1 code implementation • 28 Aug 2022 • Yinghua Zhang, Yangqiu Song, Kun Bai, Qiang Yang
To successfully attack fine-tuned models under both settings, we propose to first train an adversarial generator against the source model, which adopts an encoder-decoder architecture and maps a clean input to an adversarial example.
no code implementations • 12 Jul 2022 • Yingsong Huang, Bing Bai, Shengwei Zhao, Kun Bai, Fei Wang
The second issue refers to that models may output misleading predictions due to epistemic uncertainty and aleatoric uncertainty, thus existing methods that rely solely on the output probabilities may fail to distinguish confident samples.
no code implementations • 5 May 2022 • Fangfei Lin, Bing Bai, Kun Bai, Yazhou Ren, Peng Zhao, Zenglin Xu
Then, we embed the representations into a hyperbolic space and optimize the hyperbolic embeddings via a continuous relaxation of hierarchical clustering loss.
no code implementations • 10 May 2021 • Xinglin Pan, Jing Xu, Yu Pan, Liangjian Wen, WenXiang Lin, Kun Bai, Zenglin Xu
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification.
1 code implementation • 25 Jan 2021 • Jing Xu, Tszhang Guo, Yong Xu, Zenglin Xu, Kun Bai
Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently.
no code implementations • 15 Oct 2020 • Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Conghui Zhu, Tiejun Zhao
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.
no code implementations • 11 Oct 2020 • Jian Liang, Yuren Cao, Shuang Li, Bing Bai, Hao Li, Fei Wang, Kun Bai
We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.
no code implementations • 6 Sep 2020 • Chang Wang, Jian Liang, Mingkai Huang, Bing Bai, Kun Bai, Hao Li
We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w. r. t.
1 code implementation • 25 Aug 2020 • Yinghua Zhang, Yangqiu Song, Jian Liang, Kun Bai, Qiang Yang
To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
no code implementations • 25 Aug 2020 • Mingkai Huang, Hao Li, Bing Bai, Chang Wang, Kun Bai, Fei Wang
Federated Learning(FL) is a newly developed privacy-preserving machine learning paradigm to bridge data repositories without compromising data security and privacy.
no code implementations • 11 Jul 2020 • Zhao Kang, Xiao Lu, Jian Liang, Kun Bai, Zenglin Xu
In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning.
no code implementations • 10 Jun 2020 • Bing Bai, Jian Liang, Guanhua Zhang, Hao Li, Kun Bai, Fei Wang
In this paper, we demonstrate that one root cause of this phenomenon is the combinatorial shortcuts, which means that, in addition to the highlighted parts, the attention weights themselves may carry extra information that could be utilized by downstream models after attention layers.
1 code implementation • 9 Jun 2020 • Jian Liang, Bing Bai, Yuren Cao, Kun Bai, Fei Wang
A popular way of performing model interpretation is Instance-wise Feature Selection (IFS), which provides an importance score of each feature representing the data samples to explain how the model generates the specific output.
1 code implementation • 27 May 2020 • Junqi Zhang, Bing Bai, Ye Lin, Jian Liang, Kun Bai, Fei Wang
In this paper, we report our recent practice at Tencent for user modeling based on mobile app usage.
1 code implementation • ACL 2020 • Guanhua Zhang, Bing Bai, Junqi Zhang, Kun Bai, Conghui Zhu, Tiejun Zhao
In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the non-discrimination distribution to the discrimination distribution.
no code implementations • 7 Apr 2020 • Bing Bai, Guanhua Zhang, Ye Lin, Hao Li, Kun Bai, Bo Luo
Recurrent Neural Network (RNN)-based sequential recommendation is a popular approach that utilizes users' recent browsing history to predict future items.
1 code implementation • 12 Mar 2020 • Yinghua Zhang, Yu Zhang, Ying WEI, Kun Bai, Yangqiu Song, Qiang Yang
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
no code implementations • IJCNLP 2019 • Zhufeng Pan, Kun Bai, Yan Wang, Lianqiang Zhou, Xiaojiang Liu
To facilitate the study of incomplete utterance restoration for open-domain dialogue systems, a large-scale multi-turn dataset Restoration-200K is collected and manually labeled with the explicit relation between an utterance and its context.
no code implementations • 10 Sep 2019 • Guanhua Zhang, Bing Bai, Junqi Zhang, Kun Bai, Conghui Zhu, Tiejun Zhao
This irregularity makes the evaluation results over-estimated and affects models' generalization ability.
no code implementations • 2 Aug 2019 • Guoqiang Gong, Liangfeng Zheng, Kun Bai, Yadong Mu
Our proposed TSA-Net demonstrates clear and consistent better performances and re-calibrates new state-of-the-art on both benchmarks.
1 code implementation • CVPR 2019 • Jian Liang, Yuren Cao, Chenbin Zhang, Shiyu Chang, Kun Bai, Zenglin Xu
Authentication is a task aiming to confirm the truth between data instances and personal identities.
2 code implementations • ACL 2019 • Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.
1 code implementation • NIPS Workshop CDNNRIA 2018 • Yu Pan, Jing Xu, Maolin Wang, Jinmian Ye, Fei Wang, Kun Bai, Zenglin Xu
Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling.
1 code implementation • EMNLP 2018 • Tszhang Guo, Shiyu Chang, Mo Yu, Kun Bai
Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing.