Powerful new computers based on the principles of quantum mechanics could crack the codes that safeguard our information today. The National Institute of Standards and Technology is running a competition to find more ...
详细信息
Noise is an inevitable aspect of point cloud acquisition, necessitating filtering as a fundamental task within the realm of 3D vision. Existing learning-based filtering methods have shown promising capabilities on com...
详细信息
With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs...
详细信息
With the development and popularization of Internet technology, network security has become the focus of attention. Vulnerabilities and back doors are regarded as two of the main reasons of network security problems. ...
详细信息
Analyzing and evaluating students' progress in any learning environment is stressful and time consuming if done using traditional analysis methods. This is further exasperated by the increasing number of students ...
详细信息
Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual f...
In this paper, we introduce the IMPortance-awaReness maskIng NeTwork (IMPRINT), a novel approach to enhance the robustness of document retrieval systems against query variations, particularly those containing misspell...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
In this paper, we introduce the IMPortance-awaReness maskIng NeTwork (IMPRINT), a novel approach to enhance the robustness of document retrieval systems against query variations, particularly those containing misspellings. Unlike previous models that treat all query components (words/features) equally, IMPRINT prioritizes the most important components while masking out less relevant ones. Specifically, we propose a Mutual information-based measure to quantify component importance and integrate it into a dynamic masking mechanism that adjusts the retention probability of each component. Our method is evaluated on a combination of three benchmark datasets and three types of query variations. The experimental results show substantial performance gains compared to state-of-the-art models, achieving an average improvement of 1.2 absolute MRR@10 points in retrieval accuracy.
Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation task...
详细信息
ISBN:
(数字)9798331506476
ISBN:
(纸本)9798331506483
Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation tasks for hyperedges and vertices, leading to significant computational redundancy. This redundancy arises from recalculating shared information across different tasks. For the first time, we identify and harness implicit dataflows (i.e., dependencies) within HGNNs, introducing the microedge concept to effectively capture and reuse intricate shared information among aggregation tasks, thereby minimizing redundant computations. We have developed a new microedge-centric dataflow model that processes shared information as fine-grained microedge aggregation tasks. This dataflow model is supported by the Read-Process-Activate-Generate execution model, which aims to optimize parallelism among these tasks. Furthermore, our newly developed MeHyper, a microedge-centric HGNN accelerator, incorporates a decoupled pipeline for improved computational parallelism and a hierarchical feature management strategy to reduce off-chip memory accesses for large volumes of intermediate feature vectors generated. Our evaluation demonstrates that MeHyper substantially outperforms the leading CPUbased system PyG-CPU and the GPU-based system HyperGef, delivering performance improvements of $1,032.23 \times$ and $10.51 \times$, and energy efficiencies of $1,169.03 \times$ and $9.96 \times$, respectively.
Interactive dynamic influence diagrams (I-DIDs) are a general framework for multiagent sequential decision making under uncertainty. Due to the model complexity, a significant amount of research has been invested into...
详细信息
This paper presents a novel CSSA (Color Space Search Algorithm), introducing a metaheuristic optimization algorithm that addresses critical limitations in existing optimization methods. While current algorithms demons...
详细信息
ISBN:
(数字)9798331523657
ISBN:
(纸本)9798331523664
This paper presents a novel CSSA (Color Space Search Algorithm), introducing a metaheuristic optimization algorithm that addresses critical limitations in existing optimization methods. While current algorithms demonstrate suboptimal performance in multimodal landscapes, revealing premature convergence rates, CSSA introduces a novel approach by leveraging color theory principles in the optimization domain. The proposed algorithm combines complementary color transformations for global exploration with triadic color relationships for local exploitation, which aims to improve the exploration-exploitation balance compared to conventional methods. The algorithm's performance is evaluated across three categories of benchmark functions: unimodal functions, multimodal functions, and fixed-dimensional multimodal functions. Comprehensive experiments compared CSSA against classical (PSO, GA) and modern (MPA, EO, ALO, SSA, DA) optimization algorithms, with performance metrics including best fitness, mean fitness, solution consistency, and convergence rate analysis. Statistical analyses through the Friedman test (ranking 4.22) confirm the algorithm's robust performance, particularly in handling complex optimization landscapes. These results place CSSA as a promising optimization algorithm for complex optimization problems.
暂无评论