報告題目：Task-Driven Tensor Low-rank Representation in Machine Learning

報告題目：Task-Driven Tensor Low-rank Representation in Machine Learning

報告摘要：Many machine learning tasks can be modeled as a low-rank tensor representation problem. Tensors are the extension of matrices, which represent the multi-way arrays. Different from the matrix, tensor rank is not well defined with a tight convex relaxation. To this end, many formulations of tensor ranks are proposed like CP rank, Tucker rank, Tubal rank, and so on. Although these tensor ranks have their own advantages, they are all designed for general purposes. We argue that for a specific task, we should design a task-tailored tensor low-rank norm to better solve that task. Based on this idea, in this talk, I will present several examples of how to design task-tailored tensor low-rank norms by exploiting the characteristics of specific tasks. Those examples include hyperspectral image representation, subspace clustering, multiple view clustering, etc.

個人介紹：

賈育衡，博士，副教授，江蘇省“雙創博士”，bet356手机版唯一官网“至善青年學者”、“紫金青年學者”。2019年獲得香港城市大學(CityU)博士學位，2019-2020年任香港城市大學博士後研究員。導師為Sam Kwong 講席教授。2020年起在bet356手机版唯一官网登录任職副教授。現為bet356手机版唯一官网PALM實驗室成員。曾任斯坦福大學（Stanford University）訪問學者（2018年）。研究内容廣泛涉及機器學習和數據表示的多個子領域，主要包括半監督學習、高維數據分析與建模、張量表示與建模、圖機器學習，深度學習以及在計算機視覺、高光譜表示、社區檢測等方向的一些應用。在相關研究領域的國際會議和期刊上發表學術論文40+篇，其中CCF-A/IEEE Trans 論文25+。擔任多個國際著名期刊會議的程序委員會委員和審稿人。主持多項國家自然科學基金、江蘇省自然科學基金等橫縱向項目。