Do we need new machine learning methods?
- 2022-03-21 (Mon.), 10:30 AM
- Auditorium, B1F, Institute of Statistical Science；The tea reception will be held at 10:10.
- Lecture in English, Online live streaming through Microsoft Teams will be available.
- Prof. Chih-Jen Lin
- Department of Computer Science & Information Engineering, National Taiwan University
Abstract
If we ask about the need of developing new machine learning methods, usually the answer is yes. But in this talk I will argue that sometimes the answer is no. The reason is that good methods may be already there but people did not apply them. I will use a real example as an illustration. In the area of graph-representation learning, to evaluate the quality of the obtained representations, the multi-label problem of node classification is often considered. We found that an unrealistic setting was used in hundreds, if not thousands of papers by assuming that the number of labels of each test instance is known in the prediction stage. In practice such ground truth information is rarely available, but unfortunately this inappropriate setting is now ubiquitous in the area of graph-representation learning. The issue roots from that only rudimentary multi-label training methods were used even though advanced ones have long been available. The discussion shows that besides developing new methods, we should also pay attention to other aspects on the use of machine learning techniques.
Please click here for participating the talk online
Download
Update：2022-03-07 10:19
Back
