454 citations · 3.1k across the 117 of their papers we have counts for
12 papers · 1 filter
Learning with Multiple Complementary Labels
Lei Feng, Takuo Kaneko, Bo Han +3
A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers that can predict the correct class. Unfortuna…
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Jingfeng Zhang, Bo Han, Gang Niu +2
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled da…
Searching to Exploit Memorization Effect in Learning from Corrupted Labels
Quanming Yao, Hansi Yang, Bo Han +2
Sample selection approaches are popular in robust learning from noisy labels. However, how to properly control the selection process so that deep networks can benefit from the memo…
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
Alon Jacovi, Gang Niu, Yoav Goldberg +1
We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large coll…
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
Nan Lu, Tianyi Zhang, Gang Niu +1
The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors. Since this…
Direction Matters: On Influence-Preserving Graph Summarization and Max-cut Principle for Directed Graphs
Wenkai Xu, Gang Niu, Aapo Hyvärinen +1
Summarizing large-scaled directed graphs into small-scale representations is a useful but less studied problem setting. Conventional clustering approaches, which based on "Min-Cut"…