are focused on a classic static setting, where the input is fixed. In this paper we study the problem of sampling from a MRF when the graphical model itself is changing dynamically with time. The problem is well motivated by the growing volume and velocity of data in today's applications of the MCMC methods. For the two major MCMC approaches, respectively for the approximate and perfect sampling, namely, the Gibbs sampling and the coupling from the past (CFTP), we give dynamic versions for the respective MCMC sampling algorithms. On MRF with n variables and bounded maximum degrees, these dynamic sampling algorithms can maintain approximate samples within 1/Poly(n) total variation errors, or perfect samples, while the MRF is dynamically changing. Furthermore, the dynamic sampling algorithms are efficient with O(n) space cost, and O(log2 n) incremental time cost upon each local update to the input MRF, as long as certain decay conditions are satisfied in each step by natural couplings of the corresponding single-site chains. These decay conditions were well known in the literature of couplings for rapid mixing of Markov chains, and now for the first time, are used to imply efficient dynamic sampling algorithms. Consequently, we have efficient dynamic (approximate or perfect) sampling algorithms with O(n) space cost and O (log2 n) incremental time cost, for the following models when the maximum degree is bounded: generalMRF satisfying the Dobrushin-Shlosman condition (for approximate sampling);Ising model with temperature β where e-2|β| > 1 - 2 β+1 (for both approximate and perfect samplings);hardcore model with fugacity λ 2λ (for approximate sampling);or q > 2Δ2 + 3Δ (for perfect sampling). These results show that the coupling of single-site Markov chains that

关键词： Learning algorithms

MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Guo, Jiafeng Fan, Yixing Ji, Xiang Cheng, Xueqi University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Beijing Institute of Technology University Beijing China

Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation. Recently, deep leaning technology has been widely adopted for text matching, making neural text matching a new and active research domain. With a large number of neural matching models emerging rapidly, it becomes more and more difficult for researchers, especially those newcomers, to learn and understand these new models. Moreover, it is usually difficult to try these models due to the tedious data pre-processing, complicated parameter configuration, and massive optimization tricks, not to mention the unavailability of public codes sometimes. Finally, for researchers who want to develop new models, it is also not an easy task to implement a neural text matching model from scratch, and to compare with a bunch of existing models. In this paper, therefore, we present a novel system, namely MatchZoo, to facilitate the learning, practicing and designing of neural text matching models. The system consists of a powerful matching library and a user-friendly and interactive studio, which can help researchers: 1) to learn state-of-the-art neural text matching models systematically, 2) to train, test and apply these models with simple configurable steps;and 3) to develop their own models with rich APIs and assistance. Copyright © 2019, The Authors. All rights reserved.

关键词： Natural language processing systems

Signed graph attention networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Junjie Shen, Huawei Hou, Liang Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Graph or network data is ubiquitous in the real world, including social networks, information networks, traffic networks, biological networks and various technical networks. The non-Euclidean nature of graph data poses the challenge for modeling and analyzing graph data. Recently, Graph Neural network (GNNs) are proposed as a general and powerful framework to handle tasks on graph data, e.g., node embedding, link prediction and node classification. As a representative implementation of GNNs, Graph Attention networks (GATs) are successfully applied in a variety of tasks on real datasets. However, GAT is designed to networks with only positive links and fails to handle signed networks which contain both positive and negative links. In this paper, we propose Signed Graph Attention networks (SiGATs), generalizing GAT to signed networks. SiGAT incorporates graph motifs into GAT to capture two well-known theories in signed network research, i.e., balance theory and status theory. In SiGAT, motifs offer us the flexible structural pattern to aggregate and propagate messages on the signed network to generate node embeddings. We evaluate the proposed SiGAT method by applying it to the signed link prediction task. Experimental results on three real datasets demonstrate that SiGAT outperforms feature-based method, network embedding method and state-of-the-art GNN-based methods like signed graph convolutional network (SGCN). Copyright © 2019, The Authors. All rights reserved.

关键词： Graph neural networks

SetRank: Learning a permutation-invariant ranking model for information retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pang, Liang Xu, Jun Ai, Qingyao Lan, Yanyan Cheng, Xueqi Wen, Jirong CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Renmin University of China Beijing China University of Utah United States

In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents. Therefore, an ideal ranking model would be a mapping from a document set to a permutation on the set, and should satisfy two critical requirements: (1) it should have the ability to model cross-document interactions so as to capture local context information in a query;(2) it should be permutation-invariant, which means that any permutation of the inputted documents would not change the output ranking. Previous studies on learning-to-rank either design uni-variate scoring functions that score each document separately, and thus failed to model the cross-document interactions;or construct multivariate scoring functions that score documents sequentially, which inevitably sacrifice the permutation invariance requirement. In this paper, we propose a neural learning-to-rank model called SetRank which directly learns a permutation-invariant ranking model defined on document sets of any size. SetRank employs a stack of (induced) multi-head self attention blocks as its key component for learning the embeddings for all of the retrieved documents jointly. The self-attention mechanism not only helps SetRank to capture the local context information from cross-document interactions, but also to learn permutation-equivariant representations for the inputted documents, which therefore achieving a permutation-invariant ranking model. Experimental results on three large scale benchmarks showed that the SetRank significantly outperformed the baselines include the traditional learning-to-rank models and state-of-the-art Neural IR models. Copyright © 2019, The Authors. All rights reserved.

关键词： Information retrieval

Cake cutting on graphs: A discrete and bounded proportional protocol

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bei, Xiaohui Sun, Xiaoming Wu, Hao Zhang, Jialin Zhang, Zhijie Zi, Wei School of Physical and Mathematical Sciences Nanyang Technological University CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences

The classical cake cutting problem studies how to find fair allocations of a heterogeneous and divisible resource among multiple agents. Two of the most commonly studied fairness concepts in cake cutting are proportionality and envy-freeness. It is well known that a proportional allocation among n agents can be found efficiently via simple protocols [16]. For envy-freeness, in a recent breakthrough, Aziz and Mackenzie [5] proposed a discrete and bounded envy-free protocol for any number of players. However, the protocol suffers from high multiple-exponential query complexity and it remains open to find simpler and more efficient envy-free protocols. In this paper we consider a variation of the cake cutting problem by assuming an underlying graph over the agents whose edges describe their acquaintance relationships, and agents evaluate their shares relatively to those of their neighbors. An allocation is called locally proportional if each agent thinks she receives at least the average value over her neighbors. Local proportionality generalizes proportionality and is in an interesting middle ground between proportionality and envy-freeness: its existence is guaranteed by that of an envy-free allocation, but no simple protocol is known to produce such a locally proportional allocation for general graphs. Previous works showed locally proportional protocols for special classes of graphs, and it is listed in both [1] and [8] as an open question to design simple locally proportional protocols for more general classes of graphs. In this paper we completely resolved this open question by presenting a discrete and bounded locally proportional protocol for any given graph. Our protocol has a query complexity of only single exponential, which is significantly smaller than the six towers of n query complexity of the envy-free protocol given in [5]. Copyright © 2019, The Authors. All rights reserved.

关键词： Graphic methods

A reduced collatz dynamics maps to a residue class, and its count of x/2 over count of 3*x+1 is larger than ln3/ln2

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2020年

作者： Ren, Wei School of Computer Science China University of Geosciences Wuhan China Key Laboratory of Network Assessment Technology CAS [Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Guizhou Provincial Key Laboratory Public Big Data Guizhou University Guizhou China

We propose Reduced Collatz conjecture and prove that it is equivalent to Collatz conjecture but more primitive due to reduced dynamics. We study reduced dynamics (that consists of occurred computations from any starting integer to the first integer less than it), because it is the component of original dynamics (from any starting integer to 1). Reduced dynamics is denoted as a sequence of "I" that represents (3*x+1)/2 and "O" that represents x/2. Here 3*x+1 and x/2 are combined together because 3*x+1 is always even and thus followed by x/2. We discover and prove two key properties on reduced dynamics: (1) Reduced dynamics is invertible. That is, given a reduced dynamics, a residue class that presents such reduced dynamics, can be computed directly by our derived formula. (2) Reduced dynamics can be constructed algorithmically, instead of by computing concrete 3*x+1 and x/2 step by step. We discover the sufficient and necessary condition that guarantees a sequence consisting of "I" and "O" to be a reduced dynamics. Counting from the beginning of a sequence, if and only if the count of x/2 over the count of 3*x+1 is larger than ln3/ln2, reduced dynamics will be obtained (i.e., current integer will be less than starting integer). © 2020, CC BY.

关键词： Dynamics

Graph wavelet neural network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Bingbing Shen, Huawei Cao, Qi Qiu, Yunqi Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China

We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained via a fast algorithm without requiring matrix eigendecomposition with high computational cost. Moreover, graph wavelets are sparse and localized in vertex domain, offering high efficiency and good interpretability for graph convolution. The proposed GWNN significantly outperforms previous spectral graph CNNs in the task of graph-based semi-supervised classification on three benchmark datasets: Cora, Citeseer and Pubmed. Copyright © 2019, The Authors. All rights reserved.

关键词： Wavelet transforms

Parameter estimation with the ordered 2 regularization via an alternating direction method of multipliers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Humayoo, Mahammad Cheng, Xueqi CAS Key Laboratory of Network Data Science & Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

Regularization is a popular technique in machine learning for model estimation and for avoiding overfitting. Prior studies have found that modern ordered regularization can be more effective in handling highly correlated, high-dimensional data than traditional regularization. The reason stems from the fact that the ordered regularization can reject irrelevant variables and yield an accurate estimation of the parameters. How to scale up the ordered regularization problems when facing large-scale training data remains an unanswered question. This paper explores the problem of parameter estimation with the ordered 2-regularization via Alternating Direction Method of Multipliers (ADMM), called ADMM-O2. The advantages of ADMM-O2 include (i) scaling up the ordered 2 to a large-scale dataset, (ii) predicting parameters correctly by excluding irrelevant variables automatically, and (iii) having a fast convergence rate. Experimental results on both synthetic data and real data indicate that ADMM-O2 can perform better than or comparable to several state-of-the-art baselines. Copyright © 2019, The Authors. All rights reserved.

关键词： Parameter estimation