Lina Yao

CSIRO Data61 · Analytics and Decision Sciences

Understanding and recognizing human activities is a fundamental research topic for a wide range of important applications such as fall detection and remote health monitoring and intervention. Despite active research in human activity recognition over the past years, existing approaches based on computer vision or wearable sensor technologies presen...

A common challenge for most current recommender systems is the cold-start problem. Due to the lack of user-item interactions, the fine-tuned recommender systems are unable to handle situations with new users or new items. Recently, some works introduce the meta-optimization idea into the recommendation scenarios, i.e. predicting the user preference...

In light of the emergence of deep reinforcement learning (DRL) in recommender systems research and several fruitful results in recent years, this survey aims to provide a timely and comprehensive overview of the recent trends of deep reinforcement learning in recommender systems. We start with the motivation of applying DRL in recommender systems....

Conditional Neural Processes~(CNPs) bridge neural networks with probabilistic inference to approximate functions of Stochastic Processes under meta-learning settings. Given a batch of non-{\it i.i.d} function instantiations, CNPs are jointly optimized for in-instantiation observation prediction and cross-instantiation meta-representation adaptation...

The standard approaches to neural network implementation yield powerful function approximation capabilities but are limited in their abilities to learn meta representations and reason probabilistic uncertainties in their predictions. Gaussian processes, on the other hand, adopt the Bayesian learning scheme to estimate such uncertainties but are con...

Tremendous efforts have been devoted to pedestrian trajectory prediction using generative modeling for accommodating uncertainty and multi-modality in human behaviors. An individual's inherent uncertainty, e.g., change of destination, can be masked by complex patterns resulting from the movements of interacting pedestrians. However, latent variable...

The goal of Image-to-image (I2I) translation is to transfer an image from a source domain to a target domain, which has recently drawn increasing attention. One major branch of this research is to formulate I2I translation based on Generative Adversarial Network (GAN). As a zero-sum game, GAN can be reformulated as a Partially-observed Markov Decis...

Transportation is the backbone of the economy and urban development. Improving the efficiency, sustainability, resilience, and intelligence of transportation systems is critical and also challenging. The constantly changing traffic conditions, the uncertain influence of external factors (e.g. weather, accidents), and the interactions among multiple...

Open-World Compositional Zero-Shot Learning (OW-CZSL) aims to recognize new compositions of seen attributes and objects. In OW-CZSL, methods built on the conventional closed-world setting degrade severely due to the unconstrained OW test space. While previous works alleviate the issue by pruning compositions according to external knowledge or corre...

Within-basket recommendation ( WBR ) is to recommend suitable items for the current basket with some already known items. The within-basket auxiliary item recommendation ( WBAIR ) is to recommend auxiliary items based on the primary items in the basket. Such a task exists in many real-life scenarios. Unlike the associations between items that can b...

The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds. For this, data deletion needs to be deep and permanent, and should be removed from machine learning models. Researchers have proposed machine unlearning algorithms which aim to erase specific data from trained models more e...

Deep generative models have gained popularity in recent years due to their ability to accurately replicate inherent empirical distributions and yield novel samples. In particular, certain advances are proposed wherein the model engenders data examples following specified attributes. Nevertheless, several challenges still exist and are to be overcom...

Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, focusing on only one of the abilities may result in models that are either too general with degraded classificatio...

Electroencephalography (EEG) signals are gaining popularity in Brain-Computer Interface (BCI)-based rehabilitation and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particular BCI task, increasing the risks of overfitting i...

Object detection (OD) is a basic computer vision task. To date, there have been many OD algorithms or models for solving different problems. The performance of the current models has gradually improved and their applications have expanded. However, the models have also become more complex, with larger numbers of parameters, making them unsuitable f...

The sequential recommendation is a compelling technology for predicting users’ next interaction via their historical behaviors. Prior studies have proposed various methods to optimize the recommendation accuracy on different datasets but have not yet explored the intrinsic predictability of sequential recommendation. To this end, we consider applyi...

EEG-based tinnitus classification is a valuable tool for tinnitus diagnosis, research, and treatments. Most current works are limited to a single dataset where data patterns are similar. But EEG signals are highly non-stationary, resulting in model's poor generalization to new users, sessions or datasets. Thus, designing a model that can generalize...

We propose a graph neural network with self-attention and multi-task learning (SaM-GNN) to leverage the advantages of deep learning for credit default risk prediction. Our approach incorporates two parallel tasks based on shared intermediate vectors for input vector reconstruction and credit default risk prediction, respectively. To better leverage...

Text classification enables higher efficiency on text data queries in information retrieval. However, unintended demographic bias can impair text toxicity classification. Thus, we propose a novel debiasing framework utilizing Adversarial Learning on word embeddings of multi-class sensitive demographic words to alleviate this bias. Slight adjustment...

The task of Compositional Zero-Shot Learning (CZSL) is to recognize images of novel state-object compositions that are absent during the training stage. Previous methods of learning compositional embedding have shown effectiveness in closed-world CZSL. However, in Open-World CZSL (OW-CZSL), their performance tends to degrade significantly due to th...

Membrane Capacitive Deionization (MCDI) is a promising electrochemical technique for water desalination. Previous studies have confirrmed the effectiveness of MCDI in removing contaminants from brackish groundwaters, especially in remote areas where electricity is scarce. However, as with other water treatment technologies, performance deterioratio...

The ability to evaluate uncertainties in evolving data streams has become equally, if not more, crucial than building a static predictor. For instance, during the pandemic, a model should consider possible uncertainties such as governmental policies, meteorological features, and vaccination schedules. Neural process families (NPFs) have recently sh...

Transportation is the backbone of the economy and urban development. Improving the efficiency, sustainability, resilience, and intelligence of transportation systems is critical and also challenging. The constantly changing traffic conditions, the uncertain influence of external factors (e.g., weather, accidents), and the interactions among multipl...

Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacy-preserving manner. The main challenges of FL are that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID). Due to limite...

The frequency of serious epidemics has continued to increase in the last decade. The ability to predict the risk of outbreaks can improve prevention and control. There are few prediction models available, and of these most are manually constructed by human experts. These manual models are affected by the lack of automation and have limitations in d...

Various user behaviors are providing valuable information for user interest modeling in online information platforms. For the phenomenon that some kinds of behavior data are insufficient to express users’ preferences, therefore, some cross-domain or multi-behavior fusion approaches are proposed to solve it. However, we have not yet understood which...

Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL agents could spend times either exploring informative user-item interaction trajectories or using existing traje...

Contrastive self-supervised learning has recently benefited fMRI classification with inductive biases. Its weak label reliance prevents overfitting on small medical datasets and tackles the high intraclass variances. Nonetheless, existing contrastive methods generate resemblant pairs only on pixel-level features of 3D medical images, while the func...

In the era of Internet of Things (IoT), intelligent recommendation is playing an important role in our daily life. How to provide personalized information to users is the core concern of Internet content service providers. To improve the recommendation quality, it is a hot topic to go beyond merely user–item interaction records and take social rela...

Recommender system for the IoT (RSIoT) has attracted considerable attention. By leveraging emerging technologies such as the Internet of Things (IoT), artificial intelligence, and blockchain, RSIoT improves various indicators of residents' life. However, data integrity threats may affect the accuracy and consistency of the data particularly in the...

The Internet of Things (IoT) enables the connection of a broad range of artifacts with advanced sensory technologies and produces massive amounts of data to support ambient intelligence. While the potential of IoT systems is widely recognized, little work has demonstrated a system with the ability to execute autonomously in the real world. Inspired...

The feature analysis of point clouds, a popular representation of three‐dimensional (3D) objects, is rising as a hot research topic nowadays. Point cloud data bear a sparse and unordered nature, making many commonly used feature extraction methods, for example, Convolutional Neural Networks (CNNs) inapplicable, while previous models suitable for th...

With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are dataset-specific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demograph...

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of tasks, and deep learning holds the potential to advance a multitude of applications, including in edge computing, where deep models are deployed on edge devices to enable instant data processing and response. A key challenge is that while the application of dee...

We regularly consider answering counterfactual questions in practice, such as "Would people with diabetes take a turn for the better had they choose another medication?". Observational studies are growing in significance in answering such questions due to their widespread accumulation and comparatively easier acquisition than Randomized Control Tri...

Recently, there has been a surging interest in formulating recommendations in the context of causal inference. The studies regard the recommendation as an intervention in causal inference and frame the users' preferences as interventional effects to improve recommender systems' generalization. Many studies in the field of causal inference for recom...

Recent advances in recommender systems have proved the potential of Reinforcement Learning (RL) to handle the dynamic evolution processes between users and recommender systems. However, learning to train an optimal RL agent is generally impractical with commonly sparse user feedback data in the context of recommender systems. To circumvent the lack...

Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) {\it short-term}: interaction sequences may not result from a monolithic interest, but rather from several intertw...

Recent studies demonstrate the use of a two-stage supervised framework to generate images that depict human perception to visual stimuli from EEG, referring to EEG-visual reconstruction. They are, however, unable to reproduce the exact visual stimulus, since it is the human-specified annotation of images, not their data, that determines what the sy...

Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations. A promising strategy is to learn a global-local representation that incorporates global information with extra localities (i.e., small parts/regions of inputs). However, existing methods discover localities based on explici...

Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacy-preserving manner. The main challenges of FL is that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID). Due to limited...

We prepared a special issue "Human Activity Recognition Using Sensors and Machine Learning" on Sensors. Submissions will be welcomed at any point up until 30 June 2023.

The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence. With the gradually complex human-computer interaction requirements (e.g., multimodal inputs, time sensitivity), it is difficult for tr...

Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct classification label of the time series. Multivariate time series may come from a wide range of sources and be use...

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for trai...

Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from multimodal data. These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different instituti...

Current approaches to zero-shot learning (ZSL) struggle to learn generalizable semantic knowledge capable of capturing complex correlations. Inspired by Spiral Curriculum, which enhances learning processes by revisiting knowledge, we propose a form of spiral learning that revisits visual representations based on a sequence of attribute groups (e.g....

Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}" Existing explanation methods focus on the supervised settings, \eg, node classification and graph classifica...

EEG-based tinnitus classification is a valuable tool for tinnitus diagnosis, research, and treatments. Most current works are limited to a single dataset where data patterns are similar. But EEG signals are highly non-stationary, resulting in model's poor generalization to new users, sessions or datasets. Thus, designing a model that can generalize...

With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are dataset-specific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demograph...

Understanding and forecasting mobility patterns and travel demand are fundamental and critical to efficient transport infrastructure planning and service operation. However, most existing studies focused on deterministic demand estimation/prediction/analytics. Differently, this study provides confidence interval based demand forecasting, which can...

Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding space of those techniques makes adversarial attacks challenging to detect at an early stage. Recent advance in cau...

A significant remaining challenge for existing recommender systems is that users may not trust recommender systems for either inaccurate recommendation or lack of explanation. Thus, it becomes critical to embrace a trustworthy recommender system. This survey provides a systematic summary of three categories of trust issues in recommender systems: s...

Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose...

In interactive remote medical diagnosis, medical diagnosis support system plays an important role in the pre-screening stage. Deep learning methods are widely used in such system especially medical imaging area to provide an initial diagnosis to support medical professional. However, the shortage of annotated medical images is one of the biggest ch...

Interactive recommendation is able to learn from the interactive processes between users and systems to confront the dynamic interests of users. Recent advances have convinced that the ability of reinforcement learning to handle the dynamic process can be effectively applied in the interactive recommendation. However, the sparsity of interactive da...

Contrastive self-supervised learning has recently benefited fMRI classification with inductive biases. Its weak label reliance prevents overfitting on small medical datasets and tackles the high intraclass variances. Nonetheless, existing contrastive methods generate resemblant pairs only on pixel-level features of 3D medical images, while the func...

Recommender Systems for the IoT (RSIoT) aim for interactive item recommendations. Most existing methods focus on user feedback and have limitations in dealing with dynamic environments. Deep Reinforcement Learning (DRL) can deal with dynamic environments and conduct updates without waiting for user feedback. In this study, we design a Reminder Care...

Deep neural networks currently achieve state-of-the-art performance in many multivariate time series classification (MTSC) tasks, which are crucial for various real-world applications. However, the black-box characteristic of deep learning models impedes humans from obtaining insights into the internal regulation and decisions made by classifiers....

Little attention has been paid to how to investigate crimes related to the Internet of Things (IoT). We propose a forensic investigation framework that considers various aspects of IoT devices and evaluate it with 32 users, including investigators, law enforcement officers, and incident responders.

Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, they all focus on only one of the abilities, resulting in models that are either too general with the degraded cla...

Questions in Community Question Answering (CQA) sites are recommended to users, mainly based on users’ interest extracted from questions that users have answered or have asked. However, there is a general phenomenon that users answer fewer questions while pay more attention to follow questions and vote answers. This can impact the performance when...

Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems. In most reinforcement learning applications, reward functions provide the critical guideline for optimization. However, current reinforcement learni...

Graph neural networks (GNNs) are a specialized type of deep learning models on graphs by learning aggregations over neighbor nodes. However, recent studies reveal that the performance of GNNs are severely deteriorated by injecting adversarial examples. Hence, improving the robustness of GNNs is of significant importance. Prior works are devoted to...

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards...