Details
| Original language | English |
|---|---|
| Pages (from-to) | 8784-8792 |
| Number of pages | 9 |
| Journal | Proceedings of the AAAI Conference on Artificial Intelligence |
| Volume | 35 |
| Issue number | 10 |
| Publication status | Published - 18 May 2021 |
| Event | 35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online Duration: 2 Feb 2021 → 9 Feb 2021 |
Abstract
Positive-unlabeled learning (PU learning) is an important case of binary classification where the training data only contains positive and unlabeled samples. The current state-of-the-art approach for PU learning is the cost-sensitive approach, which casts PU learning as a cost-sensitive classification problem and relies on unbiased risk estimator for correcting the bias introduced by the unlabeled samples. However, this approach requires the knowledge of class prior and is subject to the potential label noise. In this paper, we propose a novel PU learning approach dubbed PULNS, equipped with an effective negative sample selector, which is optimized by reinforcement learning. Our PULNS approach employs an effective negative sample selector as the agent responsible for selecting negative samples from the unlabeled data. While the selected, likely negative samples can be used to improve the classifier, the performance of classifier is also used as the reward to improve the selector through the REINFORCE algorithm. By alternating the updates of the selector and the classifier, the performance of both is improved. Extensive experimental studies on 7 real-world application benchmarks demonstrate that PULNS consistently outperforms the current state-of-the-art methods in PU learning, and our experimental results also confirm the effectiveness of the negative sample selector underlying PULNS.
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, No. 10, 18.05.2021, p. 8784-8792.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - PULNS
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
AU - Luo, Chuan
AU - Zhao, Pu
AU - Chen, Chen
AU - Qiao, Bo
AU - Du, Chao
AU - Zhang, Hongyu
AU - Wu, Wei
AU - Cai, Shaowei
AU - He, Bing
AU - Rajmohan, Saravanakumar
AU - Lin, Qingwei
PY - 2021/5/18
Y1 - 2021/5/18
N2 - Positive-unlabeled learning (PU learning) is an important case of binary classification where the training data only contains positive and unlabeled samples. The current state-of-the-art approach for PU learning is the cost-sensitive approach, which casts PU learning as a cost-sensitive classification problem and relies on unbiased risk estimator for correcting the bias introduced by the unlabeled samples. However, this approach requires the knowledge of class prior and is subject to the potential label noise. In this paper, we propose a novel PU learning approach dubbed PULNS, equipped with an effective negative sample selector, which is optimized by reinforcement learning. Our PULNS approach employs an effective negative sample selector as the agent responsible for selecting negative samples from the unlabeled data. While the selected, likely negative samples can be used to improve the classifier, the performance of classifier is also used as the reward to improve the selector through the REINFORCE algorithm. By alternating the updates of the selector and the classifier, the performance of both is improved. Extensive experimental studies on 7 real-world application benchmarks demonstrate that PULNS consistently outperforms the current state-of-the-art methods in PU learning, and our experimental results also confirm the effectiveness of the negative sample selector underlying PULNS.
AB - Positive-unlabeled learning (PU learning) is an important case of binary classification where the training data only contains positive and unlabeled samples. The current state-of-the-art approach for PU learning is the cost-sensitive approach, which casts PU learning as a cost-sensitive classification problem and relies on unbiased risk estimator for correcting the bias introduced by the unlabeled samples. However, this approach requires the knowledge of class prior and is subject to the potential label noise. In this paper, we propose a novel PU learning approach dubbed PULNS, equipped with an effective negative sample selector, which is optimized by reinforcement learning. Our PULNS approach employs an effective negative sample selector as the agent responsible for selecting negative samples from the unlabeled data. While the selected, likely negative samples can be used to improve the classifier, the performance of classifier is also used as the reward to improve the selector through the REINFORCE algorithm. By alternating the updates of the selector and the classifier, the performance of both is improved. Extensive experimental studies on 7 real-world application benchmarks demonstrate that PULNS consistently outperforms the current state-of-the-art methods in PU learning, and our experimental results also confirm the effectiveness of the negative sample selector underlying PULNS.
UR - http://www.scopus.com/inward/record.url?scp=85107947831&partnerID=8YFLogxK
U2 - 10.1609/aaai.v35i10.17064
DO - 10.1609/aaai.v35i10.17064
M3 - Conference article
AN - SCOPUS:85107947831
VL - 35
SP - 8784
EP - 8792
JO - Proceedings of the AAAI Conference on Artificial Intelligence
JF - Proceedings of the AAAI Conference on Artificial Intelligence
IS - 10
Y2 - 2 February 2021 through 9 February 2021
ER -