Data Science Seminar

This presentation explores best practices for building AI/ML and generative AI (Gen AI) models responsibly on AWS.

Legal case retrieval (LCR) is a specialised and indispensable retrieval task that focuses on retrieving relevant cases given a query case.

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.

This study investigates strategies to effectively handle challenges related to data silos.

Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner.

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.

This research introduces a corresponding attack method to uncover the actual vulnerabilities within recommender systems.

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.

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.

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.

The talk will give some background on diffusion as a Generative Model for images, and text-based imaging.

This thesis addresses this gap by proposing a triadic relationship among learning theories, educational technologies, and learning analytics.

One open research problem in this field is how do we fully automate task creation?

In this session, I will provide an overview of database integration, including the motivation, problem definition, important tasks and real-world examples.

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.

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.

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.

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

This work aims to minimise the costs associated with the process of creating systematic reviews.

Our study delves into a novel decompositional approach to enhance and evaluate text-to-image alignment.

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.

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.

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

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.

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.

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.

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.

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

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.

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.

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.

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

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.

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.

Speaker: Zichun Zhu

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

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.

Speaker: Chaoyi (Joey) Li

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

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.

Speaker: Sarah Abdulaziz Alhammad (BCompSc, MCompSc)

Speaker: Xin Xia

Speaker: Yunke Qu

Speaker: Xinyi Gao
This comprehensive experimental study demonstrates that SNS consistently outperforms existing methods in different benchmark datasets.

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

Speaker: Nathaniel du Preez-Wilkinson

Speaker: Peter Bohm

Speaker: Haoyu Ren (Technical University of Munich)

Speaker: Shengyao Zhuang

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.

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

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.

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.

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.

Speaker: Dr Qiongkai Xu, The University of Melbourne
This seminar will present research towards trustworthy AI systems.

Speaker: Rischan Mafrur

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.

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

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

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.

Speaker: Yixuan Qiu

Speaker: Dr Yanbin Liu (Australian National University)

Speaker: Ruiqi Zheng

Speaker: Guanhua Ye

Speaker: Wei Yuan

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.

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.

Speaker: Ziyi Liu

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.

Speaker: Ms Fengmei Jin

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.

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.

Speaker: Mr Jordan Bishop

Speaker: Mr Zijian Wang

Speaker: Shiva Shabaninejad

Speaker: Kaiyu Guo

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.

Speaker: Mr Junliang Yu
In this presentation, we systematically investigate self-supervised recommender systems.

Speaker: Jing Long

Speaker: Sara Hajari

Speaker: Bing Liu

Join us as we discuss the first comprehensive taxonomy of NFQ categories and the expected structure of answers.

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.

Join us as we discuss a novel boosting algorithm for PU learning: Ada-PU, which compares against neural networks.

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.

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.

Join us as we discuss a proposed generative scrubbing (GS) method that learns a generator to craft noisy data to manipulate the model weights.

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.

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.

Join us as we discuss the topic of "Australian Digital Observatory?" on our weekly Data Science seminar series.

Join us as we discuss the topic of "Learning with Noisy Labels?" on our weekly Data Science seminar series.

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

Join us as we discuss the topic of "Towards Developing Efficient Vision Transformer" on our weekly Data Science seminar series.

Join us as we discuss the topic of "Improving Performance of Lightweight Networks via Knowledge Distillation" on our weekly Data Science seminar series.

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.

Join us as we discuss the topic of "An Overview of Recent Advances in Neural Information Retrieval" on our weekly Data Science seminar series.

Join us as we discuss the topic of "Butterfly Counting on Uncertain Bipartite Graphs" on our weekly Data Science seminar series.

Join us as we discuss the topic of "Diversity and Fairness from a Ranking Evaluation Perspective" on our weekly Data Science seminar series.

Join us as we discuss the topic of "Socio-Economic Diversity in Human Annotations."

Join us as we discuss the topic of "A Conceptual Framework for a Representational Approach to Information Retrieval."

Join us for an exciting seminar on the topic of "Self-Supervised Learning for Recommender Systems: Fundamental and Advances."

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.

Join us for an exciting seminar on the topic of "Unified Question Generation with Continual Lifelong Learning."

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

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.