Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse mul...
Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, ...
详细信息
Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports $3.12\times $ more demand when compared to related existing approaches.
In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbala...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.
The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosi...
详细信息
The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tears, due to its efficiency and accuracy in medical imaging. However, the interpretation and understanding of knee MRI images are time-consuming, laborious, require sufficient expertise, and are also prone to diagnostic errors. Thus, it is imperative to devise a computational method employing knee MRI for intelligent diagnosis of knee injuries, as this could expedite medical assessments by physicians, reduce costs, and substantially reduce the risk of misdiagnosis. Although several computational methods have been proposed to diagnose knee injuries, most rely heavily on local features in MRI images and exhibit low prediction accuracy. In this paper, we proposed a novel multi-view graph neural network, abbreviated as MVGNN, to identify knee injuries (specifically ACL tears and meniscal tears) by leveraging graph representations derived from multiple MRI views. Comprehensive experiments demonstrate that MVGNN achieves state-of-the-art results for diagnosing knee injuries, with a 5.9% improvement in accuracy on ACL data and a 6.5% improvement on Men data, compared to the second-best method, MVCNN.
Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. H...
详细信息
Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG.
Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. data provenance analysis on provenance graphs has em...
ISBN:
(纸本)9781939133441
Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. data provenance analysis on provenance graphs has emerged as a common approach in APT detection. However, previous works have exhibited several shortcomings: (1) requiring attack-containing data and a priori knowledge of APTs, (2) failing in extracting the rich contextual information buried within provenance graphs and (3) becoming impracticable due to their prohibitive computation overhead and memory *** this paper, we introduce MAGIC, a novel and flexible self-supervised APT detection approach capable of performing multi-granularity detection under different level of supervision. MAGIC leverages masked graph representation learning to model benign system entities and behaviors, performing efficient deep feature extraction and structure abstraction on provenance graphs. By ferreting out anomalous system behaviors via outlier detection methods, MAGIC is able to perform both system entity level and batched log level APT detection. MAGIC is specially designed to handle concept drift with a model adaption mechanism and successfully applies to universal conditions and detection scenarios. We evaluate MAGIC on three widely-used datasets, including both real-world and simulated attacks. Evaluation results indicate that MAGIC achieves promising detection results in all scenarios and shows enormous advantage over state-of-the-art APT detection approaches in performance overhead.
Network growth model is an important and popular research topic aimed at uncovering the mechanisms of network formation and evolution. Most growth models focus on two key mechanisms: growth and preferential attachment...
详细信息
Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significa...
详细信息
The void fraction is an important parameter to characterize the characteristics of annular flow, which is an important precondition for calculating the flow velocity, average density, pressure gradient, and analyzing ...
详细信息
暂无评论