Data Science Seminar

This seminar series is hosted by EECS Data Science.

Contacts

Dr Ruihong Qiu

Self-Supervised Learning for Irregular Time Series

16 July 2024 11:00am
Our primary research question is how we can effectively utilize limited labelled data for irregular time series modelling?

Information-Preserving Efficient Vision Transformers

2 July 2024 2:00pm
In this presentation, we focus on expediting ViTs while maintaining high performance.

Efficient Visual Learning via Compression of Representations, Models and Datasets

2 July 2024 1:00pm
This presentation proposes a series of compression approaches to reduce the computation complexity and memory usage of deep models for efficiency improvement.

Entity Alignment for Evolving Temporal Knowledge Graphs

25 June 2024 2:00pm
Entity Alignment (EA) is crucial for integrating heterogeneous knowledge graphs (KGs) into a unified knowledge base by identifying equivalent entities across them.

Towards Emotionally Music Generation: Enhancing Mood Through AI-Composed Soundscapes

24 June 2024 12:00pm
This talk explores the significance of personalization and its potential impact on mood improvement through AI-Composed Soundscapes.

Symptom Checkers, Search Engines and Conversational Agents for Online Health Information Seeking

19 June 2024 10:00am
This presentation explores the comparative efficacy and influencing factors of three major platforms: Search Engines, Symptom Checkers, and Large Language Model (LLM)-powered Conversational Agents.

Toward Memory-Efficient Recommender Systems

12 June 2024 1:00pm
Extensive experiments on public benchmark datasets have verified the effectiveness of the two proposed works in retaining excellent recommendation performance.

Distribution system state estimation: monitoring and characterization of active distribution networks

29 May 2024 11:00am
This presentation shows results both on synthetic data and real network+smart meter data from a Belgian system operator.

Generative Sequential Recommendation

22 May 2024 3:00pm
In this talk, we introduce the Sequential Recommendation problem and draw parallels between language modelling and recommender systems.

Multi-modal Learning for Effective In-the-Wild Plant Disease Detection

21 May 2024 10:00am
Plant disease recognition aims to identify disease through visual symptoms, and has a profound impact on agricultural production and food safety.

Efficient and Elastic Large Models

17 May 2024 3:00pm
In this talk, we will discuss the key challenges in improving efficiency of LLM serving.

Evolving Modular Neural Networks: Investigating the Role of Modularity and Linkage Learning in Neuroevolution

17 May 2024 1:00pm
This presentation investigates the role of modularity in advancing neuroevolution algorithms and proposes novel techniques that exploit this property to evolve efficient neural networks.

Deep Copula-Based Survival Analysis for Dependent Censoring

24 April 2024 1:00pm
This talk will discuss a flexible survival analysis method that simultaneously accommodates dependent censoring and eliminates the requirement for specifying the copula.

Conveying Complex Information in Multi-modal Dialogue Generation through Event, Knowledge and Reasoning

23 April 2024 1:30pm
We target conveying more complex information into multi-modal dialogue generation with events, knowledge and reasoning.

Modelling AI-informed Online Opinion Dynamics

19 April 2024 2:00pm
With the massive development in Information Communication Technology (ICT) in the past decades, people nowadays are used to fast-paced and real-time information exchange and public opinion deliberation.

Investigating the role of metadata in evaluating the data quality of repurposed data

15 April 2024 2:00pm
This PhD research investigates the critical yet under-explored role of metadata in evaluating the quality of repurposed data.

Automated Curriculum Learning for Dynamic Robot Behaviours

10 April 2024 2:00pm
In this research, we explore the under-researched and challenging area of full-body manipulation tasks for robotics.

Towards Open-World Object Segmentation and Detection

10 April 2024 1:00pm
In this talk, I will introduce a few works that have been done in my group showing the trends from close-set to open-set and to open-world.

Effective and Secure Federated Online Learning to Rank

10 April 2024 10:00am
In this thesis, we comprehensively investigate the aforementioned challenges and build effective, secure federated online learning to rank methods.

Informative Representation Learning with Multimodal Data Fusion

4 April 2024 2:00pm
This research addresses the imperative need for informative representation learning through multimodal data fusion techniques.

Federated Graph Neural Network-based Recommender Systems

26 March 2024 1:00pm
This seminar introduces several innovations to address challenges of federated GNN-based recommender systems including performance degradation, inflexible architectures, slow convergence, and the demand for substantial local storage resources.

Advancing Machine Unlearning in Deep Models: Causal Insights, Efficiency, and Effectiveness

26 March 2024 11:00am
The overall aim of this research is to advance the field of machine unlearning in the aspects of causal insights, efficiency, and effectiveness.

Advancements in Time Series Analysis: from Regular to Anomalous, Cloud-based to On-Device, and Univariate to Multivariate

26 March 2024 10:00am
This seminar explores the latest advancements in time series analysis by examining three key aspects: pattern recognition, on-device applications, and complex multivariate time series modelling.

Potential and limitations of using LLMs for personalized advertising

22 March 2024 2:00pm
This presentation investigates the potential of large language models (LLMs) for generating personalized online advertisements tailored to specific personality traits and the implications of such technology for political advertising, combining insights from two studies.

Building AI/ML & Gen AI responsibly on AWS

13 March 2024 1:00pm
This presentation explores best practices for building AI/ML and generative AI (Gen AI) models responsibly on AWS.

Effective Representation Learning for Legal Case Retrieval

12 March 2024 10:00am
Legal case retrieval (LCR) is a specialised and indispensable retrieval task that focuses on retrieving relevant cases given a query case.

Filter Bubble in Recommender System: Diversity and Beyond

7 March 2024 1:00pm
In this talk, we first discuss one of the most important aspects of the filter bubble, recommendation diversity, particularly diversified recommendation models and full-stage large-scale online experiments on short-video platforms.

Adaptive Collaborative Learning with Data Silos

13 February 2024 11:00am
This study investigates strategies to effectively handle challenges related to data silos.

Continual Graph Learning with Graph Condensation

25 January 2024 10:00am
Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner.

Sensemaking in Multi-artefact Information Tasks

23 January 2024 1:00pm
The research findings provide novel insights and understanding of the sensemaking processes in various settings and contribute to modelling practice and the design of supporting tools.

Multimodal Recommender Systems: Threats and Countermeasures in the Generative AI Era

15 December 2023 2:00pm
This research introduces a corresponding attack method to uncover the actual vulnerabilities within recommender systems.

Summer of AI 2023 Keynotes

14 December 2023 12:00pm
Join us at the 2023 Summer of AI (SAI) from 11-15 December, where you'll hear from UQ's two new Professors of AI, as well as some of our leading academics in the field.

AI and HPC Infrastructure at UQ in the next 12 to 24 months

13 December 2023 2:00pm
This talk will provide an inside view of what AI/ML/DL infrastructure UQ RCC has available right now and an early view of what is coming next.

Summer of AI 2023 Keynotes

11 December 2023 12:00pm
Join us at the 2023 Summer of AI (SAI) from 11-15 December, where you'll hear from UQ's two new Professors of AI, as well as some of our leading academics in the field.

Diffusion and text-based guidance for image morphing

8 December 2023 10:00am
The talk will give some background on diffusion as a Generative Model for images, and text-based imaging.

Synergising Learning Theory, Learning Analytics, and Educational Technologies

7 December 2023 1:00pm
This thesis addresses this gap by proposing a triadic relationship among learning theories, educational technologies, and learning analytics.

AlgorithmOS, a self organising modular framework for the implementation of algorithmic research

27 November 2023 11:00am
One open research problem in this field is how do we fully automate task creation?

Database integration in multidatabase systems

8 November 2023 11:45am
In this session, I will provide an overview of database integration, including the motivation, problem definition, important tasks and real-world examples.

Measurement, Scales, Averages, Meaningfulness

7 November 2023 10:00am
In this talk, we will introduce the fundamental notions about scales of measurement and meaningfulness, and we will show how they apply to IR evaluation measures.

Large Language Models: Risks, Opportunities and Responses

29 October 2023 2:00pm
This talk will give a high level overview of Large Language Models and present my thoughts on the potential benefits and likely risks of AI and what we should be doing about them.

Process Mining: Opportunities and Challenges

18 October 2023 1:00pm
In this talk I will first briefly introduce my previous work in Immersive Analytics, which includes the visualisation of abstract and 3D data in multiple XR scenarios.

On using language models for relevance labelling

16 October 2023 2:00pm
Speaker: Dr Paul Thomas, Microsoft
We report on experiments using GPT-4, a recent large language model, to label documents for relevance.

AI-driven Approaches for Effective Systematic Review Literature Screening

13 October 2023 3:00pm
This work aims to minimise the costs associated with the process of creating systematic reviews.

Evaluating and Improving Text to Image Alignment with Latent Diffusion Models

4 October 2023 1:00pm
Our study delves into a novel decompositional approach to enhance and evaluate text-to-image alignment.

Igniting Innovation: How Queensland's AI Hub Fuels Growth and Opportunity

20 September 2023 3:00pm
Speaker: Toni Peggrem
Are you interested in the future of artificial intelligence (AI) in Queensland? Join us for an exclusive one-hour talk into the Queensland AI Hub.

Immersive Data Visualisation and Interactive AI

20 September 2023 1:00pm
Speaker: Dr Maxime Cordeil (University of Queensland)
In this talk I will first briefly introduce my previous work in Immersive Analytics, which includes the visualisation of abstract and 3D data in multiple XR scenarios.

Towards Cost-Efficient Federated Multi-Agent Reinforcement Learning with Learnable Aggregation

20 September 2023 1:00pm
Speaker: Yi Zhang
We introduce a client-server framework designed to fortify MARL in real-world scenarios, achieving scalability, parallelization, and privacy preservation.

Enhancing Vision-and-Language Navigation with Multi-modal Prompts

20 September 2023 12:00pm
Speaker: Haodong Hong
Our research introduces a novel task, Vision-and-Language Navigation with Multi-modal Prompts (VLN-MP), in which instructions consist of both natural language and images as prompts.

Model Selection and Model Generalizability of Deep Neural Networks

19 September 2023 2:00pm
Speaker: Ekaterina Khramtsova
In this research, we explore various methods for assessing the generalisability of Deep Neural Networks on OOD samples within different scenarios, namely for model selection and for performance estimation.

Towards Robustness: Boosting Approaches for Learning from Positive and Unlabeled Data

19 September 2023 2:00pm
Speaker: Yawen Zhao
By overcoming three key challenges, we aim to work towards PU boosting methods which have superior performance alongside computational efficiency and minimal dependence on hyperparameter tuning.

Empowering Foundation Models for Unsupervised Bi-Temporal Analysis in Satellite Imagery

14 September 2023 11:30am
Speaker: Yiyun Zhang
In this study, we propose novel unsupervised approaches for BTRS analysis, specifically focusing on change and damage detection in buildings, without the need to use any annotations.

Graph Neural Networks for Large Dynamic Graphs

13 September 2023 1:00pm
Speaker: Yanping Zheng (DATA61-CSIRO)
My research focuses on improving the scalability and expressiveness of dynamic graph neural networks.

Generating data-driven continuous optimization problems for benchmarking

8 September 2023 11:00am
Speaker: Sara Hajari
In this research, a detailed exploration of problem instance generation is carried out, and possible ways this approach can be used in benchmarking practice are discussed.

Trustworthy Recommendation under Limited Data

7 September 2023 11:00am
Speaker: Chenhao Zhang
My research aims to improve recommendation systems in low-data scenarios, benefiting small and medium-sized companies and responding to public emergencies.

Machine learning guided scientific experiments

6 September 2023 3:00pm
Speaker: Cheng Soon Ong, Data61, CSIRO
The AI hype claims that everything can be solved by AI. The reality is that while there are many exciting advances in recent years, many open problems remain.

Automating Expertise in Format Identification: From Experts, Through Novices, to Machines

4 September 2023 12:30pm
Speaker: Shaochen Yu
As the role of data amplifies in decision-making, our methodologies promise efficient and streamlined solutions in format identification.

On the Role of Human and Machine Metadata in Crowdsourced Data Annotation

4 September 2023 11:00am
Speaker: Jiechen Xu
The process of data annotation, also referred to as data labeling, is a crucial step in various research fields like machine learning and behavioral studies.

Generalized Out-of-distribution Detection: Theory and Algorithm

23 August 2023 1:00pm
Speaker: Dr Zhen Fang (University of Technology Sydney)
In this talk, we will present the latest advancements in OOD detection theory, and OOD detection algorithms.

A Study on Practical Bluetooth Map-matching

22 August 2023 11:00am
Speaker: Zichun Zhu

Progressive Image generation between large gap domains with hierarchical disentangled representations

17 August 2023 10:00am
Speaker: Tianren Wang
This project will study the explicit form of a latent space to make the learning process more accurate and interpretable.

How to Detect Out-of-Distribution Data in the Wild? Challenges, Research Progress and Path Forward

16 August 2023 10:00am
Speaker: Sharon Yixuan Li (University of Wisconsin-Madison)
I will introduce a new algorithmic framework, which jointly optimizes for both accurate classification of ID samples, and reliable detection of OOD data.

Data Analysis for Multimedia

9 August 2023 1:00pm
Speaker: Prof Phoebe Chen (La Trobe University)
There is a large number of possible applications that can benefit from the analysis of multimedia data.

Task-aware Retrieval with Instructions

2 August 2023 1:00pm
Speaker: Akari Asai (University of Washington)
We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries.

Memory-efficient Recommendation

12 June 2023 3:00pm
Speaker: Yunke Qu

Mitigating Imbalanced Data Distribution in Heterogeneous Information Networks

12 June 2023 2:00pm
Speaker: Xinyi Gao
This comprehensive experimental study demonstrates that SNS consistently outperforms existing methods in different benchmark datasets.

Estimating Causal Effect: Challenges and Countermeasures

12 June 2023 1:00pm
Speaker: Hechuan Wen
Causal inference is increasingly important in guiding decision-making in high-stake domains, such as healthcare, education, e-commerce, etc.

Smart Things in Industrial IoT

31 May 2023 1:00pm
Speaker: Haoyu Ren (Technical University of Munich)

An introduction to sequential/session-based recommendation

17 May 2023 1:00pm
Speaker: Dr Shoujin Wang (University of Technology Sydney)
In recent years, sequential/session-based recommendations have emerged as a new recommendation paradigm to well model users’ dynamic and short-term preferences for more accurate and timely recommendations.

Building Experiment Tracking at Scale with Weights & Biases

10 May 2023 1:00pm
Speaker: Andrea Parker, Growth ML Engineer (Weights & Biases)
Join us to learn all about experiment tracking at scale with Pachyderm and Weights & Biases.

SEINE: SEgment-based Indexing for NEural Information Retrieval

3 May 2023 10:00am
Speaker: Dr Grace Hui Yang (Georgetown University)
We propose a novel SEgment-based Neural Indexing method, SEINE, which provides a general indexing framework that can flexibly support a variety of interaction-based neural retrieval methods.

Towards algorithms on grammar-compressed strings, trees, and graphs

28 April 2023 1:00pm
Speaker: Prof Stefan Böttcher - Universität Paderborn (Germany)
This talk gives an overview of the key ideas behind grammar-based compression techniques for strings, trees, and graphs.

Mobility Digital Twin for Connected and Automated Vehicles

26 April 2023 1:00pm
Speaker: Dr Ziran Wang (Purdue University)
In this talk, a Mobility Digital Twin (MDT) framework is introduced, which is defined as an Artificial Intelligence (AI)-based data-driven cloud-edge-device framework for mobility services.

Towards Trustworthy AI

21 April 2023 11:00am
Speaker: Dr Qiongkai Xu, The University of Melbourne
This seminar will present research towards trustworthy AI systems.

Sparks between Data Analytics and Graphs

13 April 2023 2:00pm
Speaker: Dr Shixun Huang (RMIT University)
In this talk, recent advances under multiple fields (i.e., data mining, viral marketing and urban computing) of graph analytics will be introduced.

Optimising LiDAR-Based 3D Object Detection with Limited Labels

31 March 2023 1:30pm
Speaker: Zhuoxiao (Ivan) Chen
Our research focuses on optimising the model performance for 3D object detection, especially when the labelling budget is limited.

Concept drift adaptation for multiple streams with temporal dependence

27 March 2023 4:00pm
Speaker: Dr Yiliao Song, RMIT University
Real-time decision-making for streaming data is facing a common but challenging problem, concept drift.

A magic ingredient, a secret spice, a special blend, for it can all be nice!' The Human Quotient for Better AI Systems

22 March 2023 1:00pm
Speaker: A/Prof Ujwal Gadiraju (Delft University of Technology, the Netherlands)
This talk will discuss the intriguing and pertinent role of human input in propelling better AI technology in the quickly evolving age of generative models.

Multi-Domain Few-Shot Image Classification

15 March 2023 1:00pm
Speaker: Dr Yanbin Liu (Australian National University)

AutoML for On-device Recommender Systems

14 March 2023 3:30pm
Speaker: Ruiqi Zheng

Efficient Distributed Complex Event Processing

9 March 2023 1:00pm
Speaker: Dr Matthias Weidlich (Humboldt-Universität zu Berlin (HU))
In this talk, we present some of our recent results on achieving such distribution with the model of MuSE graphs as well as optimizations that rely on push-pull-communication.

Score based Diffusion Models and Their Applications

8 March 2023 1:00pm
Speaker: Dr Jing Zhang (Australian National University)
In this talk, we will explain the basic idea of score-based diffusion models, and explore its potential in 2D/3D vision tasks.

Seven Algorithms for the Same Task (Testing Uniformity)

1 March 2023 1:00pm
Speaker: Dr Clément Canonne (University of Sydney)
In this talk, I will survey and discuss seven algorithms for uniformity testing, and explain some of their (dis)advantages.

Escaping the Echo Chamber: The Quest for Normative News Recommender Systems

22 February 2023 1:00pm
Speaker: Prof Abraham Bernstein (University of Zurich)
This talk highlights that computer science needs to increasingly engage with both the social and normative challenges of our work, possibly producing a new understanding of our discipline.

Improving Discriminative Retrieval Models Using Generative Tasks

20 February 2023 10:00am
Speaker: Professor Shane Culpepper, RMIT University
In this talk, we will discuss a novel multi-task learning approach which can be used to produce more effective neural ranking models.

Addressing Domain Shift in an Open World

19 January 2023 8:30pm
Speaker: Mr Zijian Wang

Multi-modal Data Modelling with Awareness of Efficiency, Reliability, and Privacy

8 December 2022 10:00am
Speaker: Mr Pengfei Zhang
Due to the inherent nature of data acquisition and generation, certain concerns surrounding responsible multi-modal data modelling are raised, including efficiency, reliability, and privacy.

Self-Supervised Recommender Systems

5 December 2022 1:00pm
Speaker: Mr Junliang Yu
In this presentation, we systematically investigate self-supervised recommender systems.

Decentralized POI Recommendation Systems

2 December 2022 1:00pm
Speaker: Jing Long

Towards Practical Neural Entity Alignment

23 November 2022 10:00am
Speaker: Bing Liu

A Non-Factoid Question-Answering Taxonomy

9 November 2022 1:00pm
Join us as we discuss the first comprehensive taxonomy of NFQ categories and the expected structure of answers.

LibAUC: A deep learning library for X-risk Optimization

26 October 2022 1:00pm
In this talk, Tianbao Yang will present recent research efforts into developing a deep learning library called LibAUC, which is applicable for solving a variety of compositional measures.

A Boosting Algorithm for Positive-Unlabeled Learning

19 October 2022 1:00pm
Join us as we discuss a novel boosting algorithm for PU learning: Ada-PU, which compares against neural networks.

Non-blocking Asynchronous Training for Reinforcement Learning in Real-World Environments

10 October 2022 1:00pm
Join us as we discuss a non-blocking and asynchronous DRL training architecture for non-linear, real-time dynamical systems tailored to handling variable delays.

Advancing Machine Perception for Artificial Intelligence Systems

5 October 2022 1:00pm
Join us as 2022 DECRA Fellow Dr Xin Yu discuss recent research results on machine perception algorithms in surveillance systems as well as in AI assisted medical diagnosis.

Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach

21 September 2022 1:00pm
Join us as we discuss a proposed generative scrubbing (GS) method that learns a generator to craft noisy data to manipulate the model weights.

Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation

14 September 2022 1:00pm
Join us as we discuss a more versatile setting of MSDA, namely Generalized Multi-source Domain Adaptation, wherein the source domains are partially overlapped, and the target domain is allowed to contain novel categories.

Can Pretrained Language Models Generate Persuasive, Faithful, and Informative Ad Text for Product Descriptions?

7 September 2022 1:00pm
For any e-commerce service, persuasive, faithful, and informative product descriptions can attract shoppers and improve sales. While not all sellers are capable of providing such interesting descriptions, a language generation system can be a source of such descriptions at scale, and potentially assist sellers to improve their product descriptions.

Australian Digital Observatory

3 August 2022 1:00pm
Join us as we discuss the topic of "Australian Digital Observatory?" on our weekly Data Science seminar series.

Learning with Noisy Labels

29 July 2022 1:00pm2:00pm
Join us as we discuss the topic of "Learning with Noisy Labels?" on our weekly Data Science seminar series.

Are Labels Always Necessary for Model Evaluation?

1 June 2022 1:00pm
Join us as we discuss the topic of "Are Labels Always Necessary for Model Evaluation?" on our weekly Data Science seminar series.

Towards Developing Efficient Vision Transformer

25 May 2022 1:00pm
Join us as we discuss the topic of "Towards Developing Efficient Vision Transformer" on our weekly Data Science seminar series.

Improving Performance of Lightweight Networks via Knowledge Distillation

18 May 2022 1:00pm
Join us as we discuss the topic of "Improving Performance of Lightweight Networks via Knowledge Distillation" on our weekly Data Science seminar series.

Improving Robustness of Deep Learning Models on Out-of-domain Data

11 May 2022 1:00pm
Join us as we discuss the topic of "Improving Robustness of Deep Learning Models on Out-of-domain Data" on our weekly Data Science seminar series.

An Overview of Recent Advances in Neural Information Retrieval

4 May 2022 1:00pm
Join us as we discuss the topic of "An Overview of Recent Advances in Neural Information Retrieval" on our weekly Data Science seminar series.

Butterfly Counting on Uncertain Bipartite Graphs

29 April 2022 2:00pm
Join us as we discuss the topic of "Butterfly Counting on Uncertain Bipartite Graphs" on our weekly Data Science seminar series.

Diversity and Fairness from a Ranking Evaluation Perspective

27 April 2022 1:00pm
Join us as we discuss the topic of "Diversity and Fairness from a Ranking Evaluation Perspective" on our weekly Data Science seminar series.

Socio-Economic Diversity in Human Annotations

13 April 2022 1:00pm
Join us as we discuss the topic of "Socio-Economic Diversity in Human Annotations."

A Conceptual Framework for a Representational Approach to Information Retrieval

7 April 2022 9:00am10:00am
Join us as we discuss the topic of "A Conceptual Framework for a Representational Approach to Information Retrieval."

Self-Supervised Learning for Recommender Systems: Fundamental and Advances

30 March 2022 1:00pm2:00pm
Join us for an exciting seminar on the topic of "Self-Supervised Learning for Recommender Systems: Fundamental and Advances."

Graph Mining and Applications

23 March 2022 1:00pm
Join us for an exciting seminar. Graph data mining is currently a hot research topic that attracts more and more attentions from industry and academic fields.

Unified Question Generation with Continual Lifelong Learning

16 March 2022 1:00pm
Join us for an exciting seminar on the topic of "Unified Question Generation with Continual Lifelong Learning."

PipAttack: Poisoning Federated Recommender Systems for Manipulating Item Promotion

9 March 2022 1:00pm
Join us for an exciting seminar on the topic of "PipAttack: Poisoning Federated Recommender Systems for Manipulating Item Promotion." *Pip is the package installer for Python
Rethink e-Commerce Search

Rethink e-commerce search

23 February 2022 1:30pm
Join us for an exciting seminar on the quality of user search experience on e-commerce websites and the role it plays in customer conversion.