arXiv subjects

Qiong Wu

Publications and source records attributed to Qiong Wu.

At least 145 records · Page 8Linked to original sources

arXiv2023

Delay-sensitive Task Offloading in Vehicular Fog Computing-Assisted Platoons

Vehicles in platoons need to process many tasks to support various real-time vehicular applications. When a task arrives at a vehicle, the vehicle may not process the task due to its limited computation resource. In this case, it usually requests to offload the task to other vehicles in the platoon for processing. However, when the computation resources of all the vehicles in the platoon are insufficient, the task cannot be processed in time through offloading to the other vehicles in the platoon. Vehicular fog computing (VFC)-assisted platoon can solve this problem through offloading the task to the VFC which is formed by the vehicles driving near the platoon. Offloading delay is an important performance metric, which is impacted by both the offloading strategy for deciding where the task is offloaded and the number of the allocated vehicles in VFC to process the task. Thus, it is critical to propose an offloading strategy to minimize the offloading delay. In the VFC-assisted platoon system, vehicles usually adopt the IEEE 802.11p distributed coordination function (DCF) mechanism while having various computation resources. Moreover, when vehicles arrive and depart the VFC randomly, their tasks also arrive at and depart the system randomly. In this paper, we propose a semi-Markov decision process (SMDP) based offloading strategy while considering these factors to obtain the maximal long-term reward reflecting the offloading delay. Our research provides a robust strategy for task offloading in VFC systems, its effectiveness is demonstrated through simulation experiments and comparison with benchmark strategies.

cs.NI↗

arXiv2023

Enhanced C-V2X Mode 4 to Optimize Age of Information and Reliability for IoV

Internet of vehicles (IoV) has emerged as a key technology to realize real-time vehicular application. For IoV, vehicles adopt cellular vehicle-to-everything (C-V2X) standard to support direct communication among them. C-V2X mode 4 controls resource allocation without the assistance of cellular network, hence it is widely used for IoV. However, C-V2X mode 4 has two drawbacks. First is that vehicles cannot communicate with each other for a period in some case which will cause an increase in age of information (AoI); second is that vehicles may select resource already occupied by others which will deteriorate the reliability. To address the two drawbacks, we propose an enhanced C-V2X mode 4 to optimize AoI and reliability. In addition, we consider the fact that for most vehicular applications, each vehicle periodically requires fresh information of vehicles within a certain distance and propose a new performance metric to evaluate the system AoI for IoV. Furthermore, we construct a platform through integrating SUMO and NS3. We demonstrate the superiority of the enhanced C-V2X mode 4 base on this simulation platform.

cs.NI↗

arXiv2023

FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropout

Federated Learning (FL) requires frequent exchange of model parameters, which leads to long communication delay, especially when the network environments of clients vary greatly. Moreover, the parameter server needs to wait for the slowest client (i.e., straggler, which may have the largest model size, lowest computing capability or worst network condition) to upload parameters, which may significantly degrade the communication efficiency. Commonly-used client selection methods such as partial client selection would lead to the waste of computing resources and weaken the generalization of the global model. To tackle this problem, along a different line, in this paper, we advocate the approach of model parameter dropout instead of client selection, and accordingly propose a novel framework of Federated learning scheme with Differential parameter Dropout (FedDD). 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. Specifically, the dropout rate allocation is formulated as a convex optimization problem, taking system heterogeneity, data heterogeneity, and model heterogeneity among clients into consideration. The uploaded parameter selection strategy prioritizes on eliciting important parameters for uploading to speedup convergence. Furthermore, we theoretically analyze the convergence of the proposed FedDD scheme. Extensive performance evaluations demonstrate that the proposed FedDD scheme can achieve outstanding performances in both communication efficiency and model convergence, and also possesses a strong generalization capability to data of rare classes.

cs.LG↗

arXiv2023

Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting

Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning, resulting in excessive memory overhead. In this paper, we focus on exploring PLMs as a stand-alone model for VL reasoning tasks. Inspired by the recently popular prompt tuning, we first prove that the processed visual features can be also projected onto the semantic space of PLMs and act as prompt tokens to bridge the gap between single- and multi-modal learning. However, this solution exhibits obvious redundancy in visual information and model inference, and the placement of prompt tokens also greatly affects the final performance. Based on these observations, we further propose a novel transfer learning approach for PLMs, termed Dynamic Visual Prompting (DVP). Concretely, DVP first deploys a cross-attention module to obtain text-related and compact visual prompt tokens, thereby greatly reducing the input length of PLMs. To obtain the optimal placement, we also equip DVP with a reinforcement-learning based search algorithm, which can automatically merge DVP with PLMs for different VL tasks via a very short search process. 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. We apply DVP to two representative PLMs, namely BERT and T5, and conduct extensive experiments on a set of VL reasoning benchmarks including VQA2.0, GQA and SNLIVE. The experimental results not only show the advantage of DVP on efficiency and performance, but also confirm its superiority in adapting pre-trained language models to VL tasks.

cs.CV↗

arXiv2023

Approximated Prompt Tuning for Vision-Language Pre-trained Models

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks, which greatly exacerbates the already high computational overhead. In this paper, we revisit the principle of prompt tuning for Transformer-based VLP models, and reveal that the impact of soft prompt tokens can be actually approximated via independent information diffusion steps, thereby avoiding the expensive global attention modeling and reducing the computational complexity to a large extent. Based on this finding, we propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning. To validate APT, we apply it to two representative VLP models, namely ViLT and METER, and conduct extensive experiments on a bunch of downstream tasks. Meanwhile, the generalization of APT is also validated on CLIP for image classification and StableDiffusion for text-to-image generation. The experimental results not only show the superior performance gains and computation efficiency of APT against the conventional prompt tuning methods, e.g., +7.01% accuracy and -82.30% additional computation overhead on METER, but also confirm its merits over other parameter-efficient transfer learning approaches.

cs.CV↗

arXiv2023

User-centric AIGC products: Explainable Artificial Intelligence and AIGC products

Generative AI tools, such as ChatGPT and Midjourney, are transforming artistic creation as AI-art integration advances. However, Artificial Intelligence Generated Content (AIGC) tools face user experience challenges, necessitating a human-centric design approach. This paper offers a brief overview of research on explainable AI (XAI) and user experience, examining factors leading to suboptimal experiences with AIGC tools. Our proposed solution integrates interpretable AI methodologies into the input and adjustment feedback stages of AIGC products. We underscore XAI's potential to enhance the user experience for ordinary users and present a conceptual framework for improving AIGC user experience.

cs.HC↗

arXiv2023

General-Purpose Multi-Modal OOD Detection Framework

Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems. While a plethora of methods have been developed to detect uni-modal OOD samples, only a few have focused on multi-modal OOD detection. Current contrastive learning-based methods primarily study multi-modal OOD detection in a scenario where both a given image and its corresponding textual description come from a new domain. However, real-world deployments of ML systems may face more anomaly scenarios caused by multiple factors like sensor faults, bad weather, and environmental changes. Hence, the goal of this work is to simultaneously detect from multiple different OOD scenarios in a fine-grained manner. 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. In order to better distinguish the latent representations of in-distribution (ID) and OOD samples, we adopt the Hinge loss to constrain their similarity. Furthermore, we develop a new scoring metric to integrate the prediction results from both the binary classifier and contrastive learning for identifying OOD samples. We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection. Importantly, our approach is able to achieve high accuracy in OOD detection in three different OOD scenarios simultaneously. The source code will be made publicly available upon publication.

cs.CV↗

arXiv2023

Ergodicity and stability of hybrid systems with piecewise constant type state-dependent switching

To deal with stochastic hybrid systems with general state-dependent switching, we propose an approximation method by a sequence of stochastic hybrid systems with piecewise constant type switching. The convergence rate in the Wasserstein distance is estimated in terms of the difference between transition rate matrices. Our method is based on an elaborate construction of coupling processes in terms of Skorokhod's representation theorem for jumping processes. Moreover, we establish explicit criteria on the ergodicity and stability for stochastic hybrid systems with piecewise constant type switching. Some examples are given to illustrate the sharpness of these criteria.

math.PR↗

arXiv2023

X-ray Polarimetry of the accreting pulsar 1A~0535+262 in the supercritical state with PolarLight

The X-ray pulsar 1A 0535+262 exhibited a giant outburst in 2020, offering us a unique opportunity for X-ray polarimetry of an accreting pulsar in the supercritical state. Measurement with PolarLight yielded a non-detection in 3-8 keV; the 99% upper limit of the polarization fraction (PF) is found to be 0.34 averaged over spin phases, or 0.51 based on the rotating vector model. No useful constraint can be placed with phase resolved polarimetry. These upper limits are lower than a previous theoretical prediction of 0.6-0.8, but consistent with those found in other accreting pulsars, like Her X-1, Cen X-3, 4U 1626-67, and GRO J1008-57, which were in the subcritical state, or at least not confidently in the supercritical state, during the polarization measurements. Our results suggest that the relatively low PF seen in accreting pulsars cannot be attributed to the source not being in the supercritical state, but could be a general feature.

astro-ph.HE↗

arXiv2023

Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing

In the traditional vehicular network, computing tasks generated by the vehicles are usually uploaded to the cloud for processing. However, since task offloading toward the cloud will cause a large delay, vehicular edge computing (VEC) is introduced to avoid such a problem and improve the whole system performance, where a roadside unit (RSU) with certain computing capability is used to process the data of vehicles as an edge entity. Owing to the privacy and security issues, vehicles are reluctant to upload local data directly to the RSU, and thus federated learning (FL) becomes a promising technology for some machine learning tasks in VEC, where vehicles only need to upload the local model hyperparameters instead of transferring their local data to the nearby RSU. 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. However, in AFL of VEC, different vehicles may have different impact on the global model updating because of their various local training delay, transmission delay and local data sizes. Also, if there are bad nodes among the vehicles, it will affect the global aggregation quality at the RSU. To solve the above problem, we shall propose a deep reinforcement learning (DRL) based vehicle selection scheme to improve the accuracy of the global model in AFL of vehicular network. In the scheme, we present the model including the state, action and reward in the DRL based to the specific problem. Simulation results demonstrate our scheme can effectively remove the bad nodes and improve the aggregation accuracy of the global model.

cs.LG↗

arXiv2023

Multi-Attribute Utility Preference Robust Optimization: A Continuous Piecewise Linear Approximation Approach

In this paper, we consider a multi-attribute decision making problem where the decision maker's (DM's) objective is to maximize the expected utility of outcomes but the true utility function which captures the DM's risk preference is ambiguous. We propose a maximin multi-attribute utility preference robust optimization (UPRO) model where the optimal decision is based on the worst-case utility function in an ambiguity set of plausible utility functions constructed using partially available information such as the DM's specific preferences between some lotteries. Specifically, we consider a UPRO model with two attributes, where the DM's risk attitude is multivariate risk-averse and the ambiguity set is defined by a linear system of inequalities represented by the Lebesgue-Stieltjes (LS) integrals of the DM's utility functions. To solve the maximin problem, we propose an explicit piecewise linear approximation (EPLA) scheme to approximate the DM's true unknown utility so that the inner minimization problem reduces to a linear program, and we solve the approximate maximin problem by a derivative-free (Dfree) method. Moreover, by introducing binary variables to locate the position of the reward function in a family of simplices, we propose an implicit piecewise linear approximation (IPLA) representation of the approximate UPRO and solve it using the Dfree method. Such IPLA technique prompts us to reformulate the approximate UPRO as a single mixed-integer program (MIP) and extend the tractability of the approximate UPRO to the multi-attribute case. Furthermore, we extend the model to the expected utility maximization problem with expected utility constraints where the worst-case utility functions in the objective and constraints are considered simultaneously. Finally, we report the numerical results about performances of the proposed models.

math.OC↗

arXiv2023

Deep Reinforcement Learning Based Power Allocation for Minimizing AoI and Energy Consumption in MIMO-NOMA IoT Systems

Multi-input multi-out and non-orthogonal multiple access (MIMO-NOMA) internet-of-things (IoT) systems can improve channel capacity and spectrum efficiency distinctly to support the real-time applications. Age of information (AoI) is an important metric for real-time application, but there is no literature have minimized AoI of the MIMO-NOMA IoT system, which motivates us to conduct this work. In MIMO-NOMA IoT system, the base station (BS) determines the sample collection requirements and allocates the transmission power for each IoT device. Each device determines whether to sample data according to the sample collection requirements and adopts the allocated power to transmit the sampled data to the BS over MIMO-NOMA channel. Afterwards, the BS employs successive interference cancelation (SIC) technique to decode the signal of the data transmitted by each device. The sample collection requirements and power allocation would affect AoI and energy consumption of the system. 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. In this paper, we propose the optimal power allocation to minimize the AoI and energy consumption of MIMO- NOMA IoT system based on deep reinforcement learning (DRL). Extensive simulations are carried out to demonstrate the superiority of the optimal power allocation.

cs.IT↗

arXiv2023

High stable and accurate vehicle selection scheme based on federated edge learning in vehicular networks

Federated edge learning (FEEL) technology for vehicular networks is considered as a promising technology to reduce the computation workload while keeping the privacy of users. In the FEEL system, vehicles upload data to the edge servers, which train the vehicles' data to update local models and then return the result to vehicles to avoid sharing the original data. However, the cache queue in the edge is limited and the channel between edge server and each vehicle is time-varying. Thus, it is challenging to select a suitable number of vehicles to ensure that the uploaded data can keep a stable cache queue in edge server while maximizing the learning accuracy. Moreover, selecting vehicles with different resource statuses to update data will affect the total amount of data involved in training, which further affects the model accuracy. In this paper, we propose a vehicle selection scheme, which maximizes the learning accuracy while ensuring the stability of the cache queue, where the statuses of all the vehicles in the coverage of edge server are taken into account. The performance of this scheme is evaluated through simulation experiments, which indicates that our proposed scheme can perform better than the known benchmark scheme.

cs.NI↗

arXiv2023

Asynchronous Federated Learning for Edge-assisted Vehicular Networks

Vehicular networks enable vehicles support real-time vehicular applications through training data. Due to the limited computing capability, vehicles usually transmit data to a road side unit (RSU) at the network edge to process data. However, vehicles are usually reluctant to share data with each other due to the privacy issue. 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. The traditional FL updates the global model synchronously, i.e., the RSU needs to wait for all vehicles to upload their models for the global model updating. However, vehicles may usually drive out of the coverage of the RSU before they obtain their local models through training, which reduces the accuracy of the global model. It is necessary to propose an asynchronous federated learning (AFL) to solve this problem, where the RSU updates the global model once it receives a local model from a vehicle. However, the amount of data, computing capability and vehicle mobility may affect the accuracy of the global model. In this paper, we jointly consider the amount of data, computing capability and vehicle mobility to design an AFL scheme to improve the accuracy of the global model. Extensive simulation experiments have demonstrated that our scheme outperforms the FL scheme

cs.LG↗

arXiv2023

Towards V2I Age-aware Fairness Access: A DQN Based Intelligent Vehicular Node Training and Test Method

Vehicles on the road exchange data with base station (BS) frequently through vehicle to infrastructure (V2I) communications to ensure the normal use of vehicular applications, where the IEEE 802.11 distributed coordination function (DCF) is employed to allocate a minimum contention window (MCW) for channel access. Each vehicle may change its MCW to achieve more access opportunities at the expense of others, which results in unfair communication performance. Moreover, the key access parameters MCW is the privacy information and each vehicle are not willing to share it with other vehicles. In this uncertain setting, age of information (AoI) is an important communication metric to measure the freshness of data, we design an intelligent vehicular node to learn the dynamic environment and predict the optimal MCW which can make it achieve age fairness. In order to allocate the optimal MCW for the vehicular node, we employ a learning algorithm to make a desirable decision by learning from replay history data. In particular, the algorithm is proposed by extending the traditional DQN training and testing method. Finally, by comparing with other methods, it is proved that the proposed DQN method can significantly improve the age fairness of the intelligent node.

cs.NI↗

arXiv2023

Optical spectroscopy and band structure calculations of structural phase transition in the Vanadium-based kagome metal ScV$_6$Sn$_6$

In condensed matter physics, materials with kagome lattice display a range of exotic quantum states, including charge density wave (CDW), superconductivity and magnetism. Recently, the intermetallic kagome metal ScV6Sn6 was discovered to undergo a first-order structural phase transition with the formation of a root3xroot3x3 CDW at around 92 K. The bulk electronic band properties are crucial to understanding the origin of the structural phase transition. Here, we conducted an optical spectroscopy study in combination with band structure calculations across the structural transition. Our findings showed abrupt changes in the optical reflectivity/conductivity spectra as a result of the structural transition, without any observable gap formation behavior. The optical measurements and band calculations actually reveal a sudden change of the band structure after transition. It is important to note that this phase transition is of the first-order type, which distinguishes it from conventional density-wave type condensations. Our results provide an insight into the origin of the structural phase transition in this new and unique kagome lattice.

cond-mat.str-el↗

arXiv2023

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts.

cs.CV↗

arXiv2023

A Deep Reinforcement Learning Approach for Online Parcel Assignment

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. The OPA problem is challenging due to its stochastic nature: each parcel's candidate routes, which depends on the parcel's origin, destination, weight, etc., are unknown until its order is placed, and the total parcel volume is uncertain in advance. To tackle this challenge, we propose the PPO-OPA algorithm based on deep reinforcement learning that shows competitive performance. More specifically, we introduce a novel Markov Decision Process (MDP) framework to model the OPA problem, and develop a policy gradient algorithm that adopts attention networks for policy evaluation. By designing a dedicated reward function, our proposed algorithm can achieve a lower total cost with smaller violation of constraints, comparing to the traditional method which assigns parcels to candidate routes proportionally. In addition, the performances of our proposed algorithm and the Primal-Dual algorithm are comparable, while the later assumes a known total parcel volume in advance, which is unrealistic in practice.

cs.LG↗