2026 6th International Conference on Big Data, Artificial Intelligence and Risk Management（ICBAR 2026）

As a leading role in the global megatrend of scientific innovation, We has been creating a more and more open environment for scientific innovation, increasing the depth and breadth of academic cooperation, and building a community of innovation that benefits all. Such endeavors are making new contributions to the globalization and creating a community of shared future.

2026 6th International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR 2026) will be held in Macau,China on December 10-12, 2026. Since the beginning of the 21st century, the progress of big data, artificial intelligence and risk management science has promoted the prosperity and development of the society and economy. Many universities and enterprises have developed many related technologies and products, and have achieved fruitful academic results and application transformation. The purpose of the conference is to provide experts, scholars, engineering technicians, and R&D personnel engaged in big data, artificial intelligence and risk management technology with a way to share scientific research results and cutting-edge technologies, understand academic development trends, broaden research ideas, strengthen academic research and discussion, and promote A platform for cooperation in the industrialization of academic achievements. The conference sincerely invites experts from domestic and foreign universities, scientific research institutions, scholars, business people and other relevant personnel to participate in the conference.

Abstract: Traditional machine learning constructs models by organizing knowledge from training data. Machine unlearning acts as its reverse process: it seeks to selectively erase the influence of specified training samples, concepts or memorized content from an already trained AI model, ideally making the model behave as if the target data had never been used during training. Driven by privacy regulations, user data deletion rights, removal of poisoned or biased training content, and safety requirements for large models, machine unlearning avoids the heavy cost of full retraining by developing lightweight forgetting mechanisms. This talk will introduce the core definition and paradigm of machine unlearning, distinguish exact unlearning and approximate unlearning, review representative algorithm families, and discuss key evaluation dimensions: unlearning effectiveness, preservation of model utility on remaining data, computational overhead, and verification challenges. We will also highlight open research difficulties, including knowledge entanglement in deep neural networks, persistent memorization in large language models, and attacks that recover erased information. Finally, we outline real-world application scenarios and future directions in the forgetting capability.