no code implementations • 12 Apr 2024 • Cui Zhang, Xiao Xu, Qiong Wu, Pingyi Fan, Qiang Fan, Huiling Zhu, Jiangzhou Wang
In this scheme, vehicle s mobility, channel conditions with temporal variations, computational resources with temporal variations, different data amount, transmission channel status of vehicles as well as Byzantine attacks were taken into account. Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.
no code implementations • 22 Mar 2024 • Qiong Wu, Weihao Ye, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji
In this paper, we propose a novel parameter and computation efficient tuning method for Multi-modal Large Language Models (MLLMs), termed Efficient Attention Skipping (EAS).
1 code implementation • 10 Mar 2024 • Qiong Wu, Le Kuai, Pingyi Fan, Qiang Fan, Junhui Zhao, Jiangzhou Wang
In Internet of Things (IoT) networks, the amount of data sensed by user devices may be huge, resulting in the serious network congestion.
1 code implementation • 18 Jan 2024 • Qiong Wu, Wenhua Wang, Pingyi Fan, Qiang Fan, Huiling Zhu, Khaled B. Letaief
Finally, we propose a multi-agent deep reinforcement learning (MADRL) based algorithm to decide where the predicted popular contents are collaboratively cached among SBSs.
no code implementations • 13 Dec 2023 • Jiang Zhang, Qiong Wu, Yiming Xu, Cheng Cao, Zheng Du, Konstantinos Psounis
Furthermore, student LMs fine-tuned with rationales extracted via DToT outperform baselines on all datasets with up to 16. 9\% accuracy improvement, while being more than 60x smaller than conventional LLMs.
no code implementations • 30 Nov 2023 • Qiong Wu, Wenhua Wang, Pingyi Fan, Qiang Fan, Jiangzhou Wang, Khaled B. Letaief
Vehicular edge computing (VEC) is a promising technology to support real-time vehicular applications, where vehicles offload intensive computation tasks to the nearby VEC server for processing.
no code implementations • 31 Aug 2023 • Zhiying Feng, Xu Chen, Qiong Wu, Wen Wu, Xiaoxi Zhang, Qianyi Huang
FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection, which will optimize the model parameter uploading ratios tailored to different clients' heterogeneous conditions and also select the proper set of important model parameters for uploading subject to clients' dropout rate constraints.
no code implementations • 24 Jul 2023 • Viet Duong, Qiong Wu, Zhengyi Zhou, Eric Zavesky, Jiahe Chen, Xiangzhou Liu, Wen-Ling Hsu, Huajie Shao
To reach this goal, we propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component to reap the benefits of both.
no code implementations • 27 Jun 2023 • Qiong Wu, Shubin Huang, Yiyi Zhou, Pingyang Dai, Annan Shu, Guannan Jiang, Rongrong Ji
Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens.
1 code implementation • 1 Jun 2023 • Shubin Huang, Qiong Wu, Yiyi Zhou, WeiJie Chen, Rongsheng Zhang, Xiaoshuai Sun, Rongrong Ji
In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks.
no code implementations • 6 Apr 2023 • Qiong Wu, Siyuan Wang, Pingyi Fan, Qiang Fan
Furthermore, as vehicles have different local training time due to various sizes of local data and their different computing capabilities, asynchronous federated learning (AFL) is employed to facilitate the RSU to update the global model immediately after receiving a local model to reduce the aggregation delay.
no code implementations • 11 Mar 2023 • Hongbiao Zhu, Qiong Wu, Qiang Fan, Pingyi Fan, Jiangzhou Wang, Zhengquan Li
It is critical to determine the optimal policy including sample collection requirements and power allocation to minimize the AoI and energy consumption of MIMO-NOMA IoT system, where the transmission rate is not a constant in the SIC process and the noise is stochastic in the MIMO-NOMA channel.
no code implementations • 29 Jan 2023 • Qiong Wu, Jiahan Li, Pingyang Dai, Qixiang Ye, Liujuan Cao, Yongjian Wu, Rongrong Ji
The knowledge transfer between two networks is based on an asymmetric mutual learning manner.
no code implementations • 16 Jan 2023 • Qiong Wu, Xu Chen, Tao Ouyang, Zhi Zhou, Xiaoxi Zhang, Shusen Yang, Junshan Zhang
Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally.
no code implementations • 2 Dec 2022 • Qingze Fang, Zhiwei Zhai, Shuai Yu, Qiong Wu, Xiaowen Gong, Xu Chen
The space-air-ground integrated network (SAGIN), one of the key technologies for next-generation mobile communication systems, can facilitate data transmission for users all over the world, especially in some remote areas where vast amounts of informative data are collected by Internet of remote things (IoRT) devices to support various data-driven artificial intelligence (AI) services.
no code implementations • 1 Dec 2022 • Qiong Wu, Jian Li, Zhenming Liu, Yanhua Li, Mihai Cucuringu
This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network.
no code implementations • 21 Aug 2022 • Qiong Wu, Jiaer Xia, Pingyang Dai, Yiyi Zhou, Yongjian Wu, Rongrong Ji
Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities.
1 code implementation • 16 Aug 2022 • Meijia Shao, Dong Xia, Yuan Zhang, Qiong Wu, Shuo Chen
Two-sample hypothesis testing for network comparison presents many significant challenges, including: leveraging repeated network observations and known node registration, but without requiring them to operate; relaxing strong structural assumptions; achieving finite-sample higher-order accuracy; handling different network sizes and sparsity levels; fast computation and memory parsimony; controlling false discovery rate (FDR) in multiple testing; and theoretical understandings, particularly regarding finite-sample accuracy and minimax optimality.
1 code implementation • 3 Aug 2022 • Siyuan Wang, Qiong Wu, Qiang Fan, Pingyi Fan, Jiangzhou Wang
For the traditional federated learning (FL), vehicles train the data locally to obtain a local model and then upload the local model to the RSU to update the global model, thus the data privacy can be protected through sharing model parameters instead of data.
no code implementations • 2 Aug 2022 • Qiong Wu, Yu Zhao, Qiang Fan
In this paper, we construct the time-dependent model to evaluate the platooning communication performance at the intersection based on the initial movement characteristics.
1 code implementation • 2 Aug 2022 • Qiong Wu, Yu Zhao, Qiang Fan, Pingyi Fan, Jiangzhou Wang, Cui Zhang
In addition, we consider the mobility of vehicles and propose a deep reinforcement learning algorithm to obtain the optimal cooperative caching location for the predicted popular contents in order to optimize the content transmission delay.
no code implementations • 8 Sep 2021 • Hao Zeng, Qiong Wu, Kunpeng Han, Junying He, Haoyuan Hu
In this paper, we investigate the online parcel assignment (OPA) problem, in which each stochastically generated parcel needs to be assigned to a candidate route for delivery to minimize the total cost subject to certain business constraints.
1 code implementation • CVPR 2021 • Qiong Wu, Pingyang Dai, Jie Chen, Chia-Wen Lin, Yongjian Wu, Feiyue Huang, Bineng Zhong, Rongrong Ji
In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.
no code implementations • 21 Jan 2021 • Qiong Wu, Xu Chen, Zhi Zhou, Liang Chen, Junshan Zhang
To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity.
no code implementations • 18 Jan 2021 • Qiong Wu, Tianmu Xin, Binping Xiao
The wire stretching measurement was completed on the prototype Double Quarter Wave (DQW) crab cavity for operation practice and calibration of the measurement system.
Accelerator Physics
1 code implementation • 14 Dec 2020 • Qiong Wu, Xu Chen, Zhi Zhou, Junshan Zhang
In this paper, we propose FedHome, a novel cloud-edge based federated learning framework for in-home health monitoring, which learns a shared global model in the cloud from multiple homes at the network edges and achieves data privacy protection by keeping user data locally.
1 code implementation • 2 Dec 2020 • Qiong Wu, Hanxu Liu, Ruhai Wang, Pingyi Fan, Qiang Fan, Zhengquan Li
Furthermore, the long-term reward of the system (i. e., jointly considers the transmission delay, computing delay, available resources, and diversity of vehicles and tasks) becomes a significantly important issue for providers.
Networking and Internet Architecture
1 code implementation • 5 Nov 2020 • Qiong Wu, Hongmei Ge, Pingyi Fan, Jiangzhou Wang, Qiang Fan, Zhengquan Li
However, one vehicle in platoons inevitably suffers from a disturbance resulting from the leader vehicle acceleration/deceleration, wind gust and uncertainties in a platoon control system, i. e., aerodynamics drag and rolling resistance moment etc.
Networking and Internet Architecture
no code implementations • 28 Oct 2020 • Qiong Wu, Zhenming Liu
We evaluate Rosella with a variety of workloads on a 32-node AWS cluster.
no code implementations • 5 Aug 2020 • Qiong Wu, Adam Hare, Sirui Wang, Yuwei Tu, Zhenming Liu, Christopher G. Brinton, Yanhua Li
In this work, we reexamine the inter-related problems of "topic identification" and "text segmentation" for sparse document learning, when there is a single new text of interest.
no code implementations • 27 Jul 2020 • Pingyang Dai, Peixian Chen, Qiong Wu, Xiaopeng Hong, Qixiang Ye, Qi Tian, Rongrong Ji
This drawback limits the flexibility of UDA in complicated open-set tasks where no labels are shared between domains.
no code implementations • 9 Mar 2020 • Qiong Wu, Muhong Wu, Xu Chen, Zhi Zhou, Kaiwen He, Liang Chen
Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users' QoE.
no code implementations • 26 Feb 2020 • Siqi Luo, Xu Chen, Qiong Wu, Zhi Zhou, Shuai Yu
We further formulate a joint computation and communication resource allocation and edge association problem for device users under HFEL framework to achieve global cost minimization.
Distributed, Parallel, and Cluster Computing
no code implementations • 25 Feb 2020 • Qiong Wu, Kaiwen He, Xu Chen
Internet of Things (IoT) have widely penetrated in different aspects of modern life and many intelligent IoT services and applications are emerging.
no code implementations • 7 Sep 2019 • Qiong Wu, Christopher G. Brinton, Zheng Zhang, Andrea Pizzoferrato, Zhenming Liu, Mihai Cucuringu
Pricing assets has attracted significant attention from the financial technology community.
1 code implementation • IJCAI 2019 • Qiong Wu, Yong liu, Chunyan Miao, Binqiang Zhao, Yin Zhao, Lu Guan
This paper proposes Personalized Diversity-promoting GAN (PD-GAN), a novel recommendation model to generate diverse, yet relevant recommendations.
no code implementations • 1 Jul 2019 • Yong Liu, Yingtai Xiao, Qiong Wu, Chunyan Miao, Juyong Zhang
Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions.
no code implementations • 28 May 2019 • Peixian Chen, Pingyang Dai, Qiong Wu, Yuyu Huang
Recently, the applications of person re-identification in visual surveillance and human-computer interaction are sharply increasing, which signifies the critical role of such a problem.
Optical Flow Estimation Video-Based Person Re-Identification
1 code implementation • NeurIPS 2020 • Qiong Wu, Felix Ming Fai Wong, Zhenming Liu, Yanhua Li, Varun Kanade
We study the low rank regression problem $\my = M\mx + \epsilon$, where $\mx$ and $\my$ are $d_1$ and $d_2$ dimensional vectors respectively.
no code implementations • 16 May 2019 • Qiong Wu, Yong liu, Chunyan Miao, Yin Zhao, Lu Guan, Haihong Tang
With the rapid development of recommender systems, accuracy is no longer the only golden criterion for evaluating whether the recommendation results are satisfying or not.
no code implementations • 19 Mar 2019 • Yong Liu, Yinan Zhang, Qiong Wu, Chunyan Miao, Lizhen Cui, Binqiang Zhao, Yin Zhao, Lu Guan
Interactive recommendation that models the explicit interactions between users and the recommender system has attracted a lot of research attentions in recent years.
no code implementations • 19 Jul 2018 • Qiong Wu, Shuzhen Nie, Pingyi Fan, Zhengquan Li, Cui Zhang
In the second step, we first set the minimum average one-hop delay found in the first step as the initial optimization goal and then adopt the swarming approach again to get the one-hop delay of each backbone vehicle balance to the minimum average one-hop delay.
Networking and Internet Architecture
no code implementations • 9 Jul 2018 • Ao Liu, Qiong Wu, Zhenming Liu, Lirong Xia
Next, we fix the problem by introducing a new algorithm with features constructed from "global information" of the data matrix.
1 code implementation • 29 Nov 2017 • Qiong Wu, Fan Zhang, Hao Wang, Jun Lin, Yang Liu
The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.
Information Theory Information Theory
1 code implementation • 1 Jun 2016 • Yang Li, Chunxiao Fan, Yong Li, Qiong Wu, Yue Ming
In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified and exponential linear units.
no code implementations • 17 Feb 2015 • Qiong Wu
This book discusses computational curiosity, from the psychology of curiosity to the computational models of curiosity, and then showcases several interesting applications of computational curiosity.