Search Results

Domain generalization (DG) aims to enhance the model’s ability to generalize from the source domains to unseen domains by addressing distribution shifts. A common approach in DG is to learn invariant features across domains. However, limited data ...

Federated learning (FL) emerged as a novel machine learning setting that enables collaboratively training deep models on decentralized clients with privacy constraints. In vanilla FedAvg , the global model is generated by the weighted linear combination ...

Recently, transformer models have demonstrated excellent performance across various intelligent applications owing to their ability to understand global context through self-attention mechanism. However, the extensively investigated ...

Hierarchical multi-granularity classification (HMC) assigns labels at varying levels of detail to images using a structured hierarchy that categorizes labels from coarse to fine, such as [“Suliformes”, “Fregatidae”, “Frigatebird”]. Traditional ...

• We examine the causal mechanisms behind hierarchical multi-granularity classification (HMC).
• We propose Deconf-HMC for eliminating confounding biases inherent in HMC.
• Experimental results demonstrate the superiority of the proposed ...

Recently, the transformer has exhibited remarkable performance across various applications, primarily owing to its exceptional capability in capturing global information through the attention mechanism. Nevertheless, the dot-product within ...

• The concept of fuzzy preference matroids rough set is introduced.
• A novel approximate guided representation method is developed.
• Constructed a plug-and-play transformer block based on the proposed method.
• The effectiveness and ...

On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing, holds significance for supporting human activates. Federated Learning is a promising solution for such ...

Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on target tasks often leads to a significant performance drop on the original tasks. This paper presents a ...

To address the limitations of the Raft consensus algorithm, such as the lack of support for Byzantine fault tolerance, performance bottleneck of the leader single node, and high leader election delay, an improved Byzantine fault tolerance ...

Aerial tracking has received growing attention due to its broad practical applications. However, single-view aerial trackers are still limited by challenges such as severe appearance variations and occlusions. Existing multi-view trackers utilize cross-...

Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals. In this paper, we introduce MS MARCO Web Search, the first large-scale information-rich web dataset, featuring millions of real clicked ...

Although 5G and beyond communication technology empower a large number of edge heterogeneous devices and applications, the stringent security remains a major concern when dealing with the millions of edge computing tasks in the highly dynamic ...

More researchers are proposing artificial intelligence algorithms for Internet of Things (IoT) devices and applying them to themes such as smart cities and smart transportation. In recent years, relevant research has mainly focused on data ...

Virtual screening (VS) has been incorporated into the paradigm of modern drug discovery. This field is now undergoing a new wave of revolution driven by artificial intelligence and more specifically, machine learning (ML). In terms of those out-...

Display Omitted

• Next-generation synthetic Maximal Unbiased Benchmarking Datasets (MUBDsyn) were developed through reinforcement learning combined with a deep generative model.
• MUBDsyn had less artificial enrichment bias, analogue bias and domain bias ...

Binarization efficiently compresses full-precision convolutional neural networks (CNNs) to achieve accelerated inference but with substantial performance degradations. Self-knowledge distillation (SKD) can significantly improve the performance of ...

Accurate identification of protein nucleic acid binding residues poses a significant challenge with important implications for various biological processes and drug design. Many typical computational methods for protein analysis rely on a single model ...

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in contrast to ...

To solve the problems of vote forgery and malicious election of candidate nodes in the Raft consensus algorithm, we combine zero trust with the Raft consensus algorithm and propose a secure and efficient consensus algorithm -Verifiable Secret Sharing ...

Internet of things (IoT) development tends to reduce the reliance on centralized servers. The zero-trust distributed system combined with blockchain technology has become a hot topic in IoT research. However, distribution data storage services and ...

A common concern when a policymaker draws causal inferences from and makes decisions based on observational data is that the measured covariates are insufficiently rich to account for all sources of confounding, i.e., the standard no confoundedness ...

Blockchain technology has been increasingly integrated into various fields of economic and social development. However, scalability issues such as low broadcast efficiency, high communication overhead, and high redundant transmission rate have ...