—To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (...
详细信息
As a continuous variant of Multi-armed bandits (MAB), $\mathcal{X}$-armed bandits have enriched many applications of online machine learning like personalized recommendation system. However, the attack and defense to ...
详细信息
As a continuous variant of Multi-armed bandits (MAB), $\mathcal{X}$-armed bandits have enriched many applications of online machine learning like personalized recommendation system. However, the attack and defense to the $\mathcal{X}$-armed bandits remain largely unexplored, though the MAB has proved to be vulnerable. In this paper, we aim to bridge this gap and investigate the robustness analysis for the $\mathcal{X}$-armed bandits. Specifically, we consider action-manipulation attack, which is practical but harder than the existing reward-manipulation attack. We propose an attack algorithm based on a lower bound tree (LBT), which can continuously hijack the learner’s action by perturbing $\mathcal{X}$-armed bandits’ high confidence tree (HCT) construction. As a result, the nodes including the arm targeted by the attacker is selected frequently with a sublinear attack cost. To defend against the LBT attack, we propose a robust version of the HCT algorithm, called RoHCT. We theoretically analyze that the regret of RoHCT is related to the upper bound of the total cost Q and still sublinear to total number of rounds T. We carry out experiments to evaluate the effectiveness of LBT and RoHCT.
We present a continuous reciprocal-kind Zhang dynamics (RKZD) model for solving the time-dependent linear matrixvector equation. On the basis of the model, we deduce its simplified form for solving the time-independen...
We present a continuous reciprocal-kind Zhang dynamics (RKZD) model for solving the time-dependent linear matrixvector equation. On the basis of the model, we deduce its simplified form for solving the time-independent linear matrix-vector equation (TILMVE). Subsequently, for more efficient computation and easier implementation in digital hardware, we utilize Euler forward difference formula (EFDF) to discretize the continuous RKZD model, resulting in a discrete RKZD algorithm. Finally, numerical experimental results attest to the feasibility and high effectiveness of the discrete RKZD algorithm for solving TILMVE. Comparisons with the discrete gradient neural network (or termed discrete gradient dynamics), Jacobi iteration, as well as Gauss-Seidel iteration highlight the superior convergence properties of the discrete RKZD algorithm.
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 cl...
详细信息
The Lombard effect refers to individuals’ unconscious modulation of vocal effort in response to variations in the ambient noise levels, intending to enhance speech intelligibility. The impact of different decibel lev...
详细信息
In cross-domain few-shot classification, nearest centroid classifier (NCC) aims to learn representations to construct a metric space where few-shot classification can be performed by measuring the similarities between...
详细信息
Modern large-scale systems and networks necessitate automated anomaly detection to support the high availability and quality of services. Since logs are an essential data source that can accurately reflect the state o...
Modern large-scale systems and networks necessitate automated anomaly detection to support the high availability and quality of services. Since logs are an essential data source that can accurately reflect the state of a system, log anomaly detection has attracted a lot of attention from researchers in both academia and industry. As the technology of artificial intelligence advances, plenty of work has adopted deep learning to detect log anomalies and achieved promising results. Nevertheless, it usually suffers from a lack of labels, excessive log sequence length, and low throughput problems when deploying to real-world systems. To address these challenges, we propose Log-Fold, an unsupervised Transformer-based log anomaly detection approach. In LogFold, we propose fold embedding, which can compress long log sequences to enhance the efficiency of anomaly detection. And we design a sequence reconstruction technique to enhance the effectiveness of anomaly detection. Our evaluation shows LogFold achieves 90.55% and 99.90% Fl-score on HDFS and BGL datasets, respectively, outperforming state-of-the-art methods. Besides, the fold embedding layer achieves compression rates of 36.55% and 64.86% on HDFS and BGL datasets, respectively, which helps to improve the throughput of LogFold.
Hyperledger Fabric stands as a leading framework for permissioned block-chain systems, ensuring data security and audit-ability for enterprise applications. As applications on this platform grow, understanding its com...
详细信息
ISBN:
(数字)9798350327939
ISBN:
(纸本)9798350327946
Hyperledger Fabric stands as a leading framework for permissioned block-chain systems, ensuring data security and audit-ability for enterprise applications. As applications on this platform grow, understanding its complex configuration concerning various block-chain parameters becomes vital. These configurations significantly affect the system’s performance and cost. In this research, we introduce a Stochastic Petri Net (SPN) model to analyze Hyper-ledger Fabric’s performance, considering variations in block-chain parameters, computational resources, and transaction rates. We provide case studies to validate the utility of our model, aiding block-chain administrators in determining optimal configurations for their applications. A key observation from our model highlights the block size’s role in system response time. We noted an increased mean response time, between 1 to 25 seconds, due to variations in transaction arrival rates.
Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the develop...
详细信息
Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie
Deciding on an uncertain event may lead to risk. Uncertainty occurs due to the lack of knowledge of a particular event or a situation. The only way to avoid this is to analyze the Risk. The risk analyzed properly will...
详细信息
暂无评论