報(bào)告題目：Towards Trustworthy Learning and Reasoning under Noisy Data

報(bào)告時(shí)間：2023年5月8日9:00

報(bào)告地點(diǎn)：線上騰訊會(huì)議（#騰訊會(huì)議：831-191-110）

報(bào)告人：韓波

報(bào)告人國籍：中國

報(bào)告人單位：香港浸會(huì)大學(xué)

報(bào)告人簡介：韓波，香港浸會(huì)大學(xué)計(jì)算機(jī)系助理教授，領(lǐng)導(dǎo)TMLR研究組。他同時(shí)兼任RIKEN人工智能項(xiàng)目梅峰訪問科學(xué)家，并曾兼任Microsoft研究院訪問科學(xué)家。他于2019-2020年博士后于RIKEN人工智能項(xiàng)目；2019年博士畢業(yè)于悉尼科技大學(xué)。他的研究廣泛涉獵了機(jī)器學(xué)習(xí)的諸多理論和實(shí)踐領(lǐng)域，目前關(guān)注重點(diǎn)包括可信賴表示學(xué)習(xí)，因果表示學(xué)習(xí)，基礎(chǔ)模型等方法，以及這些方法在自然科學(xué)和交叉學(xué)科的應(yīng)用。他的研究得到眾多政府和業(yè)界資金支持，并獲得眾多獎(jiǎng)項(xiàng)，包括三項(xiàng)政府研究獎(jiǎng) (RGC CAREER, NSFC Young Scientist, RIKEN BAIHO)，和五項(xiàng)企業(yè)研究獎(jiǎng) (Microsoft, NVIDIA, Huawei, Tencent, Alibaba)。

報(bào)告摘要：Trustworthy learning and reasoning are the emerging and critical topics in modern machine learning, since most real-world data are easily noisy, such as online transactions,healthcare,cyber-security, and robotics. Intuitively, trustworthy intelligent system should behave more human-like, which can learn and reason from noisy data. Therefore, in this talk, I will introduce trustworthy learning and reasoning from three human-inspired views, including reliability, robustness, and interaction. Specifically, reliability will consider uncertain cases, namely deep learning with noisy labels. Meanwhile, robustness will discuss adversarial conditions, namely deep learning with noisy (adversarial) features. Then, interaction will focus on the dynamic interaction between noisy labels and noisy features. Besides labels and features, I will discuss other noisy data, such as noisy domains, noisy demonstrations, and noisy graphs. Furthermore, I will introduce the newly established Trustworthy Machine Learning and Reasoning (TMLR) Group at Hong Kong SAR and Greater Bay Area.

邀請(qǐng)人：杜博