Timezone: »

 
Poster
Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning
Zhongzheng Ren · Raymond A. Yeh · Alex Schwing

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1330

Existing semi-supervised learning (SSL) algorithms use a single weight to balance the loss of labeled and unlabeled examples, i.e., all unlabeled examples are equally weighted. But not all unlabeled data are equal. In this paper we study how to use a different weight for “every” unlabeled example. Manual tuning of all those weights -- as done in prior work -- is no longer possible. Instead, we adjust those weights via an algorithm based on the influence function, a measure of a model's dependency on one training example. To make the approach efficient, we propose a fast and effective approximation of the influence function. We demonstrate that this technique outperforms state-of-the-art methods on semi-supervised image and language classification tasks.

Author Information

Zhongzheng Ren (UIUC)
Raymond A. Yeh (University of Illinois at Urbana–Champaign)
Alex Schwing (University of Illinois at Urbana-Champaign)

More from the Same Authors