检索结果-内蒙古大学图书馆

Serverless Approach to Running Resource-Intensive STAR Aligner

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kica, Piotr Orzechowski, Michal Malawski, Maciej Sano Centre for Computational Medicine Kraków Poland Faculty of Computer Science AGH University of Kraków Poland Academic Computer Centre Cyfronet AGH Kraków Poland

The application of serverless computing for alignment of RNA-sequences can improve many existing bioinformatics workflows by reducing operational costs and execution times. This work analyzes the applicability of serverless services for running the STAR aligner, which is known for its accuracy and large memory requirement. This presents a challenge, as serverless services were designed for light and short tasks. Nevertheless, we successfully deploy a STAR-based pipeline on AWS ECS service, propose multiple optimizations, and perform experiment with 17 TBs of data. Results are compared against standard virtual machine (VM) based solution showing that serverless is a valid alternative for small-scale batch processing. However, in large-scale where efficiency matters the most, VMs are still recommended. © 2025, CC BY.

关键词： batch data processing

batch process quality prediction based on TFCMixer modeling

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Zhao, Xiaoqiang Liu, Yongyong Hui, Yonyong Liu, Kai Yao, Qinglei College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou730050 China Gansu Key Laboratory Advanced Control for Industrial Processes Lanzhou University of Technology Lanzhou730050 China National Experimental Teaching Center of Electrical and Control Engineering Lanzhou University of Technology Lanzhou730050 China

Deep learning models are now widely used for the prediction of quality variables in batch processes. However, the dynamics and nonlinearities of batch processes, and long training time of deep learning models are unfavorable for quality prediction. To address these issues, an batch process quality prediction method based on the Temporal Feature Convolutional Mixer (TFCMixer) model is proposed. First, the maximum information coefficient (MIC) method is utilized to filter out the process variables that are more relevant to the quality variables to reduce the model training time. Second, a temporal feature convolution processor is designed to extract key information from the time series. On the one hand, the pro cessor processes the data in time dimension through convolution operation to learn the dynamic changes of the data in time, and utilizes double convolution operation to process the feature dimension in the data, so that the model can learn the interaction information between the features, which helps to deeply understand the complex relationship between the features and improve the prediction accuracy of the model;on the other hand, it incorporates a residual scale block to regulate the model's training time. Scale is incorporated to regulate the effect of residual signals in the final output, so as to adjust the performance of the model according to different tasks and data characteristics, and the Hard Swish activation function with continuous differentiability is introduced to stabilize the training of the model. Then, the temporal projection is combined with a temporal feature convolution processor to perform the conversion between time steps. Finally, experiments are conducted using data from the penicillin fermentation process and semiconductor wafer etching process. The results demonstrate the accuracy and effectiveness of the proposed model, which requires fewer iterations for training to achieve excellent prediction results. © 2025, The Authors. All ri

关键词： batch data processing

batch normalization does not improve initialization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dannemann, Joris Junike, Gero Carl von Ossietzky Universität Institut für Mathematik Oldenburg26129 Germany

batch normalization is one of the most important regularization techniques for neural networks, significantly improving training by centering the layers of the neural network. There have been several attempts to provide a theoretical justification for batch normalization. Santurkar and Tsipras (2018) [How does batch normalization help optimization? Advances in neural information processing systems, 31] claim that batch normalization improves initialization. We provide a counterexample showing that this claim is not true, i.e., batch normalization does not improve initialization. © 2025, CC BY.

关键词： batch data processing

SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Fahao Li, Peng Luan, Tom H. Su, Zhou Deng, Jing School of Computer Science and Engineering The University of Aizu Japan School of Cyber Science and Engineering Xi’an Jiaotong University China Department of Computer Science University of North Carolina Greensboro United States

Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently verified by the LLM in a verification phase. However, current state-of-the-art speculative decoding approaches have three key limitations: handling requests with varying difficulty using homogeneous SSMs, lack of robust support for batch processing, and insufficient holistic optimization for both speculation and verification phases. In this paper, we introduce SPIN, an efficient LLM inference serving system based on speculative decoding, designed to address these challenges through three main innovations. First, SPIN improves token speculation by using multiple heterogeneous SSMs, with a learning-based algorithm for SSM selection that operates without prior knowledge of request difficulty. Second, SPIN employs a request decomposition method to minimize batching overhead during LLM verification. Finally, SPIN orchestrates speculation and verification phases by pipelining their executions on GPUs to achieve further acceleration. Experimental results demonstrate that SPIN significantly outperforms state-of-the-art methods, achieving a performance increase of approximately 2.28×. © 2025, CC BY.

关键词： batch data processing

Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Behrad, Fatemeh Tuytelaars, Tinne Wagemans, Johan KU Leuven University Belgium

The capacity of Vision transformers (ViTs) to handle variable-sized inputs is often constrained by computational complexity and batch processing limitations. Consequently, ViTs are typically trained on small, fixed-size images obtained through downscaling or cropping. While reducing computational burden, these methods result in significant information loss, negatively affecting tasks like image aesthetic assessment. We introduce Charm, a novel tokenization approach that preserves Composition, High-resolution, Aspect Ratio, and Multi-scale information simultaneously. Charm prioritizes high-resolution details in specific regions while downscaling others, enabling shorter fixed-size input sequences for ViTs while incorporating essential information. Charm is designed to be compatible with pre-trained ViTs and their learned positional embeddings. By providing multiscale input and introducing variety to input tokens, Charm improves ViT performance and generalizability for image aesthetic assessment. We avoid cropping or changing the aspect ratio to further preserve information. Extensive experiments demonstrate significant performance improvements on various image aesthetic and quality assessment datasets (up to 8.1 %) using a lightweight ViT backbone. Code and pre-trained models are available at GitHub. © 2025, CC BY.

关键词： batch data processing

Scalable and Cost-Efficient ML Inference: Parallel batch processing with Serverless Functions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Barrak, Amine Ksontini, Emna Department of Computer Science and Engineering Oakland University Michigan United States

As data-intensive applications grow, batch processing in limited-resource environments faces scalability and resource management challenges. Serverless computing offers a flexible alternative, enabling dynamic resource allocation and automatic scaling. This paper explores how serverless architectures can make large-scale ML inference tasks faster and cost-effective by decomposing monolithic processes into parallel functions. Through a case study on sentiment analysis using the DistilBERT model and the IMDb dataset, we demonstrate that serverless parallel processing can reduce execution time by over 95% compared to monolithic approaches, at the same cost. © 2025, CC BY.

关键词： batch data processing

LOGITLENS4LLMS: EXTENDING LOGIT LENS ANALYSIS TO MODERN LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Zhenyu Independent Researcher Beijing China

This paper introduces LogitLens4LLMs, a toolkit that extends the Logit Lens technique to modern large language models. While Logit Lens has been a crucial method for understanding internal representations of language models, it was previously limited to earlier model architectures. Our work overcomes the limitations of existing implementations, enabling the technique to be applied to state-of-the-art architectures (such as Qwen-2.5 and Llama-3.1) while automating key analytical workflows. By developing component-specific hooks to capture both attention mechanisms and MLP outputs, our implementation achieves full compatibility with the HuggingFace transformer library while maintaining low inference overhead. The toolkit provides both interactive exploration and batch processing capabilities, supporting large-scale layer-wise analyses. Through open-sourcing our implementation, we aim to facilitate deeper investigations into the internal mechanisms of large-scale language models. The toolkit is openly available at https://***/zhenyu-02/ LogitLens4LLMs. © 2025, CC BY.

关键词： batch data processing

MEMIT-Merge: Addressing MEMIT’s Key-Value Conflicts in Same-Subject batch Editing for LLMs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dong, Zilu Shen, Xiangqing Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology China

As large language models continue to scale up, knowledge editing techniques that modify models’ internal knowledge without full retraining have gained significant attention. MEMIT, a prominent batch editing algorithm, stands out for its capability to perform mass knowledge modifications. However, we uncover a critical limitation that MEMIT’s editing efficacy significantly deteriorates when processing batches containing multiple edits sharing the same subject. Our analysis reveals that the root cause lies in MEMIT’s key value modeling framework: When multiple facts with the same subject in a batch are modeled through MEMIT’s key value mechanism, identical keys (derived from the shared subject) are forced to represent different values (corresponding to different knowledge), resulting in updates conflicts during editing. Addressing this issue, we propose MEMIT-Merge, an enhanced approach that merges value computation processes for facts sharing the same subject, effectively resolving the performance degradation in same-subject batch editing scenarios. Experimental results demonstrate that when MEMIT’s edit success rate drops to around 50% at larger batch sizes, MEMIT-Merge maintains a success rate exceeding 90%, showcasing remarkable robustness to subject entity collisions. Copyright © 2025, The Authors. All rights reserved.

关键词： batch data processing

Optimal Functional 2s−1-batch Codes: Exploring New Sufficient Conditions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yohananov, Lev Essayag, Isaac Barouch The Bioinformatics and Genomics Center MIGAL - Galilee Research Institute Kiryat Shmona11016 Israel

A functional k-batch code of dimension s consists of n servers storing linear combinations of s linearly independent information bits. These codes are designed to recover any multiset of k requests, each being a linear combination of the information bits, by k disjoint subsets of servers. A recent conjecture suggests that for any set of k = 2s-1 requests, the optimal solution requires 2s-1 servers. This paper shows that the problem of functional k-batch codes is equivalent to several other problems. Using these equivalences, we derive sufficient conditions that improve understanding of the problem and enhance the ability to find the optimal solution. Copyright © 2025, The Authors. All rights reserved.

关键词： batch data processing