arXiv subjects

Longbing Cao

Publications and source records attributed to Longbing Cao.

At least 109 records · Page 6Linked to original sources

arXiv2020

Data Science: A Comprehensive Overview

The twenty-first century has ushered in the age of big data and data economy, in which data DNA, which carries important knowledge, insights and potential, has become an intrinsic constituent of all data-based organisms. An appropriate understanding of data DNA and its organisms relies on the new field of data science and its keystone, analytics. Although it is widely debated whether big data is only hype and buzz, and data science is still in a very early phase, significant challenges and opportunities are emerging or have been inspired by the research, innovation, business, profession, and education of data science. This paper provides a comprehensive survey and tutorial of the fundamental aspects of data science: the evolution from data analysis to data science, the data science concepts, a big picture of the era of data science, the major challenges and directions in data innovation, the nature of data analytics, new industrialization and service opportunities in the data economy, the profession and competency of data education, and the future of data science. This article is the first in the field to draw a comprehensive big picture, in addition to offering rich observations, lessons and thinking about data science and analytics.

cs.CY↗

arXiv2020

Data Science: Nature and Pitfalls

Data science is creating very exciting trends as well as significant controversy. A critical matter for the healthy development of data science in its early stages is to deeply understand the nature of data and data science, and to discuss the various pitfalls. These important issues motivate the discussions in this article.

cs.CY↗

arXiv2020

Data Science: Challenges and Directions

While data science has emerged as a contentious new scientific field, enormous debates and discussions have been made on it why we need data science and what makes it as a science. In reviewing hundreds of pieces of literature which include data science in their titles, we find that the majority of the discussions essentially concern statistics, data mining, machine learning, big data, or broadly data analytics, and only a limited number of new data-driven challenges and directions have been explored. In this paper, we explore the intrinsic challenges and directions inspired by comprehensively exploring the complexities and intelligence embedded in data science problems. We focus on the research and innovation challenges inspired by the nature of data science problems as complex systems, and the methodologies for handling such systems.

cs.CY↗

arXiv2020

Jointly Modeling Intra- and Inter-transaction Dependencies with Hierarchical Attentive Transaction Embeddings for Next-item Recommendation

A transaction-based recommender system (TBRS) aims to predict the next item by modeling dependencies in transactional data. Generally, two kinds of dependencies considered are intra-transaction dependency and inter-transaction dependency. Most existing TBRSs recommend next item by only modeling the intra-transaction dependency within the current transaction while ignoring inter-transaction dependency with recent transactions that may also affect the next item. However, as not all recent transactions are relevant to the current and next items, the relevant ones should be identified and prioritized. In this paper, we propose a novel hierarchical attentive transaction embedding (HATE) model to tackle these issues. Specifically, a two-level attention mechanism integrates both item embedding and transaction embedding to build an attentive context representation that incorporates both intraand inter-transaction dependencies. With the learned context representation, HATE then recommends the next item. Experimental evaluations on two real-world transaction datasets show that HATE significantly outperforms the state-ofthe-art methods in terms of recommendation accuracy.

cs.IR↗

arXiv2020

Graph Learning Approaches to Recommender Systems: A Review

Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS). GLRS mainly employ the advanced graph learning approaches to model users' preferences and intentions as well as items' characteristics and popularity for Recommender Systems (RS). Differently from conventional RS, including content based filtering and collaborative filtering, GLRS are built on simple or complex graphs where various objects, e.g., users, items, and attributes, are explicitly or implicitly connected. With the rapid development of graph learning, exploring and exploiting homogeneous or heterogeneous relations in graphs is a promising direction for building advanced RS. In this paper, we provide a systematic review of GLRS, on how they obtain the knowledge from graphs to improve the accuracy, reliability and explainability for recommendations. First, we characterize and formalize GLRS, and then summarize and categorize the key challenges in this new research area. Then, we survey the most recent and important developments in the area. Finally, we share some new research directions in this vibrant area.

cs.IR↗

arXiv2020

FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces challenge in continuous control tasks. Conventional methods always compute the derivatives of the optimal goal with a costly computation resources, and are inefficient, unstable and lack of robust-ness when dealing with such tasks. Alternatively, derivative-based methods treat the optimization process as a blackbox and show robustness and stability in learning continuous control tasks, but not data efficient in learning. The combination of both methods so as to get the best of the both has raised attention. However, most of the existing combination works adopt complex neural networks (NNs) as the policy for control. The double-edged sword of deep NNs can yield better performance, but also makes it difficult for parameter tuning and computation. To this end, in this paper we presents a novel method called FiDi-RL, which incorporates deep RL with Finite-Difference (FiDi) policy search.FiDi-RL combines Deep Deterministic Policy Gradients (DDPG)with Augment Random Search (ARS) and aims at improving the data efficiency of ARS. The empirical results show that FiDi-RL can improves the performance and stability of ARS, and provide competitive results against some existing deep reinforcement learning methods

cs.LG↗

arXiv2019

Sequential Recommender Systems: Challenges, Progress and Prospects

The emerging topic of sequential recommender systems has attracted increasing attention in recent years.Different from the conventional recommender systems including collaborative filtering and content-based filtering, SRSs try to understand and model the sequential user behaviors, the interactions between users and items, and the evolution of users preferences and item popularity over time. SRSs involve the above aspects for more precise characterization of user contexts, intent and goals, and item consumption trend, leading to more accurate, customized and dynamic recommendations.In this paper, we provide a systematic review on SRSs.We first present the characteristics of SRSs, and then summarize and categorize the key challenges in this research area, followed by the corresponding research progress consisting of the most recent and representative developments on this topic.Finally, we discuss the important research directions in this vibrant area.

cs.IR↗

arXiv2019

A shrinkage estimation for large dimensional precision matrices using random matrix theory

In this paper, a new ridge-type shrinkage estimator for the precision matrix has been proposed. The asymptotic optimal shrinkage coefficients and the theoretical loss were derived. Data-driven estimators for the shrinkage coefficients were also conducted based on the asymptotic results deriving from random matrix theories. The new estimator which has a simple explicit formula is distribution-free and applicable to situation where the dimension of observation is greater than the sample size. Further, no assumptions are required on the structure of the population covariance matrix or the precision matrix. Finally, numerical studies are conducted to examine the performances of the new estimator and existing methods for a wide range of settings.

stat.ME↗

arXiv2019

Multi-view Information-theoretic Co-clustering for Co-occurrence Data

Multi-view clustering has received much attention recently. Most of the existing multi-view clustering methods only focus on one-sided clustering. As the co-occurring data elements involve the counts of sample-feature co-occurrences, it is more efficient to conduct two-sided clustering along the samples and features simultaneously. To take advantage of two-sided clustering for the co-occurrences in the scene of multi-view clustering, a two-sided multi-view clustering method is proposed, i.e., multi-view information-theoretic co-clustering (MV-ITCC). The proposed method realizes two-sided clustering for co-occurring multi-view data under the formulation of information theory. More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension. In addition, the mechanism of maximum entropy is also adopted to control the importance of different views, which can give a right balance in leveraging the agreement and disagreement. Extensive experiments are conducted on text and image multi-view datasets. The results clearly demonstrate the superiority of the proposed method.

cs.LG↗

arXiv2019

TBQ($σ$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning

Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces and slow down the learning process. Alternatively, some non-probabilistic measurement methods such as General Q($λ$) and Naive Q($λ$) never cut traces, but face convergence problems in practice. To address the above issues, this paper introduces a new method named TBQ($σ$), which effectively unifies the tree-backup algorithm and Naive Q($λ$). By introducing a new parameter $σ$ to illustrate the \emph{degree} of utilizing traces, TBQ($σ$) creates an effective integration of TB($λ$) and Naive Q($λ$) and continuous role shift between them. The contraction property of TB($σ$) is theoretically analyzed for both policy evaluation and control settings. We also derive the online version of TBQ($σ$) and give the convergence proof. We empirically show that, for $ε\in(0,1]$ in $ε$-greedy policies, there exists some degree of utilizing traces for $λ\in[0,1]$, which can improve the efficiency in trace utilization for off-policy reinforcement learning, to both accelerate the learning process and improve the performance.

cs.LG↗

arXiv2018

Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

Learning expressive low-dimensional representations of ultrahigh-dimensional data, e.g., data with thousands/millions of features, has been a major way to enable learning methods to address the curse of dimensionality. However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i.e., outliers). This paper introduces a ranking model-based framework, called RAMODO, to address this issue. RAMODO unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier detection approach - the random distance-based approach. This customized learning yields more optimal and stable representations for the targeted outlier detectors. Additionally, RAMODO can leverage little labeled data as prior knowledge to learn more expressive and application-relevant representations. We instantiate RAMODO to an efficient method called REPEN to demonstrate the performance of RAMODO. Extensive empirical results on eight real-world ultrahigh dimensional data sets show that REPEN (i) enables a random distance-based detector to obtain significantly better AUC performance and two orders of magnitude speedup; (ii) performs substantially better and more stably than four state-of-the-art representation learning methods; and (iii) leverages less than 1% labeled data to achieve up to 32% AUC improvement.

cs.LG↗

arXiv2015

Coupling Analysis Between Twitter and Call Centre

Social media has been contributing many research areas such as data mining, recommender systems, time series analysis, etc. However, there are not many successful applications regarding social media in government agencies. In fact, lots of governments have social media accounts such as twitter and facebook. More and more customers are likely to communicate with governments on social media, causing massive external social media data for governments. This external data would be beneficial for analysing behaviours and real needs of the customers. Besides this, most governments also have a call centre to help customers solve their problems. It is not difficult to imagine that the enquiries on external social media and internal call centre may have some coupling relationships. The couplings could be helpful for studying customers' intent and allocating government's limited resources for better service. In this paper, we mainly focus on analysing the coupling relations between internal call centre and external public media using time series analysis methods for Australia Department of Immigration and Border Protec-tion. The discovered couplings demonstrate that call centre and public media indeed have correlations, which are significant for understanding customers' behaviours.

cs.SI↗

arXiv2015

CSAL: Self-adaptive Labeling based Clustering Integrating Supervised Learning on Unlabeled Data

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in revealing the aggregation property of unlabeled data, but the performance of most clustering methods is limited by the absence of labeled data. In real applications, however, it is time-consuming and sometimes impossible to obtain labeled data. The combination of clustering and classification is a promising and active approach which can largely improve the performance. In this paper, we propose an innovative and effective clustering framework based on self-adaptive labeling (CSAL) which integrates clustering and classification on unlabeled data. Clustering is first employed to partition data and a certain proportion of clustered data are selected by our proposed labeling approach for training classifiers. In order to refine the trained classifiers, an iterative process of Expectation-Maximization algorithm is devised into the proposed clustering framework CSAL. Experiments are conducted on publicly data sets to test different combinations of clustering algorithms and classification models as well as various training data labeling methods. The experimental results show that our approach along with the self-adaptive method outperforms other methods.

cs.LG↗

arXiv2014

Coupled Matrix Factorization within Non-IID Context

Recommender systems research has experienced different stages such as from user preference understanding to content analysis. Typical recommendation algorithms were built on the following bases: (1) assuming users and items are IID, namely independent and identically distributed, and (2) focusing on specific aspects such as user preferences or contents. In reality, complex recommendation tasks involve and request (1) personalized outcomes to tailor heterogeneous subjective preferences; and (2) explicit and implicit objective coupling relationships between users, items, and ratings to be considered as intrinsic forces driving preferences. This inevitably involves the non-IID complexity and the need of combining subjective preference with objective couplings hidden in recommendation applications. In this paper, we propose a novel generic coupled matrix factorization (CMF) model by incorporating non-IID coupling relations between users and items. Such couplings integrate the intra-coupled interactions within an attribute and inter-coupled interactions among different attributes. Experimental results on two open data sets demonstrate that the user/item couplings can be effectively applied in RS and CMF outperforms the benchmark methods.

cs.IR↗

arXiv2014

Non-parametric shrinkage mean estimation for quadratic loss functions with unknown covariance matrices

In this paper, a shrinkage estimator for the population mean is proposed under known quadratic loss functions with unknown covariance matrices. The new estimator is non-parametric in the sense that it does not assume a specific parametric distribution for the data and it does not require the prior information on the population covariance matrix. Analytical results on the improvement of the proposed shrinkage estimator are provided and some corresponding asymptotic properties are also derived. Finally, we demonstrate the practical improvement of the proposed method over existing methods through extensive simulation studies and real data analysis. Keywords: High-dimensional data; Shrinkage estimator; Large $p$ small $n$; $U$-statistic.

stat.ME↗

arXiv2014

Coupled Item-based Matrix Factorization

The essence of the challenges cold start and sparsity in Recommender Systems (RS) is that the extant techniques, such as Collaborative Filtering (CF) and Matrix Factorization (MF), mainly rely on the user-item rating matrix, which sometimes is not informative enough for predicting recommendations. To solve these challenges, the objective item attributes are incorporated as complementary information. However, most of the existing methods for inferring the relationships between items assume that the attributes are "independently and identically distributed (iid)", which does not always hold in reality. In fact, the attributes are more or less coupled with each other by some implicit relationships. Therefore, in this pa-per we propose an attribute-based coupled similarity measure to capture the implicit relationships between items. We then integrate the implicit item coupling into MF to form the Coupled Item-based Matrix Factorization (CIMF) model. Experimental results on two open data sets demonstrate that CIMF outperforms the benchmark methods.

cs.LG↗

arXiv2013

Copula Mixed-Membership Stochastic Blockmodel for Intra-Subgroup Correlations

The \emph{Mixed-Membership Stochastic Blockmodel (MMSB)} is a popular framework for modeling social network relationships. It can fully exploit each individual node's participation (or membership) in a social structure. Despite its powerful representations, this model makes an assumption that the distributions of relational membership indicators between two nodes are independent. Under many social network settings, however, it is possible that certain known subgroups of people may have high or low correlations in terms of their membership categories towards each other, and such prior information should be incorporated into the model. To this end, we introduce a \emph{Copula Mixed-Membership Stochastic Blockmodel (cMMSB)} where an individual Copula function is employed to jointly model the membership pairs of those nodes within the subgroup of interest. The model enables the use of various Copula functions to suit the scenario, while maintaining the membership's marginal distribution, as needed, for modeling membership indicators with other nodes outside of the subgroup of interest. We describe the proposed model and its inference algorithm in detail for both the finite and infinite cases. In the experiment section, we compare our algorithms with other popular models in terms of link prediction, using both synthetic and real world data.

cs.LG↗

arXiv2013

Learning Hidden Structures with Relational Models by Adequately Involving Rich Information in A Network

Effectively modelling hidden structures in a network is very practical but theoretically challenging. Existing relational models only involve very limited information, namely the binary directional link data, embedded in a network to learn hidden networking structures. There is other rich and meaningful information (e.g., various attributes of entities and more granular information than binary elements such as "like" or "dislike") missed, which play a critical role in forming and understanding relations in a network. In this work, we propose an informative relational model (InfRM) framework to adequately involve rich information and its granularity in a network, including metadata information about each entity and various forms of link data. Firstly, an effective metadata information incorporation method is employed on the prior information from relational models MMSB and LFRM. This is to encourage the entities with similar metadata information to have similar hidden structures. Secondly, we propose various solutions to cater for alternative forms of link data. Substantial efforts have been made towards modelling appropriateness and efficiency, for example, using conjugate priors. We evaluate our framework and its inference algorithms in different datasets, which shows the generality and effectiveness of our models in capturing implicit structures in networks.

cs.LG↗