| |
 | | Date: | 20 October 2023, Friday | | Time: | 3:30pm to 5:15pm | | Venue: | Seminar Room B1-1, Basement 1
School of Economics/School of Computing & Information Systems 2 |
|
Limited seating. Registration will close on 18 October 2023 or once maximum capacity is reached. Registration is required for attendance. | Research Cluster: Artificial Intelligence & Data Science | | | | Topic: | Low-Resource Learning on Graphs
| | Speaker: | FANG Yuan, Assistant Professor of Computer Science
| | Abstract: | Graph structures are ubiquitous in various domains, ranging from social networks and e-commerce platforms to transportation and biological systems. On these graphs, various graph-based analytics and mining tasks exist, many of which can be cast as instances of link prediction, node classification, and graph classification. Moving away from manual feature engineering, graph neural networks (GNN) have witnessed widespread success in various application scenarios due to their ability to learn powerful graph representations automatically. However, their success is often dependent on the availability and quality of graph structures and labeled data, without which their performance can suffer. In this talk, we explore alternative learning paradigms different from the traditional supervised learning paradigm, specifically addressing two types of low-resource scenarios on graphs: structure scarcity and label scarcity. We will first provide an overview of low-resource problems and methods on graphs, and then introduce some of our representative works on these problems. |
|
| | | Research Cluster: Human-Machine Collaborative Systems | | | | Topic: | Understanding and Supporting Collaboration with Agents, Robots and People
| Speaker:
| Tony TANG, Associate Professor of Computer Science; Member, SMU Institutional Review Board
| | Abstract: | In this talk, I discuss our research group’s efforts to design and evaluate effective forms of collaboration between humans, agents, and robots. We will explore, through six example projects, how interaction through computing can be seen through the lens of collaboration. Then, I will show that understanding how *humans* interact with one another provides design opportunities for designing new forms of human-*computer* interaction, be it with agents or robots. |
|
| | | Research Cluster: Information Systems & Technology | | | | Topic: | Unveiling the Code Model Enigma: Interpreting the Gap Between AI and Human Intuition in Code Clone Detection
| | Speaker: | Shamsa ABID, Research Scientist
| | Abstract: | Semantic code clone detection remains a challenging task in the realm of software engineering. While AI models are reportedly accurate, they often fail to generalize to other codebases, raising questions about their reliability and trustworthiness. We need ways to understand or interpret the decision-making behavior of the code models and evaluate whether it aligns with human intuition. In this direction, our goal is to evaluate the performance of models in relation to human intuition using counterfactual data mutations. In this talk, I will discuss how we create a human-labeled dataset of code regions of core and non-core similarities and differences, and how we perturb code clone pairs systematically to examine shifts in prediction. Our findings have practical implications, aiding researchers and end-users in choosing code clone detection models more effectively. |
| | | | | | ABOUT THE SPEAKER(S) | | | |  | Dr. Yuan Fang is an Assistant Professor at the School of Computing and Information Systems at Singapore Management University (SMU). He was previously a data scientist at DBS Bank and a research scientist at A*STAR. His research interests revolve around graph-based learning and its applications in recommender systems, social network analysis, and bioinformatics.
| | | |  | Anthony (Tony) TANG is an Associate Professor in the School of Computing and Information Systems at the Singapore Management University. He leads the RICELab (Rethinking Interaction, Collaboration and Engagement) group, which focuses on Human-Computer Interaction, Computer Supported Cooperative Work and Ubiquitous Computing. Tony's work explores how to give people new ways of thinking about and interacting with people, data, agents, and robots. His current work explores how we can apply our understanding human communication, coordination and collaboration dynamics to the design of human-AI interaction. His work has been generously supported by Singapore's Ministry of Education, Canada's National Science and Engineering Research Council, MITACS, and from industry including as NAVER AI, Autodesk Research, and Nokia Research.
| | | |  | Dr. Shamsa Abid is currently working as a Research Scientist in the Centre for Research on Intelligent Software Engineering (RISE) at Singapore Management University under the supervision of Prof. Lingxiao Jiang. Before that, she was an Intern at JetBrains, where she refined her Ph.D. thesis work to develop a large-scale context-sensitive code recommendation plugin for the Intellij IDE. She obtained her Ph.D. in Computer Science from the Syed Babar Ali School of Science and Engineering (SBASSE) at LUMS, Lahore in 2021. Previously, she has held teaching positions for various computer science courses including Web Programming, Software Quality Assurance, and Creating Digital Content. She also has industry experience working as a Senior Software Engineer at Techlogix Pvt. Ltd. and as a Software Engineer at Xavor Pvt. Ltd. Currently, her research focuses on Explainable AI for code models where model interpretability, trustworthiness, and causality are her core research interests. She actively provides research paper review services and has been a committee member for the International Conference of Software Engineering (ICSE 2023) Demonstration Track, the Mining Software Repositories (MSR 2023) Industry Track, and the International Workshop on Interpretability, Robustness, and Benchmarking in Neural Software Engineering (InteNSE'23). |
| | | | SEMINAR MODERATOR | | |  | David LO
OUB Chair Professor of Computer Science
Director Information Systems & Technology Cluster
Director, Centre for Research for Intelligent Software Engineering |
|
|
|
|
