Keynote Speaker

Keynote:
Towards Automated Artificial Intelligence via Automated Algorithm Selection

Heike Trautmann (Paderborn University, Germany)

Abstract:

Robust Automated Algorithm Selection is of crucial importance for constructing high-performing automated AI systems. It has long been observed that for practically any computational problem that has been intensely studied, different problem instances are best solved using different algorithms. This is particularly pronounced for computationally hard problems, where in most cases, no single algorithm defines the state of the art; instead, there is a set of algorithms with complementary strengths. This performance complementarity can be exploited in various ways, one of which is based on the idea of selecting, from a set of given algorithms, for each problem instance to be solved the one expected to perform best. The task of automatically selecting an algorithm from a given set is known as the per-instance algorithm selection problem and has been intensely studied over the past 15 years, leading to major improvements in the state of the art in single-objective continuous black-box optimisation and in solving a growing number of discrete combinatorial optimisation tasks, including traveling salesperson problems.

Short Bio:

Heike Trautmann is Professor of Machine Learning and Optimization at Paderborn University, Germany. Her research mainly focuses on (Trustworthy) Artificial Intelligence, Machine Learning, Data Science, Automated Algorithm Selection and Configuration, Exploratory Landscape Analysis, (Multiobjective) Evolutionary Optimisation and Data Stream Mining. She is also (Guest) Professor of Data Science in the Data Management and Biometrics group at the University of Twente, Netherlands. Moreover, she serves as key supporter of the Confederation of Laboratories for Artificial Intelligence Research in Europe (CLAIRE), founder and member of the Configuration and Selection of Algorithms (Coseal) Network and Member of the European Research Center for Information Systems (ERCIS) leading the AI and Data Science research cluster.

Keynote:
Recent Advances in Graph Neural Networks:

Concepts, Applications, and Future Directions

Ting Zhong (University of Electronic Science and Technology of China, China)

Abstract:
Graph Neural Networks (GNNs) have garnered significant attention in recent years for their capabilities to learn high-dimensional and unstructured graph data. This keynote delves into the theories and applications of GNNs, highlighting recent state-of-the-art models in a variety of domains. We provide an overview of the basic concepts in GNNs, including graph convolutional networks and attention mechanisms, and discuss their applications in real-world applications. Furthermore, we showcase our lab’s research efforts in enhancing GNNs, focusing on novel architectures, optimization techniques, explainable predictions, and graph foundation models. By combining insights from cutting-edge research and our own contributions, this keynote offers a comprehensive understanding of the current landscape and future directions of Graph Neural Networks.
Short Bio:

Ting Zhong received the B.S. degree in computer application and the M.S. degree in computer software and theory from Beijing Normal University, Beijing, China, in 1999 and 2002, respectively, and the Ph.D. degree in information and communication engineering from the University of Electronic Science and Technology of China (UESTC), Chengdu, China, in 2009.,She is a Full Professor with UESTC. Her current research interests include deep learning, social networks, and cloud computing.

Keynote:
Empowering Proactive Data Mining Strategies through Generative AI

Teddy Mantoro (Sampoerna University, Indonesia)

Abstract:
The artificial intelligence (AI) landscape in data mining is undergoing a major transformation, transitioning from predictive models to generative frameworks. This shift signals more than just a change in approach; it represents a fundamental evolution in extracting insights from large amounts of data. This new approach promises to reshape data mining by not only predicting but also creating new possibilities. Generative AI empowers proactive data mining strategies, not just by predicting the future, but by actively creating it. By unlocking hidden potential in data and generating new possibilities, generative AI drives innovation and facilitates data-driven decision-making, resulting in a more impactful and transformative approach to proactive data-mining strategies. By leveraging generative AI, any organization can predict outcomes and actively shape and create new types of data in text, image, or video. The capabilities of generative models are explored in their ability to synthesize new data points, discover patterns, and even generate new hypotheses. Furthermore, this study focuses on how these changes empower organizations to adopt a proactive approach, enabling them to anticipate trends, identify opportunities, and mitigate risks before they materialize. Through real-world examples and case studies, the transformative potential of generative AI in data mining will be presented to provide insight into how AI can drive innovation across industry and government agencies.
Short Bio:
Teddy Mantoro is a Professor of Computer Science in the areas of Artificial Intelligence, Mobile Computing, Information Security, Wireless Sensor Networks, and Intelligent Environment. He obtained a PhD, an MSc, and a BSc, all in Computer Science. His PhD was obtained from the School of Computer Science, the Australian National University (ANU), Canberra, Australia (2006) and his MSc was from the School of Computer Science, Asian Institute of Technology, Bangkok, Thailand (1994). He is a Senior Member of IEEE (2013) and a Professional Member of ACM (Association for Computing Machinery). He is the chair of IEEE Computational Intelligence Society, Indonesia Chapter dan Indonesian Neural Network Society (IdNNS). He was the General Chair of many international conferences, including ICONIP 2021, ICCED 2017-present, and IC2IE 2019-present. He has received 20+ research grants to date. From 2009 – to date, he has received 5 Gold, 9 Silver, and 11 Bronze Medals from International IT Innovation Competitions. He has published 275+ conference/journal papers. He was the chief judge and the problem setter coordinator for ACM-ICPC Malaysia National level 2010-2017 (8 years), the chief judge of Asia programming regional contest in the Kuala Lumpur site, and an honorary judge in the Jakarta site for many years as well. In Malaysia, he has filed 4 (four) patents in credit to his name. He can be contacted at email: teddy@ieee.org.