A Universal Unbiased Method for Classification from Aggregate Observations
Jul 24, 2023
Speakers
Tongliang Liu
Speaker · 0 followers
Xiaofeng Zhu
Speaker · 0 followers
Heng Tao Shen
Speaker · 0 followers
About
In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances, due to privacy concerns or unaffordable annotation costs. This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances. CFAO is a generalized learning framework that contains various learning problems, such as multiple-instance learning and learning from label proportions. The goal of this paper is to present a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary losses—previous research failed to achieve this goal. Practically, our method works by weighing the importance of each instance and each label in the group, which provides purified supervision for the classifier to learn. Theoretically, our proposed method not only guarantees the risk consistency due to the unbiased risk estimator but also can be compatible with arbitrary losses. Extensive experiments on various problems of CFAO demonstrate the superiority of our proposed method.In conventional supervised classification, true labels are required for individual instances. However, it could be prohibitive to collect the true labels for individual instances, due to privacy concerns or unaffordable annotation costs. This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances. CFAO is a generalized learning framework that contains various learning problems, such as mu…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Simplified Temporal Consistency Reinforcement Learning
Watch later
Yi Zhao, …
HiC2Self: Self-supervised Hi-C contact map denoising
Watch later
Large Language Models Struggle to Learn Long-Tail Knowledge
Watch later
Efficient Transformed Gaussian Processes
Watch later
Juan Maroñas, …
Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
Watch later
Xing Liu, …
