1 code implementation • 15 May 2023 • Bing Wang, Ximing Li, Zhiyao Yang, Yuanyuan Guan, Jiayin Li, Shengsheng Wang
To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI).
1 code implementation • IEEE Transactions on Emerging Topics in Computing 2022 • Jianping Cai, Ximeng Liu, Zhiyong Yu, Kun Guo, Jiayin Li
The experiments show that our proposed algorithm takes only about 400 seconds to handle up to 9. 6 million large-scale samples, while the state-of-the-art algorithms take close to 1000 seconds to handle every 1000 samples, which embodies the advantage of our algorithms in handling large-scale samples. δ -data indistinguishability theory, we provide quantitative theoretical guarantees for the security of our algorithms.