Advanced artificial intelligence techniques, such as federated learning, has been applied to broad areas, e.g., image classification, speech recognition, smart city, and healthcare. Despite intensive research on federated learning, existing schemes are vulnerable to attacks and can hardly meet the security requirements for real-world applications. The problem of designing a secure federated learning framework to ensure the correctness of training procedure has not been sufficiently studied and remains open. In this paper, we propose VFChain, a verifiable and auditable federated learning framework based on the blockchain system. First, to provide the verifiability, a committee is selected through the blockchain to collectively aggregate models and record verifiable proofs in the blockchain. Then, to provide the auditability, a novel authenticated data structure is proposed for blockchain to improve the search efficiency of verifiable proofs and support a secure rotation of committee. Finally, to further improve the search efficiency, an optimization scheme is proposed to support multiple-model learning tasks. We implement VFChain and conduct extensive experiments by utilizing the popular deep learning models over the public real-world dataset. The evaluation results demonstrate the effectiveness of our proposed VFChain system.
28 December 2021 in IEEE Transactions on Parallel and Distributed Systems
Deep learning (DL) is becoming increasingly popular in many domains, including computer vision, speech recognition, self-driving automobiles, etc. GPU can train DL models efficiently but is expensive, which motivates users to share GPU resource to reduce money costs in practice. To ensure efficient sharing among multiple users, it is necessary to develop efficient GPU resource management and scheduling solutions. However, existing ones have several shortcomings. First, they require the users to specify the job resource requirement which is usually quite inaccurate and leads to cluster resource underutilization. Second, when scheduling DL jobs, they rarely take the cluster network characteristics into consideration, resulting in low job execution performance. To overcome the above issues, we propose Liquid, an efficient GPU resource management platform for DL jobs with intel li gent resource re qui rement estimation and sche d uling. First, we propose a regression model based method for job resource requirement estimation to avoid users over-allocating computing resources. Second, we propose intelligent cluster network-efficient scheduling methods in both immediate and batch modes based on the above resource requirement estimation techniques. Third, we further propose three system-level optimizations, including pre-scheduling data transmission, fine-grained GPU sharing, and event-driven communication. Experimental results show that our Liquid can accelerate the job execution speed by 18% on average and shorten the average job completion time (JCT) by 21% compared with cutting-edge solutions. Moreover, the proposed optimization methods are effective in various scenarios.
10 October 2024 in IEEE/ACM Transactions on Networking
Nowadays, there exists a lot of cross-region data transmission demand on the cloud. It is promising to use serverless computing for data compressing to save the total data size. However, it is challenging to estimate the data transmission time and monetary cost with serverless compression. In addition, minimizing the data transmission cost is non-trivial due to the enormous parameter space. This paper focuses on this problem and makes the following contributions: 1) We propose empirical data transmission time and monetary cost models based on serverless compression. It can also predict compression information, e.g., ratio and speed using chunk sampling and machine learning techniques. 2) For single-task cloud data transmission, we propose two efficient parameter search methods based on Sequential Quadratic Programming (SQP) and Eliminate then Divide and Conquer (EDC) with proven error upper bounds. Besides, we propose a parameter fine-tuning strategy to deal with transmission bandwidth variance. 3) Furthermore, for multi-task scenarios, a parameter search method based on dynamic programming and numerical computation is proposed. We have implemented the system called Fluid-Shuttle, which includes straggler optimization, cache optimization, and the autoscaling decompression mechanism. Finally, we evaluate the performance of Fluid-Shuttle with various workloads and applications on the real-world AWS serverless computing platform. Experimental results show that the proposed approach can improve the parameter search efficiency by over 3 $\times$ compared with the state-of-art methods and achieves better parameter quality. In addition, our approach achieves higher time efficiency and lower monetary cost compared with competing cloud data transmission approaches.
21 December 2021 in IEEE Transactions on Mobile Computing
Several recent works have studied mobile charging under the “one-to-many” charging pattern where a single charger can charge multiple devices simultaneously. However, most of them focus on path planning and charging time allocation, but overlook the underlying dependence of the charging efficiency on initial deployment positions of chargers. This paper studies the problem of P lacing directional w I reless chargers with L imited m O bili T y (PILOT), that is, maximize the overall charging utility for a set of static rechargeable devices on a 2D plane by determining deployment positions, stop positions and orientations, and portions of time for all deployed chargers that can move in a limited area after their deployment. To the best of our knowledge, we are the first to study placement of mobile directional chargers under the “one-to-many” pattern. To address PILOT, we propose a $(\frac{1}{2}-\epsilon)$ -approximation algorithm. First, we present a method to approximate nonlinear charging power of chargers, and further propose an approach to construct Maximal Covered Set uniform subareas to reduce the infinite continuous search space for stop positions and orientations to a finite discrete one. Second, we present geometrical techniques to further reduce the infinite solution space for candidate deployment positions to a finite one without performance loss, and transform PILOT to a mixed integer nonlinear programming problem. Finally, we propose a linear programming based greedy algorithm to address it. Simulation and experimental results show that our algorithm outperforms six comparison algorithms by $19.74 \% \sim 500.01 \%$ .
15 December 2025 in ACM Transactions on Information Systems
API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.
1 January 2016 in Computational Intelligence and Neuroscience
Electroencephalogram- (EEG-) based brain-computer interface (BCI) systems usually utilize one type of changes in the dynamics of brain oscillations for control, such as event-related desynchronization/synchronization (ERD/ERS), steady state visual evoked potential (SSVEP), and P300 evoked potentials. There is a recent trend to detect more than one of these signals in one system to create a hybrid BCI. However, in this case, EEG data were always divided into groups and analyzed by the separate processing procedures. As a result, the interactive effects were ignored when different types of BCI tasks were executed simultaneously. In this work, we propose an improved tensor based multiclass multimodal scheme especially for hybrid BCI, in which EEG signals are denoted as multiway tensors, a nonredundant rank-one tensor decomposition model is proposed to obtain nonredundant tensor components, a weighted fisher criterion is designed to select multimodal discriminative patterns without ignoring the interactive effects, and support vector machine (SVM) is extended to multiclass classification. Experiment results suggest that the proposed scheme can not only identify the different changes in the dynamics of brain oscillations induced by different types of tasks but also capture the interactive effects of simultaneous tasks properly. Therefore, it has great potential use for hybrid BCI.