PyTorchKR Papers

최신 논문

총 10,241편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2408.13248

Foundational Model for Electron Micrograph Analysis: Instruction-Tuning Small-Scale Language-and-Vision Assistant for Enterprise Adoption

Semiconductor imaging and analysis are critical yet understudied in deep learning, limiting our ability for precise control and optimization in semiconductor manufacturing. We introduce a small-scale multimodal framework for analyzing semiconductor electron microscopy images (MAEMI) through vision-language instruction tuning. We generate a customized instruction-following dataset using large multimodal models on microscopic image analysis. We perform knowledge transfer from larger to smaller models through knowledge distillation, resulting in improved accuracy of smaller models on visual question answering (VQA) tasks. This approach eliminates the need for expensive, human expert-annotated datasets for microscopic image analysis tasks. Enterprises can further finetune MAEMI on their intellectual data, enhancing privacy and performance on low-cost consumer hardware. Our experiments show that MAEMI outperforms traditional methods, adapts to data distribution shifts, and supports high-throughput screening.

arXiv:2408.13227

Enhancing Few-Shot Transfer Learning with Optimized Multi-Task Prompt Tuning through Modular Prompt Composition

In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the performance of multiple tasks by facilitating the transfer of knowledge between their corresponding prompts in a multi-task setting. Our proposed approach decomposes the prompt for each target task into a combination of shared prompts (source prompts) and a task-specific prompt (private prompt). During training, the source prompts undergo fine-tuning and are integrated with the private prompt to drive the target prompt for each task. We present and compare multiple methods for combining source prompts to construct the target prompt, analyzing the roles of both source and private prompts within each method. We investigate their contributions to task performance and offer flexible, adjustable configurations based on these insights to optimize performance. Our empirical findings clearly showcase improvements in accuracy and robustness compared to the conventional practice of prompt tuning and related works. Notably, our results substantially outperform other methods in the field in few-shot settings, demonstrating superior performance in various tasks across GLUE benchmark, among other tasks. This achievement is attained with a significantly reduced amount of training data, making our method a promising one for few-shot settings.

arXiv:2408.11828

Online Electric Vehicle Charging Detection Based on Memory-based Transformer using Smart Meter Data

The growing popularity of Electric Vehicles (EVs) poses unique challenges for grid operators and infrastructure, which requires effectively managing these vehicles' integration into the grid. Identification of EVs charging is essential to electricity Distribution Network Operators (DNOs) for better planning and managing the distribution grid. One critical aspect is the ability to accurately identify the presence of EV charging in the grid. EV charging identification using smart meter readings obtained from behind-the-meter devices is a challenging task that enables effective managing the integration of EVs into the existing power grid. Different from the existing supervised models that require addressing the imbalance problem caused by EVs and non-EVs data, we propose a novel unsupervised memory-based transformer (M-TR) that can run in real-time (online) to detect EVs charging from a streaming smart meter. It dynamically leverages coarse-scale historical information using an M-TR encoder from an extended global temporal window, in conjunction with an M-TR decoder that concentrates on a limited time frame, local window, aiming to capture the fine-scale characteristics of the smart meter data. The M-TR is based on an anomaly detection technique that does not require any prior knowledge about EVs charging profiles, nor it does only require real power consumption data of non-EV users. In addition, the proposed model leverages the power of transfer learning. The M-TR is compared with different state-of-the-art methods and performs better than other unsupervised learning models. The model can run with an excellent execution time of 1.2 sec. for 1-minute smart recordings.

arXiv:2408.12277

Modularized data-driven approximation of the Koopman operator and generator

Extended Dynamic Mode Decomposition (EDMD) is a widely-used data-driven approach to learn an approximation of the Koopman operator. Consequently, it provides a powerful tool for data-driven analysis, prediction, and control of nonlinear dynamical (control) systems. In this work, we propose a novel modularized EDMD scheme tailored to interconnected systems. To this end, we utilize the structure of the Koopman generator that allows to learn the dynamics of subsystems individually and thus alleviates the curse of dimensionality by considering observable functions on smaller state spaces. Moreover, our approach canonically enables transfer learning if a system encompasses multiple copies of a model as well as efficient adaption to topology changes without retraining. We provide finite-data bounds on the estimation error using tools from graph theory. The efficacy of the method is illustrated by means of various numerical examples.

arXiv:2408.11926

Defining Boundaries: The Impact of Domain Specification on Cross-Language and Cross-Domain Transfer in Machine Translation

Recent advancements in neural machine translation (NMT) have revolutionized the field, yet the dependency on extensive parallel corpora limits progress for low-resource languages and domains. Cross-lingual transfer learning offers a promising solution by utilizing data from high-resource languages but often struggles with in-domain NMT. This paper investigates zero-shot cross-lingual domain adaptation for NMT, focusing on the impact of domain specification and linguistic factors on transfer effectiveness. Using English as the source language and Spanish for fine-tuning, we evaluate multiple target languages, including Portuguese, Italian, French, Czech, Polish, and Greek. We demonstrate that both language-specific and domain-specific factors influence transfer effectiveness, with domain characteristics playing a crucial role in determining cross-domain transfer potential. We also explore the feasibility of zero-shot cross-lingual cross-domain transfer, providing insights into which domains are more responsive to transfer and why. Our results show the importance of well-defined domain boundaries and transparency in experimental setups for in-domain transfer learning.

arXiv:2408.11873

Parameter-Efficient Transfer Learning under Federated Learning for Automatic Speech Recognition

This work explores the challenge of enhancing Automatic Speech Recognition (ASR) model performance across various user-specific domains while preserving user data privacy. We employ federated learning and parameter-efficient domain adaptation methods to solve the (1) massive data requirement of ASR models from user-specific scenarios and (2) the substantial communication cost between servers and clients during federated learning. We demonstrate that when equipped with proper adapters, ASR models under federated tuning can achieve similar performance compared with centralized tuning ones, thus providing a potential direction for future privacy-preserved ASR services. Besides, we investigate the efficiency of different adapters and adapter incorporation strategies under the federated learning setting.

arXiv:2408.12266공식 코드 · Papers with Code

Accounts of using the Tustin-Net architecture on a rotary inverted pendulum

In this report we investigate the use of the Tustin neural network architecture (Tustin-Net) for the identification of a physical rotary inverse pendulum. This physics-based architecture is of particular interest as it builds on the known relationship between velocities and positions. We here aim at discussing the advantages, limitations and performance of Tustin-Nets compared to first-principles grey-box models on a real physical apparatus, showing how, with a standard training procedure, the former can hardly achieve the same accuracy as the latter. To address this limitation, we present a training strategy based on transfer learning that yields Tustin-Nets that are competitive with the first-principles model, without requiring extensive knowledge of the setup as the latter.

arXiv:2408.12426

Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification

The increasing popularity of Artificial Intelligence in recent years has led to a surge in interest in image classification, especially in the agricultural sector. With the help of Computer Vision, Machine Learning, and Deep Learning, the sector has undergone a significant transformation, leading to the development of new techniques for crop classification in the field. Despite the extensive research on various image classification techniques, most have limitations such as low accuracy, limited use of data, and a lack of reporting model size and prediction. The most significant limitation of all is the need for model explainability. This research evaluates four different approaches for crop classification, namely traditional ML with handcrafted feature extraction methods like SIFT, ORB, and Color Histogram; Custom Designed CNN and established DL architecture like AlexNet; transfer learning on five models pre-trained using ImageNet such as EfficientNetV2, ResNet152V2, Xception, Inception-ResNetV2, MobileNetV3; and cutting-edge foundation models like YOLOv8 and DINOv2, a self-supervised Vision Transformer Model. All models performed well, but Xception outperformed all of them in terms of generalization, achieving 98% accuracy on the test data, with a model size of 80.03 MB and a prediction time of 0.0633 seconds. A key aspect of this research was the application of Explainable AI to provide the explainability of all the models. This journal presents the explainability of Xception model with LIME, SHAP, and GradCAM, ensuring transparency and trustworthiness in the models' predictions. This study highlights the importance of selecting the right model according to task-specific needs. It also underscores the important role of explainability in deploying AI in agriculture, providing insightful information to help enhance AI-driven crop management strategies.

arXiv:2408.12326

Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models

Large Language Models (LLMs) have demonstrated exceptional capabilities across various machine learning (ML) tasks. Given the high costs of creating annotated datasets for supervised learning, LLMs offer a valuable alternative by enabling effective few-shot in-context learning. However, these models can produce hallucinations, particularly in domains with incomplete knowledge. Additionally, current methods for knowledge distillation using LLMs often struggle to enhance the effectiveness of both teacher and student models. To address these challenges, we introduce DualChecker, an innovative framework designed to mitigate hallucinations and improve the performance of both teacher and student models during knowledge distillation. DualChecker employs ContextAligner to ensure that the context provided by teacher models aligns with human labeling standards. It also features a dynamic checker system that enhances model interaction: one component re-prompts teacher models with more detailed content when they show low confidence, and another identifies borderline cases from student models to refine the teaching templates. This interactive process promotes continuous improvement and effective knowledge transfer between the models. We evaluate DualChecker using a green innovation textual dataset that includes binary, multiclass, and token classification tasks. The experimental results show that DualChecker significantly outperforms existing state-of-the-art methods, achieving up to a 17% improvement in F1 score for teacher models and 10% for student models. Notably, student models fine-tuned with LLM predictions perform comparably to those fine-tuned with actual data, even in a challenging domain. We make all datasets, models, and code from this research publicly available.

arXiv:2408.11322공식 코드 · Papers with Code

Transfer Learning and the Early Estimation of Single-Photon Source Quality using Machine Learning Methods

The use of single-photon sources (SPSs) is central to numerous systems and devices proposed amidst a modern surge in quantum technology. However, manufacturing schemes remain imperfect, and single-photon emission purity must often be experimentally verified via interferometry. Such a process is typically slow and costly, which has motivated growing research into whether SPS quality can be more rapidly inferred from incomplete emission statistics. Hence, this study is a sequel to previous work that demonstrated significant uncertainty in the standard method of quality estimation, i.e. the least-squares fitting of a physically motivated function, and asks: can machine learning (ML) do better? The study leverages eight datasets obtained from measurements involving an exemplary quantum emitter, i.e. a single InGaAs/GaAs epitaxial quantum dot; these eight contexts predominantly vary in the intensity of the exciting laser. Specifically, via a form of `transfer learning', five ML models, three linear and two ensemble-based, are trained on data from seven of the contexts and tested on the eighth. Validation metrics quickly reveal that even a linear regressor can outperform standard fitting when it is tested on the same contexts it was trained on, but the success of transfer learning is less assured, even though statistical analysis, made possible by data augmentation, suggests its superiority as an early estimator. Accordingly, the study concludes by discussing future strategies for grappling with the problem of SPS context dissimilarity, e.g. feature engineering and model adaptation.

arXiv:2408.11294

RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining

The field of Natural Language Processing (NLP) has seen significant advancements with the development of Large Language Models (LLMs). However, much of this research remains focused on English, often overlooking low-resource languages like Korean. This oversight presents challenges due to the unique non-alphabetic token structure of Korean and the substantial memory and computational demands required for LLM training, which frequently lead to memory constraints and out-of-memory errors. To address these issues, we present RedWhale, a model specifically tailored for Korean language processing. RedWhale is developed using an efficient continual pretraining approach that includes a comprehensive Korean corpus preprocessing pipeline, a specialized tokenizer, an optimized model initialization technique, and a multistage pretraining strategy. These innovations collectively reduce training time and computational costs while maintaining high levels of accuracy and comprehension. By leveraging cross-lingual transfer learning, which exploits shared linguistic similarities across languages, RedWhale builds on English models to enhance Korean language processing. Experimental results demonstrate that RedWhale outperforms other leading models on Korean NLP benchmarks, including the Korean Balanced Evaluation of Significant Tasks (KoBEST), showing superior understanding and generation of Korean text. Furthermore, RedWhale showed no signs of convergence even after pretraining on 9.7 billion tokens, indicating the potential for further improvements with additional training. This work represents a significant advancement in bridging the linguistic divide, particularly in enhancing NLP capabilities for the Korean language.

arXiv:2408.11407

Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection

Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors. Existing methods often overlook the significant differences in feature space caused by the large gap in scale between the teacher and student models. This limitation hampers the efficiency of knowledge transfer during the distillation process. Furthermore, the complex backgrounds in UAV images make it challenging for the student model to efficiently learn the object features. In this paper, we propose a novel knowledge distillation framework for UAV-OD. Specifically, a progressive distillation approach is designed to alleviate the feature gap between teacher and student models. Then a new feature alignment method is provided to extract object-related features for enhancing student model's knowledge reception efficiency. Finally, extensive experiments are conducted to validate the effectiveness of our proposed approach. The results demonstrate that our proposed method achieves state-of-the-art (SoTA) performance in two UAV-OD datasets.

arXiv:2408.11768공식 코드 · Papers with Code

Embedding Ordinality to Binary Loss Function for Improving Solar Flare Forecasting

In this paper, we propose a novel loss function aimed at optimizing the binary flare prediction problem by embedding the intrinsic ordinal flare characteristics into the binary cross-entropy (BCE) loss function. This modification is intended to provide the model with better guidance based on the ordinal characteristics of the data and improve the overall performance of the models. For our experiments, we employ a ResNet34-based model with transfer learning to predict $\geq$M-class flares by utilizing the shape-based features of magnetograms of active region (AR) patches spanning from $-$90$^{\circ}$ to $+$90$^{\circ}$ of solar longitude as our input data. We use a composite skill score (CSS) as our evaluation metric, which is calculated as the geometric mean of the True Skill Score (TSS) and the Heidke Skill Score (HSS) to rank and compare our models' performance. The primary contributions of this work are as follows: (i) We introduce a novel approach to encode ordinality into a binary loss function showing an application to solar flare prediction, (ii) We enhance solar flare forecasting by enabling flare predictions for each AR across the entire solar disk, without any longitudinal restrictions, and evaluate and compare performance. (iii) Our candidate model, optimized with the proposed loss function, shows an improvement of $\sim$7%, $\sim$4%, and $\sim$3% for AR patches within $\pm$30$^\circ$, $\pm$60$^\circ$, and $\pm$90$^\circ$ of solar longitude, respectively in terms of CSS, when compared with standard BCE. Additionally, we demonstrate the ability to issue flare forecasts for ARs in near-limb regions (regions between $\pm$60$^{\circ}$ to $\pm$90$^{\circ}$) with a CSS=0.34 (TSS=0.50 and HSS=0.23), expanding the scope of AR-based models for solar flare prediction. This advances the reliability of solar flare forecasts, leading to more effective prediction capabilities.

arXiv:2408.10955

Multichannel Attention Networks with Ensembled Transfer Learning to Recognize Bangla Handwritten Charecter

The Bengali language is the 5th most spoken native and 7th most spoken language in the world, and Bengali handwritten character recognition has attracted researchers for decades. However, other languages such as English, Arabic, Turkey, and Chinese character recognition have contributed significantly to developing handwriting recognition systems. Still, little research has been done on Bengali character recognition because of the similarity of the character, curvature and other complexities. However, many researchers have used traditional machine learning and deep learning models to conduct Bengali hand-written recognition. The study employed a convolutional neural network (CNN) with ensemble transfer learning and a multichannel attention network. We generated the feature from the two branches of the CNN, including Inception Net and ResNet and then produced an ensemble feature fusion by concatenating them. After that, we applied the attention module to produce the contextual information from the ensemble features. Finally, we applied a classification module to refine the features and classification. We evaluated the proposed model using the CAMTERdb 3.1.2 data set and achieved 92\% accuracy for the raw dataset and 98.00\% for the preprocessed dataset. We believe that our contribution to the Bengali handwritten character recognition domain will be considered a great development.

arXiv:2408.10894공식 코드 · Papers with Code

ViLReF: An Expert Knowledge Enabled Vision-Language Retinal Foundation Model

Subtle semantic differences in retinal image and text data present great challenges for pre-training visual-language models. Moreover, false negative samples, i.e., image-text pairs having the same semantics but incorrectly regarded as negatives, disrupt the visual-language pre-training process and affect the model's learning ability. This work aims to develop a retinal foundation model, called ViLReF, by pre-training on a paired dataset comprising 451,956 retinal images and corresponding diagnostic text reports. In our vision-language pre-training strategy, we leverage expert knowledge to facilitate the extraction of labels and propose a novel constraint, the Weighted Similarity Coupling Loss, to adjust the speed of pushing sample pairs further apart dynamically within the feature space. Furthermore, we employ a batch expansion module with dynamic memory queues, maintained by momentum encoders, to supply extra samples and compensate for the vacancies caused by eliminating false negatives. Extensive experiments are conducted on multiple datasets for downstream classification and segmentation tasks. The experimental results demonstrate the powerful zero-shot and transfer learning capabilities of ViLReF, verifying the effectiveness of our pre-training strategy. Our ViLReF model is available at: https://github.com/T6Yang/ViLReF.

arXiv:2408.10688공식 코드 · Papers with Code

TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning

Recently, large-scale pre-trained vision-language models (e.g., CLIP), have garnered significant attention thanks to their powerful representative capabilities. This inspires researchers in transferring the knowledge from these large pre-trained models to other task-specific models, e.g., Video Action Recognition (VAR) models, via particularly leveraging side networks to enhance the efficiency of parameter-efficient fine-tuning (PEFT). However, current transferring approaches in VAR tend to directly transfer the frozen knowledge from large pre-trained models to action recognition networks with minimal cost, instead of exploiting the temporal modeling capabilities of the action recognition models themselves. Therefore, in this paper, we propose a memory-efficient Temporal Difference Side Network (TDS-CLIP) to balance knowledge transferring and temporal modeling, avoiding backpropagation in frozen parameter models. Specifically, we introduce a Temporal Difference Adapter (TD-Adapter), which can effectively capture local temporal differences in motion features to strengthen the model's global temporal modeling capabilities. Furthermore, we designed a Side Motion Enhancement Adapter (SME-Adapter) to guide the proposed side network in efficiently learning the rich motion information in videos, thereby improving the side network's ability to capture and learn motion information. Extensive experiments are conducted on three benchmark datasets, including Something-Something V1\&V2, and Kinetics-400. Experimental results demonstrate that our approach achieves competitive performance.

arXiv:2408.10458

Transfer Operator Learning with Fusion Frame

The challenge of applying learned knowledge from one domain to solve problems in another related but distinct domain, known as transfer learning, is fundamental in operator learning models that solve Partial Differential Equations (PDEs). These current models often struggle with generalization across different tasks and datasets, limiting their applicability in diverse scientific and engineering disciplines. This work presents a novel framework that enhances the transfer learning capabilities of operator learning models for solving Partial Differential Equations (PDEs) through the integration of fusion frame theory with the Proper Orthogonal Decomposition (POD)-enhanced Deep Operator Network (DeepONet). We introduce an innovative architecture that combines fusion frames with POD-DeepONet, demonstrating superior performance across various PDEs in our experimental analysis. Our framework addresses the critical challenge of transfer learning in operator learning models, paving the way for adaptable and efficient solutions across a wide range of scientific and engineering applications.

arXiv:2408.10932

The Evolution of Reinforcement Learning in Quantitative Finance: A Survey

Reinforcement Learning (RL) has experienced significant advancement over the past decade, prompting a growing interest in applications within finance. This survey critically evaluates 167 publications, exploring diverse RL applications and frameworks in finance. Financial markets, marked by their complexity, multi-agent nature, information asymmetry, and inherent randomness, serve as an intriguing test-bed for RL. Traditional finance offers certain solutions, and RL advances these with a more dynamic approach, incorporating machine learning methods, including transfer learning, meta-learning, and multi-agent solutions. This survey dissects key RL components through the lens of Quantitative Finance. We uncover emerging themes, propose areas for future research, and critique the strengths and weaknesses of existing methods.

arXiv:2408.09344공식 코드 · Papers with Code

GitHub is an effective platform for collaborative and reproducible laboratory research

Laboratory research is a complex, collaborative process that involves several stages, including hypothesis formulation, experimental design, data generation and analysis, and manuscript writing. Although reproducibility and data sharing are increasingly prioritized at the publication stage, integrating these principles at earlier stages of laboratory research has been hampered by the lack of broadly applicable solutions. Here, we propose that the workflow used in modern software development offers a robust framework for enhancing reproducibility and collaboration in laboratory research. In particular, we show that GitHub, a platform widely used for collaborative software projects, can be effectively adapted to organize and document all aspects of a research project's lifecycle in a molecular biology laboratory. We outline a three-step approach for incorporating the GitHub ecosystem into laboratory research workflows: 1. designing and organizing experiments using issues and project boards, 2. documenting experiments and data analyses with a version control system, and 3. ensuring reproducible software environments for data analyses and writing tasks with containerized packages. The versatility, scalability, and affordability of this approach make it suitable for various scenarios, ranging from small research groups to large, cross-institutional collaborations. Adopting this framework from a project's outset can increase the efficiency and fidelity of knowledge transfer within and across research laboratories. An example GitHub repository based on this approach is available at https://github.com/rasilab/github_demo and a template repository that can be copied is available at https://github.com/rasilab/github_template.

arXiv:2408.08503

Computational strategies for cross-species knowledge transfer and translational biomedicine

Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling, and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that utilize transcriptome data and/or molecular networks. We introduce the term "agnology" to describe the functional equivalence of molecular components regardless of evolutionary origin, as this concept is becoming pervasive in integrative data-driven models where the role of evolutionary origin can become unclear. Our review addresses four key areas of information and knowledge transfer across species: (1) transferring disease and gene annotation knowledge, (2) identifying agnologous molecular components, (3) inferring equivalent perturbed genes or gene sets, and (4) identifying agnologous cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer.