Chengqi Zhang

Chengqi Zhang
University of Technology Sydney | UTS · Centre for Quantum Computation and Intelligent Systems (QCIS)

About

488
Publications
108,075
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
13,674
Citations

Publications

Publications (488)
Article
Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For example, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily l...
Preprint
In a federated learning system, the clients, e.g. mobile devices and organization participants, usually have different personal preferences or behavior patterns, namely Non-IID data problems across clients. Clustered federated learning is to group users into different clusters that the clients in the same group will share the same or similar behavi...
Preprint
Full-text available
Open banking enables individual customers to own their banking data, which provides fundamental support for the boosting of a new ecosystem of data marketplaces and financial services. In the near future, it is foreseeable to have decentralized data ownership in the finance sector using federated learning. This is a just-in-time technology that can...
Preprint
Federated learning (FL) can protect data privacy in distributed learning since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of heterogeneity that is commonly encountered in practical settings, e.g., non-IID data over different users. Existing FL approaches usually update a single...
Article
Node clustering aims to partition the vertices in a graph into multiple groups or communities. Existing studies have mostly focused on developing deep learning approaches to learn a latent representation of nodes, based on which simple clustering methods like k-means are applied. These two-step frameworks for node clustering are difficult to manipu...
Preprint
Full-text available
Healthcare representation learning on the Electronic Health Record (EHR) is seen as crucial for predictive analytics in the medical field. Many natural language processing techniques, such as word2vec, RNN and self-attention, have been adapted for use in hierarchical and time stamped EHR data, but fail when they lack either general or task-specific...
Preprint
Full-text available
Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the potentially useful middle and high frequency band of graph signals are ignored. Second, the bandwidth of existing g...
Article
Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned continuous vector r...
Preprint
Full-text available
Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image ca...
Preprint
Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that...
Preprint
Many graph embedding approaches have been proposed for knowledge graph completion via link prediction. Among those, translating embedding approaches enjoy the advantages of light-weight structure, high efficiency and great interpretability. Especially when extended to complex vector space, they show the capability in handling various relation patte...
Preprint
Wrong labeling problem and long-tail relations are two main challenges caused by distant supervision in relation extraction. Recent works alleviate the wrong labeling by selective attention via multi-instance learning, but cannot well handle long-tail relations even if hierarchies of the relations are introduced to share knowledge. In this work, we...
Preprint
The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on...
Preprint
Full-text available
Electronic health records (EHRs) are longitudinal records of a patient's interactions with healthcare systems. A patient's EHR data is organized as a three-level hierarchy from top to bottom: patient journey - all the experiences of diagnoses and treatments over a period of time; individual visit - a set of medical codes in a particular visit; and...
Conference Paper
Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main proble...
Preprint
We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical applications but has been rarely studied in previous literature. It brings new challenges of distinguishing between many...
Article
We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical applications but has been rarely studied in previous literature. It brings new challenges of distinguishing between many...
Preprint
Full-text available
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully...
Article
Full-text available
The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on...
Article
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from...
Article
Full-text available
Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology structure to learn node representations, recently proposed attributed network embedding algorithms attempt to...
Preprint
Full-text available
Meta-learning extracts the common knowledge acquired from learning different tasks and uses it for unseen tasks. It demonstrates a clear advantage on tasks that have insufficient training data, e.g., few-shot learning. In most meta-learning methods, tasks are implicitly related via the shared model or optimizer. In this paper, we show that a meta-l...
Article
Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph-analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes,...
Conference Paper
Full-text available
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not...
Conference Paper
Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulat...
Conference Paper
Full-text available
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they...
Preprint
Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulat...
Preprint
Full-text available
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not...
Preprint
Full-text available
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they...
Preprint
Full-text available
Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology structure to learn node representations, recently proposed attributed network embedding algorithms attempt to...
Preprint
Full-text available
Traditional network embedding primarily focuses on learning a dense vector representation for each node, which encodes network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned dense vector represen...
Preprint
Full-text available
Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes,...
Preprint
Full-text available
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from...
Article
Matrix factorization has been widely applied to various applications. With the fast development of storage and internet technologies, we have been witnessing a rapid increase of data. In this paper, we propose new algorithms for matrix factorization with the emphasis on efficiency. In addition, most existing methods of matrix factorization only con...
Conference Paper
Full-text available
Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model...
Preprint
Full-text available
Attributed network embedding aims to learn low-dimensional vector representations for nodes in a network, where each node contains rich attributes/features describing node content. Because network topology structure and node attributes often exhibit high correlation, incorporating node attribute proximity into network embedding is beneficial for le...
Article
Recent advancements in artificial intelligence (AI) are providing the insurance industry with new opportunities to create tailored solutions and services based on newfound knowledge of consumers, and the execution of enhanced operations and business functions. However, insurance data is heterogeneous, and imbalanced class distribution with low freq...
Article
When users in online social networks make a decision, they are often affected by their neighbors. Social recommendation models utilize social information to reveal the impact of neighbors on user preferences, and this impact is often described by the linear superposition of neighbor preferences or by global trust propagation. Further exploration ne...
Article
Full-text available
Processing, mining, and learning complex data refer to an advanced study area of data mining and knowledge discovery concerning the development and analysis of approaches for discovering patterns and learning models from data with a complex structure (e.g., multirelational data, XML data, text data, image data, time series, sequences, graphs, strea...
Article
Full-text available
Recommender systems are designed to solve the information overload problem and have been widely studied for many years. Conventional recommender systems tend to take ratings of users on products into account. With the development of Web 2.0, Rating Networks in many online communities (e.g. Netflix and Douban) allow users not only to co-comment or c...
Conference Paper
Full-text available
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which...
Conference Paper
Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention...
Chapter
Network embedding in heterogeneous information networks (HINs) is a challenging task, due to complications of different node types and rich relationships between nodes. As a result, conventional network embedding techniques cannot work on such HINs. Recently, metapath-based approaches have been proposed to characterize relationships in HINs, but th...
Article
Time series has been a popular research topic over the past decade. Salient subsequences of time series that can benefit the learning task, e.g. classification or clustering, are called shapelets. Shapelet-based time series learning extracts these types of salient subsequences with highly informative features from a time series. Most existing metho...
Article
Networked data are common in domains where instances are characterized by both feature values and inter-dependency relationships. Finding cluster structures for networked instances and discovering representative features for each cluster represent a special co-clustering task usefully for many real-world applications, such as automatic categorizati...
Article
Multi-instance learning (MIL) is a useful tool for tackling labeling ambiguity in learning because it allows a bag of instances to share one label. Bag mapping transforms a bag into a single instance in a new space via instance selection and has drawn significant attention recently. To date, most existing work is based on the original space, using...
Article
Spectral clustering (SC) has been widely applied to various computer vision tasks, where the key is to construct a robust affinity matrix for data partitioning. With the increase in visual features, conventional SC methods are facing two challenges: 1) how to effectively generate an affinity matrix based on multiple features? and 2) how to deal wit...
Preprint
Full-text available
In this paper, we propose a self-attention mechanism, dubbed "fast directional self-attention (Fast-DiSA)", which is a fast and light extension of "directional self-attention (DiSA)". The proposed Fast-DiSA performs as expressively as the original DiSA but only uses much less computation time and memory, in which 1) both token2token and source2toke...
Article
Full-text available
Recurrent neural networks (RNN), convolutional neural networks (CNN) and self-attention networks (SAN) are commonly used to produce context-aware representations. RNN can capture long-range dependency but is hard to parallelize and not time-efficient. CNN focuses on local dependency but does not perform well on some tasks. SAN can model both such d...
Article
Full-text available
Network embedding in heterogeneous information networks (HINs) is a challenging task, due to complications of different node types and rich relationships between nodes. As a result, conventional network embedding techniques cannot work on such HINs. Recently, metapath-based approaches have been proposed to characterize relationships in HINs, but th...
Article
Full-text available
Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention...
Conference Paper
Recurrent neural networks (RNN), convolutional neural networks (CNN) and self-attention networks (SAN) are commonly used to produce context-aware representations. RNN can capture long-range dependency but is hard to parallelize and not time-efficient. CNN focuses on local dependency but does not perform well on some tasks. SAN can model both such d...
Article
With the widespread use of information technologies, information networks have increasingly become popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the...
Chapter
As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building...
Article
Many applications involve objects containing structure and rich content information, each describing different feature aspects of the object. Graph learning and classification is a common tool for handling such objects. To date, existing graph classification has been limited to the single-graph setting with each object being represented as one grap...
Article
Full-text available
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used in NLP tasks to capture the long-term and local dependencies respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propo...
Article
Although existing antispam strategies detect traditional spam activities effectively, evolving spam schemes can successfully cheat conventional testing by buying the comments that are written by genuine users and sold by specific web markets. Such spam activities turn into a kind of advertising campaign among business owners to maintain their rank...
Conference Paper
Full-text available
Review rating prediction is an important research topic. The problem was approached from either the perspective of recommender systems (RS) or that of sentiment analysis (SA). Recent SA research using deep neural networks (DNNs) has realized the importance of user and product interaction for better interpreting the sentiment of reviews. However , t...
Conference Paper
This paper addresses social network embedding, which aims to embed social network nodes, including user profile information, into a latent low-dimensional space. Most of the existing works on network embedding only consider network structure, but ignore user-generated content that could be potentially helpful in learning a better joint network repr...
Article
Protein phosphorylation is the process of binding a protein kinase to a specific site in a protein substrate for post-translational modification. Thousands of distinct phosphorylation sites have been identified, but most of them are not annotated with any kinase information. This work proposes a novel kinase-subgrouping propensity method (kiSP) to...
Article
Online reviews are extensively utilized by potential buyers to make business decisions. Unfortunately, fraudsters offer to write spam reviews for product promotion or competitor defamation, which drives online business holders to adopt this type of vicious strategy to increase their profits. These fake reviews always mislead users who shop online....