Qiong Wu

Qiong Wu, Yu Zhao, Qiang Fan et al.

The vehicular edge computing (VEC) can cache contents in different RSUs at the network edge to support the real-time vehicular applications. In VEC, owing to the high-mobility characteristics of vehicles, it is necessary to cache the user data in advance and learn the most popular and interesting contents for vehicular users. Since user data usually contains privacy information, users are reluctant to share their data with others. To solve this problem, traditional federated learning (FL) needs to update the global model synchronously through aggregating all users' local models to protect users' privacy. However, vehicles may frequently drive out of the coverage area of the VEC before they achieve their local model trainings and thus the local models cannot be uploaded as expected, which would reduce the accuracy of the global model. In addition, the caching capacity of the local RSU is limited and the popular contents are diverse, thus the size of the predicted popular contents usually exceeds the cache capacity of the local RSU. Hence, the VEC should cache the predicted popular contents in different RSUs while considering the content transmission delay. In this paper, we consider the mobility of vehicles and propose a cooperative Caching scheme in the VEC based on Asynchronous Federated and deep Reinforcement learning (CAFR). We first consider the mobility of vehicles and propose an asynchronous FL algorithm to obtain an accurate global model, and then propose an algorithm to predict the popular contents based on the global model. 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. Extensive experimental results have demonstrated that the CAFR scheme outperforms other baseline caching schemes.

Qiong Wu, Xu Chen, Tao Ouyang et al.

Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to frequently exchange model parameters of large data size with the remote cloud server directly via wide-area networks (WAN), leading to significant communication overhead and long transmission time. To mitigate the communication bottleneck, we resort to the hierarchical federated learning paradigm of HiFL, which reaps the benefits of mobile edge computing and combines synchronous client-edge model aggregation and asynchronous edge-cloud model aggregation together to greatly reduce the traffic volumes of WAN transmissions. Specifically, we first analyze the convergence bound of HiFL theoretically and identify the key controllable factors for model performance improvement. We then advocate an enhanced design of HiFlash by innovatively integrating deep reinforcement learning based adaptive staleness control and heterogeneity-aware client-edge association strategy to boost the system efficiency and mitigate the staleness effect without compromising model accuracy. Extensive experiments corroborate the superior performance of HiFlash in model accuracy, communication reduction, and system efficiency.

Qiong Wu, Siyuan Wang, Pingyi Fan et al.

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.

Qingze Fang, Zhiwei Zhai, Shuai Yu et al.

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. However, training AI models centrally with the assistance of SAGIN faces the challenges of highly constrained network topology, inefficient data transmission, and privacy issues. To tackle these challenges, we first propose a novel topology-aware federated learning framework for the SAGIN, namely Olive Branch Learning (OBL). Specifically, the IoRT devices in the ground layer leverage their private data to perform model training locally, while the air nodes in the air layer and the ring-structured low earth orbit (LEO) satellite constellation in the space layer are in charge of model aggregation (synchronization) at different scales.To further enhance communication efficiency and inference performance of OBL, an efficient Communication and Non-IID-aware Air node-Satellite Assignment (CNASA) algorithm is designed by taking the data class distribution of the air nodes as well as their geographic locations into account. Furthermore, we extend our OBL framework and CNASA algorithm to adapt to more complex multi-orbit satellite networks. We analyze the convergence of our OBL framework and conclude that the CNASA algorithm contributes to the fast convergence of the global model. Extensive experiments based on realistic datasets corroborate the superior performance of our algorithm over the benchmark policies.

Hongbiao Zhu, Qiong Wu, Qiang Fan et al.

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.

Qiong Wu, Jiahan Li, Pingyang Dai et al.

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.

Qiong Wu, Shubin Huang, Yiyi Zhou et al.

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.

Shubin Huang, Qiong Wu, Yiyi Zhou et al.

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.

Qiong Wu, Jiaer Xia, Pingyang Dai et al.

Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality gap caused by cameras operating on different spectra. Existing VI-ReID methods mainly focus on learning general features across modalities, often at the expense of feature discriminability. To address this issue, we present a novel cycle-construction-based network for neutral yet discriminative feature learning, termed CycleTrans. Specifically, CycleTrans uses a lightweight Knowledge Capturing Module (KCM) to capture rich semantics from the modality-relevant feature maps according to pseudo queries. Afterwards, a Discrepancy Modeling Module (DMM) is deployed to transform these features into neutral ones according to the modality-irrelevant prototypes. To ensure feature discriminability, another two KCMs are further deployed for feature cycle constructions. With cycle construction, our method can learn effective neutral features for visible and infrared images while preserving their salient semantics. Extensive experiments on SYSU-MM01 and RegDB datasets validate the merits of CycleTrans against a flurry of state-of-the-art methods, +4.57% on rank-1 in SYSU-MM01 and +2.2% on rank-1 in RegDB.

Siyuan Wang, Qiong Wu, Qiang Fan et al.

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

Qiong Wu, Jian Li, Zhenming Liu et al.

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. Our goal is to forecast the future evolution of ensembles of multivariate time series in such applications (e.g., the future return of a financial asset or the future popularity of a Twitter account). Designing ML algorithms for such systems requires addressing the challenges of high-dimensional interactions and non-linearity. Existing approaches usually adopt an ad-hoc approach to integrating high-dimensional techniques into non-linear models and recent studies have shown these approaches have questionable efficacy in time-evolving interacting systems. To this end, we propose a novel framework, which we dub as the additive influence model. Under our modeling assumption, we show that it is possible to decouple the learning of high-dimensional interactions from the learning of non-linear feature interactions. To learn the high-dimensional interactions, we leverage kernel-based techniques, with provable guarantees, to embed the entities in a low-dimensional latent space. To learn the non-linear feature-response interactions, we generalize prominent machine learning techniques, including designing a new statistically sound non-parametric method and an ensemble learning algorithm optimized for vector regressions. Extensive experiments on two common applications demonstrate that our new algorithms deliver significantly stronger forecasting power compared to standard and recently proposed methods.

Viet Duong, Qiong Wu, Zhengyi Zhou et al.

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.

Cui Zhang, Xiao Xu, Qiong Wu et al.

In vehicle edge computing (VEC), asynchronous federated learning (AFL) is used, where the edge receives a local model and updates the global model, effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles, renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model, and the vehicle may also be affected by Byzantine attacks, leading to the deterioration of the vehicle data. However, based on deep reinforcement learning (DRL), we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL. At the same time, when aggregating AFL, we can focus on those vehicles with better performance to improve the accuracy and safety of the system. In this paper, we proposed a vehicle selection scheme based on DRL in VEC. 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.

Qiong Wu, Wei Yu, Yiyi Zhou et al.

With ever increasing parameters and computation, vision-language pre-trained (VLP) models exhibit prohibitive expenditure in downstream task adaption. Recent endeavors mainly focus on parameter efficient transfer learning (PETL) for VLP models by only updating a small number of parameters. However, excessive computational overhead still plagues the application of VLPs. In this paper, we aim at parameter and computation efficient transfer learning (PCETL) for VLP models. In particular, PCETL not only needs to limit the number of trainable parameters in VLP models, but also to reduce the computational redundancy during inference, thus enabling a more efficient transfer. To approach this target, we propose a novel dynamic architecture skipping (DAS) approach towards effective PCETL. Instead of directly optimizing the intrinsic architectures of VLP models, DAS first observes the significances of their modules to downstream tasks via a reinforcement learning (RL) based process, and then skips the redundant ones with lightweight networks, i.e., adapters, according to the obtained rewards. In this case, the VLP model can well maintain the scale of trainable parameters while speeding up its inference on downstream tasks. To validate DAS, we apply it to two representative VLP models, namely ViLT and METER, and conduct extensive experiments on a bunch of VL tasks. The experimental results not only show the great advantages of DAS in reducing computational complexity, e.g. -11.97% FLOPs of METER on VQA2.0, but also confirm its competitiveness against existing PETL methods in terms of parameter scale and performance. Our source code is given in our appendix.

Hao Zeng, Qiong Wu, Kunpeng Han et al.

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.

Qiong Wu, Zhenming Liu

Large-scale interactive web services and advanced AI applications make sophisticated decisions in real-time, based on executing a massive amount of computation tasks on thousands of servers. Task schedulers, which often operate in heterogeneous and volatile environments, require high throughput, i.e., scheduling millions of tasks per second, and low latency, i.e., incurring minimal scheduling delays for millisecond-level tasks. Scheduling is further complicated by other users' workloads in a shared system, other background activities, and the diverse hardware configurations inside datacenters. We present Rosella, a new self-driving, distributed approach for task scheduling in heterogeneous clusters. Rosella automatically learns the compute environment and adjusts its scheduling policy in real-time. The solution provides high throughput and low latency simultaneously because it runs in parallel on multiple machines with minimum coordination and only performs simple operations for each scheduling decision. Our learning module monitors total system load and uses the information to dynamically determine optimal estimation strategy for the backends' compute-power. Rosella generalizes power-of-two-choice algorithms to handle heterogeneous workers, reducing the max queue length of O(log n) obtained by prior algorithms to O(log log n). We evaluate Rosella with a variety of workloads on a 32-node AWS cluster. Experimental results show that Rosella significantly reduces task response time, and adapts to environment changes quickly.

Yong Liu, Yinan Zhang, Qiong Wu et al.

Interactive recommendation that models the explicit interactions between users and the recommender system has attracted a lot of research attentions in recent years. Most previous interactive recommendation systems only focus on optimizing recommendation accuracy while overlooking other important aspects of recommendation quality, such as the diversity of recommendation results. In this paper, we propose a novel recommendation model, named \underline{D}iversity-promoting \underline{D}eep \underline{R}einforcement \underline{L}earning (D$^2$RL), which encourages the diversity of recommendation results in interaction recommendations. More specifically, we adopt a Determinantal Point Process (DPP) model to generate diverse, while relevant item recommendations. A personalized DPP kernel matrix is maintained for each user, which is constructed from two parts: a fixed similarity matrix capturing item-item similarity, and the relevance of items dynamically learnt through an actor-critic reinforcement learning framework. We performed extensive offline experiments as well as simulated online experiments with real world datasets to demonstrate the effectiveness of the proposed model.