no code implementations • 5 Feb 2025 • Cheng He, Xu Huang, Gangwei Jiang, Zhaoyi Li, Defu Lian, Hong Xie, Enhong Chen, Xijie Liang, Zengrong Zheng
Universal knowledge representation is a central problem for multivariate time series(MTS) foundation models and yet remains open.
no code implementations • 2 Jul 2024 • Su Pan, Xingyang Nie, Xiaoyu Zhai, Biao Wang, Huilin Ge, Cheng He, Zhenping Ding
This study proposes a novel method for the classification of PQDs, termed ST-GSResNet, which utilizes the S-Transform and an improved residual neural network (ResNet) with a channel attention mechanism.
no code implementations • 24 Mar 2023 • Ruiqi Rich Zhu, Cheng He, Yu Jeffrey Hu
However, investors tend to suffer significantly worse investment returns after purchasing recommended funds, and this negative impact is also most significant for investors with low socioeconomic status.
1 code implementation • 13 Nov 2022 • Jiajia Li, Feng Tan, Cheng He, Zikai Wang, Haitao Song, Lingfei Wu, Pengwei Hu
Modern IT system operation demands the integration of system software and hardware metrics.
no code implementations • 8 Oct 2021 • Shengran Hu, Ran Cheng, Cheng He, Zhichao Lu, Jing Wang, Miao Zhang
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments.
3 code implementations • ICCV 2021 • Shihua Huang, Zhichao Lu, Ran Cheng, Cheng He
Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction.
Ranked #24 on
Semantic Segmentation
on ADE20K val
no code implementations • 22 May 2021 • Ye Tian, Xingyi Zhang, Cheng He, Kay Chen Tan, Yaochu Jin
In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems.
no code implementations • 27 Nov 2020 • Shengran Hu, Ran Cheng, Cheng He, Zhichao Lu
In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries.
2 code implementations • 14 Sep 2020 • Hao Tan, Ran Cheng, Shihua Huang, Cheng He, Changxiao Qiu, Fan Yang, Ping Luo
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.
no code implementations • 4 Aug 2020 • Shihua Huang, Cheng He, Ran Cheng
Existing I2I translation methods adopt multiple domain-specific content encoders for different domains, where each domain-specific content encoder is trained with images from the same domain only.
Generative Adversarial Network
Image-to-Image Translation
+1
no code implementations • 20 Dec 2019 • Shujie Han, Jun Wu, Erci Xu, Cheng He, Patrick P. C. Lee, Yi Qiang, Qixing Zheng, Tao Huang, Zixi Huang, Rui Li
To provide proactive fault tolerance for modern cloud data centers, extensive studies have proposed machine learning (ML) approaches to predict imminent disk failures for early remedy and evaluated their approaches directly on public datasets (e. g., Backblaze SMART logs).
no code implementations • 11 Oct 2019 • Cheng He, Shihua Huang, Ran Cheng, Kay Chen Tan, Yaochu Jin
The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables.
no code implementations • 10 Jul 2019 • Cheng He, Shihua Huang, Ran Cheng, Kay Chen Tan, Yaochu Jin
Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models. Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models. Since it usually requires a certain amount of data (i. e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality. To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial networks (GANs). At each generation of the proposed algorithm, the parent solutions are first classified into \emph{real} and \emph{fake} samples to train the GANs; then the offspring solutions are sampled by the trained GANs. Thanks to the powerful generative ability of the GANs, our proposed algorithm is capable of generating promising offspring solutions in high-dimensional decision space with limited training data. The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables. Experimental results on these test problems demonstrate the effectiveness of the proposed algorithm.
no code implementations • 5 Oct 2018 • Gengchen Mai, Krzysztof Janowicz, Cheng He, Sumang Liu, Ni Lao
To test a system's ability to understand the text we adopt an information retrieval evaluation by ranking all the review sentences for a question based on the likelihood that they answer this question.