Xiaoyang Qu

Xiaoyang Qu

Auto-generated profile, based on publicly available information

Xiaoyang Qu

Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 August 2023 in Journal of Ethnopharmacology
Verified
Journal Article
Closed access
QLQinning Li
Qinning Li
YXYan Xiang
Yan Xiang
ZZZhenxu Zhang
Zhenxu Zhang
XQXiaoyang Qu
Xiaoyang Qu
JWJie Wu
Jie Wu
HTHao Tang
Hao Tang

5 October 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YWYinwei Wei
Yinwei Wei
XQXiaoyang Qu
Xiaoyang Qu
XWXiang Wang
Xiang Wang
YMYunshan Ma
Yunshan Ma
LNLiqiang Nie
Liqiang Nie
TCTat-Seng Chua
Tat-Seng Chua
To empower the trust of current recommender systems, the counterfactual explanation (CE) method is adopted to generate the counterfactual instance for each input and take their changes causing the different outcomes as the explanation. Although promising results have been achieved by existing CE-based methods, we propose to generate the attribute-oriented counterfactual explanation. Different from them, we aim to generate the counterfactual instance by performing the intervention on the attributes, and then build an attribute-oriented counterfactual explainable recommender system. Considering the correlation and categorical values of attributes, how to efficiently generate the reliable counterfactual instances on the attributes challenges us. To alleviate such a problem, we propose to extract the decision rules over the attributes to guide the attribute-oriented counterfactual generation. Specifically, we adopt the gradient boosting decision tree (GBDT) to pre-build the decision rules over the attributes and develop a Rule-guided Counterfactual Explainable Recommendation model ( RCER ) to predict the user-item interaction and generate the counterfactual instances for the user-item pairs. We finally conduct extensive experiments on four publicly datasets, including NYC, LON, Amazon, and Movielens datasets. Experimental results have qualitatively and quantitatively justified the superiority of our model over existing cutting-edge baselines. We release the code: https://github.com/quxiaoyang0zero/RCER .

1 December 2020
Verified
Conference Paper
Closed access
XQXiaoyang Qu
Xiaoyang Qu
JWJianzong Wang
Jianzong Wang
JXJing Xiao
Jing Xiao
Although deep learning takes researchers out of complicated feature engineering, designing practical deep learning models is still a complicated process. Neural Architecture Search (NAS) is famous for automating the design of deep learning models. While the fundamental problem of NAS methods is time-consuming, parallel computing is an encouraging way to relieve this problem. We designed a two-level hierarchical parallel system called ParallelNAS, comprising a parallel explorer and parallel evaluators. For the parallel explorer, a general-purposed distributed search framework is built on virtualized, massively-parallel, asynchronous infrastructure. For parallel evaluators, we integrate a segment-balanced sparsity scheme into a mainstream data-parallel architecture. The overall experiment results demonstrate that our distributed and parallel system can reach near-linear speedups on a cluster of 64 GPUs.

23 February 2021 in arXiv
Verified
Preprint
Open access
PDF file
XQXiaoyang Qu
Xiaoyang Qu
JWJianzong Wang
Jianzong Wang
JXJing Xiao
Jing Xiao
Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which might not always be available. A possible solution is a data-free adversarial distillation framework, which deploys a generative network to transfer the teacher model's knowledge to the student model. However, the data generation efficiency is low in the data-free adversarial distillation. We add an activation regularizer and a virtual interpolation method to improve the data generation efficiency. The activation regularizer enables the students to match the teacher's predictions close to activation boundaries and decision boundaries. The virtual interpolation method can generate virtual samples and labels in-between decision boundaries. Our experiments show that our approach surpasses state-of-the-art data-free distillation methods. The student model can achieve 95.42% accuracy on CIFAR-10 and 77.05% accuracy on CIFAR-100 without any original training data. Our model's accuracy is 13.8% higher than the state-of-the-art data-free method on CIFAR-100.

18 July 2021
Verified
Conference Paper
Closed access
XQXiaoyang Qu
Xiaoyang Qu
JWJianzong Wang
Jianzong Wang
JLJie Liu
Jie Liu
JXJing Xiao
Jing Xiao
Neural Architecture Search (NAS) becomes increasingly popular due to the ability to liberate the researchers from the complicated model design. However, typical NAS methods search for high-quality networks at a substantial cost of time and resources. This work enhances the neural architecture search by upgrading the weak components of promising candidate networks. First, we define a search space stacked with repeated components, such as cells and blocks. Second, we propose an attention-wise component evaluation metric to score the components. Third, we exploit a novel search policy to discover weak and strong components in promising candidate networks. Lastly, we use strong components to replace weak components. Besides, to achieve higher accuracy with less time cost, we integrate two optimization schemes: knowledge transfer and self-ensemble. The knowledge transfer accelerates model training by integrating an attentive regularizer into the objective goal. And the self-ensemble method ensembles promising candidate networks as the teacher network to teach the student network. The experiment results demonstrate our method can achieve state-of-the-art results(97.48% accuracy on CIFAR-10 and 84.38% accuracy on CIFAR-100).

1 April 2021
Verified
Book Chapter
Closed access
PDF file
NZNan Zhang
Nan Zhang
JWJianzong Wang
Jianzong Wang
XQXiaoyang Qu
Xiaoyang Qu
JXJing Xiao
Jing Xiao