Federated learning (FL) is revolutionizing machine learning by enabling multiple decentralized clients to collaboratively train a shared model. In mobile scenarios, client devices exchange model parameters with a central server via wireless channels. However, designing efficient wireless FL (WFL) is challenging due to limited energy and channel capacity. To fully utilize communication resources, over-the-air (OTA) computation has been introduced, allowing direct aggregation of analog parameter signals. However, it conceals clients’ information from the server, making advanced client selection strategies, e.g., cluster-based client selection, and sparsification compression algorithms like TopK inapplicable. To address these limitations, we propose the WFL with Voting-based Clustering (WFL-VC) algorithm, which can integrate advanced client selection and the TopK model sparsification algorithm with OTA. WFL-VC consists of two phases: 1) Phase 1: clients vote on significant parameters based on local models, allowing the server to select clients and identify the global Topk parameters; and 2) Phase 2: the selected clients upload model update parameters with globally aligned indices for over-the-air computation at the server. By combining OTA computation with cluster-based client selection and TopK sparsification, WFL-VC substantially reduces the energy consumption of OTA-based WFL. Extensive experiments on real-world datasets show that WFL-VC outperforms competitive baselines while consuming considerably less energy.

To address growing concerns about data privacy on mobile devices, the federated learning (FL) paradigm enables clients to collaboratively train models while sharing only local model updates. However, privacy risks remain in FL, as adversaries can still infer sensitive information from these updates. To enhance secure aggregation in FL, various protection mechanisms combining encryption and multi-party computation (MPC) have been proposed. These approaches, however, often introduce substantial communication and computational overhead, making secure aggregation impractical on resource-constrained devices, e.g., smart phones. To tackle these efficiency challenges, we are among the first to propose the integration of differential privacy (DP) with encryption and MPC for secure aggregation. Our proposed protocol, Federated Learning with Noise-based Secure Aggregation (FedNSA), injects noise through DP to obfuscate individual model updates. Encryption is employed to correlate the noise across different clients, while MPC ensures perfect noise cancellation at the server side. Finally, we theoretically analyze its advantages and conduct extensive experiments on public datasets to demonstrate the superiority of our approach across multiple dimensions in comparison with the state-of-the-art baselines.

The scarcity data of medical field brings the collaborative training in medical vision-language pre-training (VLP) cross different clients. Therefore, the collaborative training in medical VLP faces two challenges: First, the medical data requires privacy, thus can not directly shared across different clients. Second, medical data distribution across institutes is typically heterogeneous, hindering local model alignment and representation capabilities. To simultaneously overcome these two challenges, we propose the framework called personalized model selector with fused multimodal information (PMS-FM). The contribution of PMS-FM is two-fold: 1) PMS-FM uses embeddings to represent information in different formats, allowing for the fusion of multimodal data. 2) PMS-FM adapts to personalized data distributions by training multiple models. A model selector then identifies and selects the best-performing model for each individual client. Extensive experiments with multiple real-world medical datasets demonstrate the superb performance of PMS-FM over existing federated learning methods on different zero-shot classification tasks.

It is known that federated learning (FL) incurs heavy communication overhead for model training by exchanging model updates between clients and the parameter server (PS) over the Internet for multiple rounds. Compressing model updates is an effective approach to alleviating communication overhead in FL. Yet the tradeoff between compression and model accuracy in the networked environment remains unclear and, for simplicity, most implementations adopt a fixed compression rate only during the entire learning process. In this paper, we for the first time systematically examine this tradeoff, explicitly quantifying the relation between the compression error, the final model accuracy and the learning rate. Specifically, we factor the compression error of each global iteration into the convergence rate analysis under non-convex loss for both unbiased and biased compression algorithms. We then present an adaptation framework to maximize the final model accuracy by strategically adjusting the compression rate in each iteration. We further discuss key implementation issues of our framework in practical networks with classical compression algorithms. Experiments over the most representative MNIST, CIFAR-10 and CIFAR-100 datasets demonstrate that our solutions effectively shrink network traffic volume while maintain high model accuracy in FL.

With the widespread use of GPS devices and the advancement of location-based services, a vast amount of trajectory data has been collected and mined for various applications. Trajectory clustering, which categorizes trajectories into distinct groups, is the fundamental functionality of trajectory data mining. The challenge is how to cluster on a mass of trajectory data efficiently and universally with satisfying results. The raw trajectory clustering algorithms are universal, but trapped in the dilemma between efficiency and desirable results. Other approaches, such as density-based, road network-based, and deep learning-based algorithms, encounter issues like high time complexity, loss of trajectory integrity, reliance on road networks, and data quality during training. To tackle these challenges, we first propose the efficient KMCT (k-Means Clustering of Trajectories) algorithm based on a semantic interpolation transformation to cluster raw trajectories and achieve satisfying results. Additionally, we introduce the DA-KMCT (Density Accelerated k-Means Clustering of Trajectories) algorithm to further boost the clustering process based on trajectory densities and an optimized centroid selecting strategy. Moreover, we present a novel clustering evaluation method called IOD, which efficiently estimates clustering results on large-scale datasets with linear time complexity. Experimental results on real-world datasets demonstrate that KMCT and DA-KMCT outperform five related methods in terms of clustering quality and time efficiency, and the proposed IOD evaluation shows a strong correlation with the Silhouette Coefficient, offering a reliable and efficient alternative for evaluating clustering results.

Temporal Knowledge Graph (TKG) reasoning, aiming to predict future unknown facts based on historical information, has attracted considerable attention due to its great practical value.Insight into history is the key to predict the future.However, most existing TKG reasoning models singly capture repetitive history, ignoring the entity's multi-hop neighbour history which can provide valuable background knowledge for TKG reasoning.In this paper, we propose Multi-Granularity History and Entity Similarity Learning (MGESL) model for Temporal Knowledge Graph Reasoning, which models historical information from both coarse-grained and fine-grained history.Since similar entities tend to exhibit similar behavioural patterns, we also design a hypergraph convolution aggregator to capture the similarity between entities.Furthermore, we introduce a more realistic setting for the TKG reasoning, where candidate entities are already known at the timestamp to be predicted.Extensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed model.

Time series classification assigns predefined labels or classes to sequences of data points ordered chronologically, which is a fundamental task for time series analysis. Existing time series classification methods mainly focus on a specific type of time series (i.e., univariate time series or multivariate time series), while failing to support both of them efficiently and effectively. In addition, most of existing multivariate time series classification methods model all variables collectively, resulting in protracted computational times and suboptimal accuracy. In this paper, we introduce TSec, an innovative time series classification framework that exhibits high training efficiency and classification accuracy for both univariate time series and multivariate time series. During online classification, TSec first involves sequence segmentation and de-duplication, and then employs pre-trained models to perform classifications. To opti-mize the classification performance, TSec (i) utilizes correlation analysis to reveal closely interconnected groups of variables within multivariate time series data; (ii) incorporates time series alignment and different sliding windows to generate potential shapelets; (iii) applies PAA and SAX techniques to eliminate duplicates, thereby enhancing the quality of shapelets; (iv) adopts Bi-GRU and GCN-GRU models to effectively capture the characteristics of the two types of time series. Extensive experiments on 112 public univariate time series datasets and 26 public multivariate time series datasets show that TSec can achieve both high efficiency and accuracy compared with the state-of-the-art 19 toolkits.

Optimization and sampling based algorithms are two branches of methods in machine learning, while existing safe reinforcement learning (RL) algorithms are mainly based on optimization, it is still unclear whether sampling based methods can lead to desirable performance with safe policy. This paper formulates the Langevin policy for safe RL, and proposes Langevin Actor-Critic (LAC) to accelerate the process of policy inference. Concretely, instead of parametric policy, the proposed Langevin policy provides a stochastic process that directly infers actions, which is the numerical solver to the Langevin dynamic of actions on the continuous time. Furthermore, to make Langevin policy practical on RL tasks, the proposed LAC accumulates the transitions induced by Langevin policy and reproduces them with a generator. Finally, extensive empirical results show the effectiveness and superiority of LAC on the MuJoCo-based and Safety Gym tasks.

The current pattern mining algorithms focus on discovering either frequent itemsets or high-utility itemsets. The goal of this research is to study the problem of mining frequent-utility itemsets. To solve this problem, two novel algorithms named FUIMTWU-Tree (Frequent-utility Itemset Mining based on TWU-Tree) and FUIMTF-Tree (Frequent-utility Itemset Mining based on TF-Tree) are presented based on the integration of IHUP and HUI-Miner. The TWU-tree and TF-Tree structures are utilised to avoid the unnecessary utility-list construction of itemsets that do not appear in a transaction dataset. The performance of the proposed algorithms is evaluated on various datasets. The results of the experiments demonstrate that FUIMTWU-Tree and FUIMTF-Tree perform efficiently in terms of speed, pruning performance and scalability.

Abstract As a fundamental part of indoor scene understanding, the research of indoor room layout estimation has attracted much attention recently. The task is to predict the structure of a room from a single image. In this paper, we illustrate that this task can be well solved even without sophisticated post-processing program, by adopting Feature Pyramid Networks (FPN) to solve this problem with adaptive changes. The proposed model employs two strategies to deliver quality output. First, it can predicts the coarse positions of key points correctly by preserving the order of these key points in the data augmentation stage. Then the coordinate of each corner point is refined by moving each corner point to its nearest image boundary as output. Our method has demonstrated great performance on the benchmark LSUN dataset on both processing efficiency and accuracy. Compared with the state-of-the-art end-to-end method, our method is two times faster at processing speed (32 ms) than its speed (86 ms), with 0.71% lower key point error and 0.2% higher pixel error respectively. Besides, the advanced two-step method is only 0.02% better than our result on key point error. Both the high efficiency and accuracy make our method a good choice for some real-time room layout estimation tasks.

The continuing development of intelligent transportation terminals and the massive generated traffic data have placed tremendous pressure on traffic data acquisition. However, most of existing intelligent transportation systems and applications rely on well-defined data, while few studies focus on how to collect live traffic data from various vehicle terminals in a large number. To solve this problem, we propose an efficient and non-blocking data acquisition system in this paper, which can retrieve traffic data based on different priority or QoS requirements from a large number of various terminals in real-time, so that the application layer can easily access certain type of traffic data it needs. Extensive experiment and simulation results prove the efficiency, reliability, and scalability of our proposed system. Besides, two real applications based on the proposed system are introduced in the paper.

Perceptual video coding (PVC) optimization has been an important video coding technique, which can be consistent with the perception characteristics of the human visual system (HVS). Currently, PVC schemes incorporating the just noticeable distortion (JND) model can obtain better performance gain in all PVC schemes. To further accelerate the JND computation for real-time video coding applications (e.g. surveillance video coding and conference video coding), this paper proposes a fast perceptual surveillance video coding (PSVC) scheme based on background model-driven JND estimation method. First, to utilize the surveillance scene characteristics, the computation complexity of JND estimation can be significantly decreased by reusing the content complexity of background regions. Then we apply the perceptive video coding scheme into the background modeling-based surveillance video codec. The proposed scheme adopts background modeling frame as background anchor. Experimental results show that the proposed scheme can yield remarkable time saving of 42.33% maximum and on average 34.76% with approximate bitrate reductions and similar subjective quality, compared to HEVC and other state-of-the-art schemes.

With rapid development of intelligent video surveillance systems based on cloud computing devices and edge computing devices in Cyber-Physical-Social Systems, massive surveillance video data has brings enormous challenge for video storage and transmission. However, existing surveillance video coding approaches hardly utilize intelligent video analysis results for improving video coding. This paper proposed a surveillance video coding scheme for traffic scene based on vehicle knowledge and shared library by cloud-edge computing in Cyber-Physical-Social Systems. Firstly, in order to provide the object library for synchronous application at the encode and decode side offline, a generation method of shared long-term foreground reference object library is proposed by using the existing large-scale monitoring vehicle object datasets. Then, to meet the requirement of low complexity and high-performance coding, a virtual foreground reference picture generation method with coding-oriented object retrieval is proposed. Experimental results show that the proposed scheme can obtain the satisfactory effect of the virtual foreground reference picture. Also, it can yield remarkable bit rate reductions, compared to HEVC.

There is an emerging trend of integrating machine learning (ML) techniques into database systems (DB). Considering that almost all the ML toolkits assume that the input of ML algorithms is a single table even though many real-world datasets are stored as multiple tables due to normalization in DB. Thus, data scientists have to perform joins before learning a ML model. This strategy is called learning after joins, which incurs redundancy avoided by normalization. In the area of ML, the Support Vector Machine (SVM) is one of the most standard classification tools. In this paper, we focus on the factorized SVM with gaussian kernels over normalized data. We present factorized learning approaches for two main SVM optimization methods, i.e., Gradient Descent (GD) and Sequential Minimal Optimization (SMO), by factorizing gaussian kernel function computation. Furthermore, we transform the normalized data into matrices, and boost the efficiency of SVM learning via linear algebra operations. Extensive experiments with nine real normalized data sets demonstrate the efficiency and scalability of our proposed approaches.

Reputation is useful for establishing trust between Web service (WS) providers and WS consumers. In the context of WS composition, a challenging issue of reputation management is to propagate a user's impression of a composite WS (i.e., the user's feedback rating) to its component WSs. In this paper, we propose a Shapley value based approach which can achieve fair impression propagation, that is, the reputation of a component WS is never awarded (or penalized) for the good (or bad) performances of the other peer component WSs in the same composite WS. The fairness of the proposed approach is validated through theoretical analysis and experimental results.

Service recommendation in a Web of services with uncertain QoS is a challenging problem. In this paper, we propose a reputation-based service recommendation framework. We formally define a service reputation model that analyzes the relations between uncertain QoS and reputation. We also devise a two-phase planning approach to constructing a composite service as the recommendation when none of existing services can fulfill the user's requirements alone. Furthermore, we design a utility difference based approach that can fairly distribute the overall rating of a composite service to its component services and theoretically prove its fairness. We evaluate the efficiency and fairness of our framework on a publicly available dataset: ICEBE05.