Efficient federated multi-view learning

Multi-view subspace learning via bidirectional sparsity

Failures are normal rather than exceptional in cloud computing environments, high fault tolerance issue is one of the major obstacles for opening up a new era of high serviceability cloud computing as fault tolerance plays a key role in ensuring cloud serviceability. Fault tolerant service is an essential part of Service Level Objectives (SLOs) in clouds. To achieve high level of cloud serviceability and to meet high level of cloud SLOs, a foolproof fault tolerance strategy is needed. In this paper, the definitions of fault, error, and failure in a cloud are given, and the principles for high fault tolerance objectives are systematically analyzed by referring to the fault tolerance theories suitable for large-scale distributed computing environments. Based on the principles and semantics of cloud fault tolerance, a dynamic adaptive fault tolerance strategy DAFT is put forward. It includes: (i) analyzing the mathematical relationship between different failure rates and two different fault tolerance strategies, which are checkpointing fault tolerance strategy and data replication fault tolerance strategy; (ii) building a dynamic adaptive checkpointing fault tolerance model and a dynamic adaptive replication fault tolerance model by combining the two fault tolerance models together to maximize the serviceability and meet the SLOs; and (iii) evaluating the dynamic adaptive fault tolerance strategy under various conditions in large-scale cloud data centers and consider different system centric parameters, such as fault tolerance degree, fault tolerance overhead, response time, etc. Theoretical as well as experimental results conclusively demonstrate that the dynamic adaptive fault tolerance strategy DAFT has high potential as it provides efficient fault tolerance enhancements, significant cloud serviceability improvement, and great SLOs satisfaction. It efficiently and effectively achieves a trade-off for fault tolerance objectives in cloud computing environments.

Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views, requiring no access to earlier views of data. However, MVCIL is challenged by the catastrophic forgetting of old information and the interference with learning new concepts. To address this, we first develop a randomization-based representation learning technique serving for feature extraction to guarantee their separate view-optimal working states, during which multiple views belonging to a class are presented sequentially; Then, we integrate them one by one in the orthogonality fusion subspace spanned by the extracted features; Finally, we introduce selective weight consolidation for learning-without-forgetting decision-making while encountering new classes. Extensive experiments on synthetic and real-world datasets validate the effectiveness of our approach.

Most previous work on fault-tolerant (FT) multiprocessor design has concentrated on deterministic k-fault-tolerant (k-FT) designs in which exactly k spare processors and some spare switches and links are added to construct multiprocessors that can tolerate any k processor faults. However, after k faults are reconfigured around, much of the extra links and switches can remain unutilized. We show how to use the node-covering principle of Dutt and Hayes (1992) and error correcting codes in order to construct probabilistic designs with very high average fault tolerance but low wiring and switch overhead. This design methodology is applicable to any multiprocessor interconnection topology. We also obtain the deterministic fault tolerance for these designs and develop efficient layout strategies for them. >

Multi-view multi-label learning serves an important framework to learn from objects with diverse representations and rich semantics. Existing multi-view multi-label learning techniques focus on exploiting shared subspace for fusing multi-view representations, where helpful view-specific information for discriminative modeling is usually ignored. In this paper, a novel multi-view multi-label learning approach named SIMM is proposed which leverages shared subspace exploitation and view-specific information extraction. For shared subspace exploitation, SIMM jointly minimizes confusion adversarial loss and multi-label loss to utilize shared information from all views. For view-specific information extraction, SIMM enforces an orthogonal constraint w.r.t. the shared subspace to utilize view-specific discriminative information. Extensive experiments on real-world data sets clearly show the favorable performance of SIMM against other state-of-the-art multi-view multi-label learning approaches.

This work targets design of a robust universal logic gate in Quantum-dot cellular automata (RUQCA) that realizes majority and minority functions simultaneously with high fault tolerance. An alternative tile structure of QCA with hybrid cell orientations is formulated to maximize its throughput. The characterization of defective behaviour of RUQCA gate under cell deposition, cell misplacement and cell misalignment defects is investigated. The results show that the proposed RUQCA gate has very high fault coverage of 95%. The synthesis of fault tolerant multiplexer using RUQCA, with 90% fault tolerance, establishes the effectiveness of RUQCA.

The existing Multi-View Learning (MVL) is to discuss how to learn from patterns with multiple information sources and has been proven its superior generalization to the usual Single-View Learning (SVL). However, in most real-world cases there are just single source patterns available such that the existing MVL cannot work. The purpose of this paper is to develop a new multi-view regularization learning for single source patterns. Concretely, for the given single source patterns, we first map them into M feature spaces by M different empirical kernels, then associate each generated feature space with our previous proposed Discriminative Regularization (DR), and finally synthesize M DRs into one single learning process so as to get a new Multi-view Discriminative Regularization (MVDR), where each DR can be taken as one view of the proposed MVDR. The proposed method achieves: (1) the complementarity for multiple views generated from single source patterns; (2) an analytic solution for classification; (3) a direct optimization formulation for multi-class problems without one-against-all or one-against-one strategies.

Triple redundant fault tolerance: A hardware-implemented approach

The author reviews number-theoretic techniques for achieving hardware modularity in order to facilitate high data rates, testability, reliability, and fault tolerance, in VLSI digital signal processing systems. The theory of RNS (residue number system) error detection and correction is reviewed, and the special properties of modular systems are discussed for providing a rich environment for fault tolerant designs. Questions of reliability and fault tolerance on both the integrated circuit level and higher systems levels are discussed. The design of a convolutional back-projection digital processor for synthetic aperture radar (SAR) image processing is used as an example to investigate appropriate interactions between circuit-level error checking and system-level fault tolerance. >

Deep multi-view representation learning focuses on training a unified low-dimensional representation for data with multiple sources or modalities. With the rapidly growing attention of graph neural networks, more and more researchers have introduced various graph models into multi-view learning. Although considerable achievements have been made, most existing methods usually propagate information in a single view and fuse multiple information only from the perspective of attributes or relationships. To solve the aforementioned problems, we propose an efficient model termed Dual Fusion-Propagation Graph Neural Network (DFP-GNN) and apply it to deep multi-view clustering tasks. The proposed method is designed with three submodules and has the following merits: a) The proposed view-specific and cross-view propagation modules can capture the consistency and complementarity information among multiple views; b) The designed fusion module performs multi-view information fusion with the attributes of nodes and the relationships among them simultaneously. Experiments on popular databases show that DFP-GNN achieves significant results compared with several state-of-the-art algorithms.

Datacenter networks have been designed to tolerate failures of network equipment and provide sufficient bandwidth. In practice, however, failures and maintenance of networking and power equipment often make tens to thousands of servers unavailable, and network congestion can increase service latency. Unfortunately, there exists an inherent tradeoff between achieving high fault tolerance and reducing bandwidth usage in network core; spreading servers across fault domains improves fault tolerance, but requires additional bandwidth, while deploying servers together reduces bandwidth usage, but also decreases fault tolerance. We present a detailed analysis of a large-scale Web application and its communication patterns. Based on that, we propose and evaluate a novel optimization framework that achieves both high fault tolerance and significantly reduces bandwidth usage in the network core by exploiting the skewness in the observed communication patterns.

Recent researches on multiview learning have received widespread attention due to the increasing generalization of multiview data. As an effective probabilistic model, random walk has also shown encouraging performance in various fields. To further exploit the potential of utilizing random walk schemes to address multiview learning problems, this article proposes a simple yet efficient multigraph random walk scheme for both multiview clustering and semisupervised classification tasks. The proposed model integrates random walk with multiview learning, and recursively learns a globally stable probability distribution matrix from multiple views, on the basis of which the label indicator is obtained in the scene of clustering or semisupervised classification. Furthermore, an adaptive weight vector is learned to incorporate the diversity and complementarity of multiview data. Besides, the relationships between the proposed scheme and spectral clustering, neighborhood embedding and manifold embedding are analyzed theoretically. Finally, comprehensive comparative experiments are conducted with several state-of-the-art multiview clustering and semisupervised classification methods on eight real-world datasets. The experimental results demonstrate the superiority of the proposed method in terms of both clustering and classification performance.

Multiphase motors have high reliability and good fault tolerance ability, and are widely used in electric drive systems such as electric vehicles, ships and aircrafts. In these systems, the peak power of the motor is high, but it works in the light load state for a long time. When the motor is in fault-tolerant state, the heating of windings and iron core is unbalanced, which decreases the motor performance. In this paper, an asymmetric winding multi-phase motor structure is proposed. The performance with different slot pole combination and winding distribution are compared. The torque, efficiency and temperature rise under different working modes such as normal operation, whole set of winding cut off and single-phase winding cut off are analyzed. The results show that asymmetric windings can improve the efficiency of the system under longterm light load conditions. The single-layer and double-layer winding motors have lower torque and higher ripple under fault-tolerant conditions; and the performance degradation can be suppressed by using multi-layer windings, and the suitable slot pole combination for multi-layer windings is obtained through comparative analysis.

Effective load balancing approach in cloud computing using Inspired Lion Optimization Algorithm

For modern high performance systems, aggressive technology and voltage scaling has drastically increased their susceptibility to soft errors. At the grand scale of cloud computing, it is clear that soft error induced failures will occur far more frequently, but it is unclear as to how to effectively apply current error detection and fault tolerance techniques in scale. In this paper, we focus on energy-aware fault tolerant scheduling in public, multi-user cloud systems, and explore the three-way tradeoff between reliability (in terms of soft error resiliency), performance and energy. Through a systematically optimized resource allocation, error detection approach selection, virtual machine placement, spatial/temporal redundancy augmentation and task scheduling process, the cloud service provider can achieve high error coverage and fault tolerance confidence while minimizing global energy costs under user deadline constraints. Our scheduling algorithm includes a static scheduling phase that operates on task graph based workload inputs prior to execution, and a light-weight dynamic scheduler that migrates tasks during execution in case of excessive reexecutions. All schedules are evaluated on a runtime simulation engine that (1) mimics the performance fluctuations in cloud systems, and (2) supports the injection of arbitrary fault patterns. Compared to current virtual machine or task replication techniques, we are able to reduce overall application failure rates by over 50% with approximately 76% total energy overhead.