no code implementations • 17 Apr 2024 • Hao Yan, Yuhong Guo
To address these two inherent challenges in supervised federated learning, we propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication by harnessing pretrained vision-language models, such as CLIP.
no code implementations • 5 Apr 2024 • Jiuyun Hu, Ziyue Li, Chen Zhang, Fugee Tsung, Hao Yan
Moreover, a case study in the station clustering based on real passenger flow data is conducted, with quite valuable insights discovered.
no code implementations • 26 Mar 2024 • Nurettin Sergin, Jiayu Huang, Tzyy-Shuh Chang, Hao Yan
One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types.
no code implementations • 26 Mar 2024 • Xinyu Zhao, Hao Yan, Yongming Liu
This article argues that we can identify the events more accurately by leveraging the event taxonomy.
no code implementations • 23 Mar 2024 • Hao Yan, Zhihui Ke, Xiaobo Zhou, Tie Qiu, Xidong Shi, Dadong Jiang
Implicit neural representations for video (NeRV) have recently become a novel way for high-quality video representation.
no code implementations • 17 Mar 2024 • Kaiyan Chang, Kun Wang, Nan Yang, Ying Wang, Dantong Jin, Wenlong Zhu, Zhirong Chen, Cangyuan Li, Hao Yan, Yunhao Zhou, Zhuoliang Zhao, Yuan Cheng, Yudong Pan, Yiqi Liu, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li
Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3. 5 in Verilog generation and outperforms in EDA script (i. e., SiliconCompiler) generation with only 200 EDA script data.
no code implementations • 13 Mar 2024 • Yuyang Ye, Peng Xu, Lizheng Ren, Tinghuan Chen, Hao Yan, Bei Yu, Longxing Shi
Gate sizing plays an important role in timing optimization after physical design.
no code implementations • 7 Mar 2024 • Leilei Jin, Jiajie Xu, Wenjie Fu, Hao Yan, Longxing Shi
With shrinking interconnect spacing in advanced technology nodes, existing timing predictions become less precise due to the challenging quantification of crosstalk-induced delay.
no code implementations • 31 Oct 2023 • Ziyue Li, Hao Yan, Chen Zhang, Lijun Sun, Wolfgang Ketter, Fugee Tsung
In this paper, we propose a novel tensor Dirichlet Process Multinomial Mixture model with graphs, which can preserve the hierarchical structure of the multi-dimensional trip information and cluster them in a unified one-step manner with the ability to determine the number of clusters automatically.
no code implementations • 7 Sep 2023 • Jiuyun Hu, Naichen Shi, Raed Al Kontar, Hao Yan
We propose personalized Tucker decomposition (perTucker) to address the limitations of traditional tensor decomposition methods in capturing heterogeneity across different datasets.
no code implementations • 23 Jun 2023 • Ziyue Li, Hao Yan, Chen Zhang, Andi Wang, Wolfgang Ketter, Lijun Sun, Fugee Tsung
In this paper, we propose a novel Tensor Dirichlet Process Multinomial Mixture model (Tensor-DPMM), which is designed to preserve the multi-mode and hierarchical structure of the multi-dimensional trip information via tensor, and cluster them in a unified one-step manner.
2 code implementations • 14 May 2023 • Hao Yan, Saurabh Srivastava, Yintao Tai, Sida I. Wang, Wen-tau Yih, Ziyu Yao
In this work, we propose a new task of simulating NL feedback for interactive semantic parsing.
no code implementations • 15 Dec 2022 • Hao Yan, Yuhong Guo
We first split the unlabeled training set in the target domain into a pseudo-labeled confident subset and an unlabeled less-confident subset according to the prediction confidence scores from the pre-trained source model.
Source-Free Domain Adaptation Unsupervised Domain Adaptation
2 code implementations • 26 Oct 2022 • Jianan Zhao, Meng Qu, Chaozhuo Li, Hao Yan, Qian Liu, Rui Li, Xing Xie, Jian Tang
In this paper, we propose an efficient and effective solution to learning on large text-attributed graphs by fusing graph structure and language learning with a variational Expectation-Maximization (EM) framework, called GLEM.
Ranked #1 on Node Property Prediction on ogbn-papers100M
no code implementations • 16 Oct 2022 • Jiayu Huang, Yutian Pang, Yongming Liu, Hao Yan
Neural Networks (NNs) have been widely {used in supervised learning} due to their ability to model complex nonlinear patterns, often presented in high-dimensional data such as images and text.
no code implementations • 9 Aug 2022 • Xinyu Zhao, Jiuyun Hu, Yajun Mei, Hao Yan
High-dimensional data has become popular due to the easy accessibility of sensors in modern industrial applications.
no code implementations • 9 Aug 2022 • Jiuyun Hu, Yajun Mei, Sarah Holte, Hao Yan
In this paper, we present an efficient statistical method (denoted as "Adaptive Resources Allocation CUSUM") to robustly and efficiently detect the hotspot with limited sampling resources.
no code implementations • 7 May 2022 • Chengdong Lan, Hao Yan, Cheng Luo, Tiesong Zhao
At the decoder side, we combine the SI and adjacent viewpoints to reconstruct intermediate views using the GAN generator.
no code implementations • 25 Feb 2022 • Michael Biehler, Hao Yan, Jianjun Shi
Unstructured point clouds with varying sizes are increasingly acquired in a variety of environments through laser triangulation or Light Detection and Ranging (LiDAR).
no code implementations • 20 Sep 2021 • Xinyu Zhao, Hao Yan, Zhiyong Hu, Dongping Du
Electrical conduction among cardiac tissue is commonly modeled with partial differential equations, i. e., reaction-diffusion equation, where the reaction term describes cellular stimulation and diffusion term describes electrical propagation.
no code implementations • 17 May 2021 • Hao Yan, Nurretin Dorukhan Sergin, William A. Brenneman, Stephen Joseph Lange, Shan Ba
In multistage manufacturing systems, modeling multiple quality indices based on the process sensing variables is important.
no code implementations • 29 Apr 2021 • Ruifeng Zheng, Lin Lin, Hao Yan
The extent that ISI and noise are suppressed in an MCvD system determines its effectiveness, especially at a high data rate.
no code implementations • 6 Oct 2020 • Mary Lou P Bailey, Hao Yan, Ivan Surovtsev, Jessica F Williams, Megan C King, Simon G J Mochrie
This suggests that the origin of the theory-experiment discrepancy is associated with localization noise, which influences only the first two covariances.
Biological Physics
no code implementations • 22 Sep 2020 • Jie Guo, Hao Yan, Chen Zhang, Steven Hoi
We consider online change detection of high dimensional data streams with sparse changes, where only a subset of data streams can be observed at each sensing time point due to limited sensing capacities.
no code implementations • 15 Aug 2020 • Hongzhi Wang, Yan Wei, Hao Yan
Therefore, the users of the database need to select the storage engine and design data model according to the workload encountered.
no code implementations • 23 Apr 2020 • Hao Yan, Marco Grasso, Kamran Paynabar, Bianca Maria Colosimo
The use of video-imaging data for in-line process monitoring applications has become more and more popular in the industry.
no code implementations • 23 Apr 2020 • Ziyue Li, Hao Yan, Chen Zhang, Fugee Tsung
Spatiotemporal data is very common in many applications, such as manufacturing systems and transportation systems.
1 code implementation • 11 Dec 2019 • Ziyue Li, Nurettin Dorukhan Sergin, Hao Yan, Chen Zhang, Fugee Tsung
Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data.
no code implementations • 1 Nov 2019 • Nurettin Sergin, Hao Yan
To do so, we formulate nonlinear and probabilistic extensions of the monitoring statistics from classical approaches as the expected reconstruction error (ERE) and the KL-divergence (KLD) based monitoring statistics.
no code implementations • 4 Oct 2019 • Hao Yan, Kamran Paynabar, Jianjun Shi
In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for online inspection and anomaly quantification.
1 code implementation • 9 Jun 2019 • Hao Peng, Jian-Xin Li, Hao Yan, Qiran Gong, Senzhang Wang, Lin Liu, Lihong Wang, Xiang Ren
Most existing methods focus on learning the structural representations of vertices in a static network, but cannot guarantee an accurate and efficient embedding in a dynamic network scenario.
no code implementations • JOURNAL OF QUALITY TECHNOLOGY 2018 • Chen Zhang, Hao Yan, Seungho Lee, Jianjun Shi
However, there are several challenges in developing an effective process monitoring system: (i) data streams generated by multiple sensors are high-dimensional profiles; (ii) sensor signals are affected by noise due to system-inherent variations; (iii) signals of different sensors have cluster-wise features; and (iv) an anomaly may cause only sparse changes of sensor signals.
no code implementations • 26 Jul 2018 • Hao Yan, Kamran Paynabar, Massimo Pacella
Advanced 3D metrology technologies such as Coordinate Measuring Machine (CMM) and laser 3D scanners have facilitated the collection of massive point cloud data, beneficial for process monitoring, control and optimization.
no code implementations • 11 Apr 2018 • Chen Zhang, Hao Yan, Seungho Lee, Jianjun Shi
Multivariate functional data from a complex system are naturally high-dimensional and have complex cross-correlation structure.