PyTorchKR Papers

최신 논문

총 10,240편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.11752공식 코드 · Papers with Code

Towards Foundation Model for Chemical Reactor Modeling: Meta-Learning with Physics-Informed Adaptation

Developing accurate models for chemical reactors is often challenging due to the complexity of reaction kinetics and process dynamics. Traditional approaches require retraining models for each new system, limiting generalizability and efficiency. In this work, we take a step toward foundation models for chemical reactor modeling by introducing a neural network framework that generalizes across diverse reactor types and rapidly adapts to new chemical processes. Our approach leverages meta-learning to pretrain the model on a broad set of reactor dynamics, enabling efficient adaptation to unseen reactions with minimal data. To further enhance generalizability, we incorporate physics-informed fine-tuning, ensuring physically consistent adaptation to new reactor conditions. Our framework is evaluated across three integer-order fundamental reactor types - continuous stirred tank reactors, batch reactors, and plug flow reactors - demonstrating superior few-shot adaptation compared to conventional data-driven, physics-informed, and transfer learning approaches. By combining meta-learning with physics-informed adaptation, this work lays the foundation for a generalizable modeling framework, advancing the development of foundation models for chemical engineering applications. Source code is available at https://github.com/killingbear999/chemical-reactor-foundation-model.

arXiv:2405.10944

Probabilistic transfer learning methodology to expedite high fidelity simulation of reactive flows

Reduced order models based on the transport of a lower dimensional manifold representation of the thermochemical state, such as Principal Component (PC) transport and Machine Learning (ML) techniques, have been developed to reduce the computational cost associated with the Direct Numerical Simulations (DNS) of reactive flows. Both PC transport and ML normally require an abundance of data to exhibit sufficient predictive accuracy, which might not be available due to the prohibitive cost of DNS or experimental data acquisition. To alleviate such difficulties, similar data from an existing dataset or domain (source domain) can be used to train ML models, potentially resulting in adequate predictions in the domain of interest (target domain). This study presents a novel probabilistic transfer learning (TL) framework to enhance the trust in ML models in correctly predicting the thermochemical state in a lower dimensional manifold and a sparse data setting. The framework uses Bayesian neural networks, and autoencoders, to reduce the dimensionality of the state space and diffuse the knowledge from the source to the target domain. The new framework is applied to one-dimensional freely-propagating flame solutions under different data sparsity scenarios. The results reveal that there is an optimal amount of knowledge to be transferred, which depends on the amount of data available in the target domain and the similarity between the domains. TL can reduce the reconstruction error by one order of magnitude for cases with large sparsity. The new framework required 10 times less data for the target domain to reproduce the same error as in the abundant data scenario. Furthermore, comparisons with a state-of-the-art deterministic TL strategy show that the probabilistic method can require four times less data to achieve the same reconstruction error.

arXiv:2405.10626공식 코드 · Papers with Code

Dynamic data sampler for cross-language transfer learning in large language models

Large Language Models (LLMs) have gained significant attention in the field of natural language processing (NLP) due to their wide range of applications. However, training LLMs for languages other than English poses significant challenges, due to the difficulty in acquiring large-scale corpus and the requisite computing resources. In this paper, we propose ChatFlow, a cross-language transfer-based LLM, to address these challenges and train large Chinese language models in a cost-effective manner. We employ a mix of Chinese, English, and parallel corpus to continuously train the LLaMA2 model, aiming to align cross-language representations and facilitate the knowledge transfer specifically to the Chinese language model. In addition, we use a dynamic data sampler to progressively transition the model from unsupervised pre-training to supervised fine-tuning. Experimental results demonstrate that our approach accelerates model convergence and achieves superior performance. We evaluate ChatFlow on popular Chinese and English benchmarks, the results indicate that it outperforms other Chinese models post-trained on LLaMA-2-7B.

arXiv:2405.10870공식 코드 · Papers with Code

Multicenter Privacy-Preserving Model Training for Deep Learning Brain Metastases Autosegmentation

Objectives: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. Materials and methods: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, NYU and BraTS Challenge 2023 on BM segmentation were used for this evaluation. First, the multicenter performance of a convolutional neural network (DeepMedic) for BM autosegmentation was established for exclusive single-center training and for training on pooled data, respectively. Subsequently bilateral collaboration was evaluated, where a UKER pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. Results: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. Conclusion: Data heterogeneity results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.

arXiv:2405.10629공식 코드 · Papers with Code

DeepPavlov at SemEval-2024 Task 8: Leveraging Transfer Learning for Detecting Boundaries of Machine-Generated Texts

The Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection shared task in the SemEval-2024 competition aims to tackle the problem of misusing collaborative human-AI writing. Although there are a lot of existing detectors of AI content, they are often designed to give a binary answer and thus may not be suitable for more nuanced problem of finding the boundaries between human-written and machine-generated texts, while hybrid human-AI writing becomes more and more popular. In this paper, we address the boundary detection problem. Particularly, we present a pipeline for augmenting data for supervised fine-tuning of DeBERTaV3. We receive new best MAE score, according to the leaderboard of the competition, with this pipeline.

arXiv:2405.10087

Continuous Transfer Learning for UAV Communication-aware Trajectory Design

Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential decisions based on real-time feedback. Despite these advantages, the use of DRL for UAV trajectory planning requires significant retraining when the UAV is confronted with a new environment, resulting in wasted resources and time. Therefore, it is essential to develop techniques that can reduce the overhead of retraining DRL models, enabling them to adapt to constantly changing environments. This paper presents a novel method to reduce the need for extensive retraining using a double deep Q network (DDQN) model as a pretrained base, which is subsequently adapted to different urban environments through Continuous Transfer Learning (CTL). Our method involves transferring the learned model weights and adapting the learning parameters, including the learning and exploration rates, to suit each new environment specific characteristics. The effectiveness of our approach is validated in three scenarios, each with different levels of similarity. CTL significantly improves learning speed and success rates compared to DDQN models initiated from scratch. For similar environments, Transfer Learning (TL) improved stability, accelerated convergence by 65%, and facilitated 35% faster adaptation in dissimilar settings.

arXiv:2405.10256

Biasing & Debiasing based Approach Towards Fair Knowledge Transfer for Equitable Skin Analysis

Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in diagnosing skin diseases, often outperforming dermatologists. However, they have also unveiled biases linked to specific demographic traits, notably concerning diverse skin tones or gender, prompting concerns regarding fairness and limiting their widespread deployment. Researchers are actively working to ensure fairness in AI-based solutions, but existing methods incur an accuracy loss when striving for fairness. To solve this issue, we propose a `two-biased teachers' (i.e., biased on different sensitive attributes) based approach to transfer fair knowledge into the student network. Our approach mitigates biases present in the student network without harming its predictive accuracy. In fact, in most cases, our approach improves the accuracy of the baseline model. To achieve this goal, we developed a weighted loss function comprising biasing and debiasing loss terms. We surpassed available state-of-the-art approaches to attain fairness and also improved the accuracy at the same time. The proposed approach has been evaluated and validated on two dermatology datasets using standard accuracy and fairness evaluation measures. We will make source code publicly available to foster reproducibility and future research.

arXiv:2405.09960

A Unified Deep Transfer Learning Model for Accurate IoT Localization in Diverse Environments

Internet of Things (IoT) is an ever-evolving technological paradigm that is reshaping industries and societies globally. Real-time data collection, analysis, and decision-making facilitated by localization solutions form the foundation for location-based services, enabling them to support critical functions within diverse IoT ecosystems. However, most existing works on localization focus on single environment, resulting in the development of multiple models to support multiple environments. In the context of smart cities, these raise costs and complexity due to the dynamicity of such environments. To address these challenges, this paper presents a unified indoor-outdoor localization solution that leverages transfer learning (TL) schemes to build a single deep learning model. The model accurately predicts the localization of IoT devices in diverse environments. The performance evaluation shows that by adopting an encoder-based TL scheme, we can improve the baseline model by about 17.18% in indoor environments and 9.79% in outdoor environments.

arXiv:2405.09021

Deep Learning in Earthquake Engineering: A Comprehensive Review

This article surveys the growing interest in utilizing Deep Learning (DL) as a powerful tool to address challenging problems in earthquake engineering. Despite decades of advancement in domain knowledge, issues such as uncertainty in earthquake occurrence, unpredictable seismic loads, nonlinear structural responses, and community engagement remain difficult to tackle using domain-specific methods. DL offers promising solutions by leveraging its data-driven capacity for nonlinear mapping, sequential data modeling, automatic feature extraction, dimensionality reduction, optimal decision-making, etc. However, the literature lacks a comprehensive review that systematically covers a consistent scope intersecting DL and earthquake engineering. To bridge the gap, the article first discusses methodological advances to elucidate various applicable DL techniques, such as multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), autoencoder (AE), transfer learning (TL), reinforcement learning (RL), and graph neural network (GNN). A thorough research landscape is then disclosed by exploring various DL applications across different research topics, including vision-based seismic damage assessment and structural characterization, seismic demand and damage state prediction, seismic response history prediction, regional seismic risk assessment and community resilience, ground motion (GM) for engineering use, seismic response control, and the inverse problem of system/damage identification. Suitable DL techniques for each research topic are identified, emphasizing the preeminence of CNN for vision-based tasks, RNN for sequential data, RL for community resilience, and unsupervised learning for GM analysis. The article also discusses opportunities and challenges for leveraging DL in earthquake engineering research and practice.

arXiv:2405.09014공식 코드 · Papers with Code

Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy

In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in the proposed feature-based federated learning, we design the extracted features and outputs to be uploaded instead of parameter updates. For this distributed learning model, we determine the required payload and provide comparisons with the existing schemes. Subsequently, we analyze the robustness of feature-based federated transfer learning against packet loss, data insufficiency, and quantization. Finally, we address privacy considerations by defining and analyzing label privacy leakage and feature privacy leakage, and investigating mitigating approaches. For all aforementioned analyses, we evaluate the performance of the proposed learning scheme via experiments on an image classification task and a natural language processing task to demonstrate its effectiveness.

arXiv:2405.09394

SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning

Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have emerged as useful foundation models (FMs) to be fine-tuned for a wide range of downstream tasks. However, large-scale pre-trained models make it challenging for traditional FL due to high communication overhead in the resource-constrained IoT. This has inspired the field of parameter-efficient fine-tuning (PEFT) research. Existing PEFT methods attempt to optimize model performance at the given dropout level. Such an approach places the burden on human users to find a dropout rate that provides a satisfactory level of performance through trial-and-error, which is time consuming and resource intensive. To address this limitation, we propose the Step-wise Parameter Dropout for Continual Federated Learning (SPD-CFL) approach. Instead of pre-defining a desired dropout rate, it allows users to specify the target level of performance and then attempts to find the most suitable dropout rate for the given FL model. Specifically, on the server side, SPD-CFL drops trainable parameters in a stepwise manner to improve communication efficiency by reducing the rank of low-rank adaptation (LoRA). The sensitivity-based gradient consistency (SGC) measure is designed to facilitate the adaptive adjustment of parameter dropout. In addition, SPD-CFL introduces continual learning (CL) on the client side to mitigate performance degradation due to the inconsistent optima with distinct parameter dropout rates under heterogeneous FL. Extensive experiments on the public benchmark dataset CIFAR-10 and a real-world medical Face dataset demonstrate significant superiority of SPD-CFL over state-of-the-art methods. Compared to the best-performing baseline, it achieves a 2.07% higher test AUC while reducing communication overhead by 29.53%.

arXiv:2405.09318

Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls

In the current cybersecurity landscape, protecting military devices such as communication and battlefield management systems against sophisticated cyber attacks is crucial. Malware exploits vulnerabilities through stealth methods, often evading traditional detection mechanisms such as software signatures. The application of ML/DL in vulnerability detection has been extensively explored in the literature. However, current ML/DL vulnerability detection methods struggle with understanding the context and intent behind complex attacks. Integrating large language models (LLMs) with system call analysis offers a promising approach to enhance malware detection. This work presents a novel framework leveraging LLMs to classify malware based on system call data. The framework uses transfer learning to adapt pre-trained LLMs for malware detection. By retraining LLMs on a dataset of benign and malicious system calls, the models are refined to detect signs of malware activity. Experiments with a dataset of over 1TB of system calls demonstrate that models with larger context sizes, such as BigBird and Longformer, achieve superior accuracy and F1-Score of approximately 0.86. The results highlight the importance of context size in improving detection rates and underscore the trade-offs between computational complexity and performance. This approach shows significant potential for real-time detection in high-stakes environments, offering a robust solution to evolving cyber threats.

arXiv:2405.08920

Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning

A recent study by De et al. (2022) has reported that large-scale representation learning through pre-training on a public dataset significantly enhances differentially private (DP) learning in downstream tasks, despite the high dimensionality of the feature space. To theoretically explain this phenomenon, we consider the setting of a layer-peeled model in representation learning, which results in interesting phenomena related to learned features in deep learning and transfer learning, known as Neural Collapse (NC). Within the framework of NC, we establish an error bound indicating that the misclassification error is independent of dimension when the distance between actual features and the ideal ones is smaller than a threshold. Additionally, the quality of the features in the last layer is empirically evaluated under different pre-trained models within the framework of NC, showing that a more powerful transformer leads to a better feature representation. Furthermore, we reveal that DP fine-tuning is less robust compared to fine-tuning without DP, particularly in the presence of perturbations. These observations are supported by both theoretical analyses and experimental evaluation. Moreover, to enhance the robustness of DP fine-tuning, we suggest several strategies, such as feature normalization or employing dimension reduction methods like Principal Component Analysis (PCA). Empirically, we demonstrate a significant improvement in testing accuracy by conducting PCA on the last-layer features.

arXiv:2405.08843

FLEXIBLE: Forecasting Cellular Traffic by Leveraging Explicit Inductive Graph-Based Learning

From a telecommunication standpoint, the surge in users and services challenges next-generation networks with escalating traffic demands and limited resources. Accurate traffic prediction can offer network operators valuable insights into network conditions and suggest optimal allocation policies. Recently, spatio-temporal forecasting, employing Graph Neural Networks (GNNs), has emerged as a promising method for cellular traffic prediction. However, existing studies, inspired by road traffic forecasting formulations, overlook the dynamic deployment and removal of base stations, requiring the GNN-based forecaster to handle an evolving graph. This work introduces a novel inductive learning scheme and a generalizable GNN-based forecasting model that can process diverse graphs of cellular traffic with one-time training. We also demonstrate that this model can be easily leveraged by transfer learning with minimal effort, making it applicable to different areas. Experimental results show up to 9.8% performance improvement compared to the state-of-the-art, especially in rare-data settings with training data reduced to below 20%.

arXiv:2405.08199공식 코드 · Papers with Code

Modeling of Time-varying Wireless Communication Channel with Fading and Shadowing

The real-time quantification of the effect of a wireless channel on the transmitting signal is crucial for the analysis and the intelligent design of wireless communication systems for various services. Recent mechanisms to model channel characteristics independent of coding, modulation, signal processing, etc., using deep learning neural networks are promising solutions. However, the current approaches are neither statistically accurate nor able to adapt to the changing environment. In this paper, we propose a new approach that combines a deep learning neural network with a mixture density network model to derive the conditional probability density function (PDF) of receiving power given a communication distance in general wireless communication systems. Furthermore, a deep transfer learning scheme is designed and implemented to allow the channel model to dynamically adapt to changes in communication environments. Extensive experiments on Nakagami fading channel model and Log-normal shadowing channel model with path loss and noise show that the new approach is more statistically accurate, faster, and more robust than the previous deep learning-based channel models.

arXiv:2405.08703

Using autoencoders and deep transfer learning to determine the stellar parameters of 286 CARMENES M dwarfs

Deep learning (DL) techniques are a promising approach among the set of methods used in the ever-challenging determination of stellar parameters in M dwarfs. In this context, transfer learning could play an important role in mitigating uncertainties in the results due to the synthetic gap (i.e. difference in feature distributions between observed and synthetic data). We propose a feature-based deep transfer learning (DTL) approach based on autoencoders to determine stellar parameters from high-resolution spectra. Using this methodology, we provide new estimations for the effective temperature, surface gravity, metallicity, and projected rotational velocity for 286 M dwarfs observed by the CARMENES survey. Using autoencoder architectures, we projected synthetic PHOENIX-ACES spectra and observed CARMENES spectra onto a new feature space of lower dimensionality in which the differences between the two domains are reduced. We used this low-dimensional new feature space as input for a convolutional neural network to obtain the stellar parameter determinations. We performed an extensive analysis of our estimated stellar parameters, ranging from 3050 to 4300 K, 4.7 to 5.1 dex, and -0.53 to 0.25 dex for Teff, logg, and [Fe/H], respectively. Our results are broadly consistent with those of recent studies using CARMENES data, with a systematic deviation in our Teff scale towards hotter values for estimations above 3750 K. Furthermore, our methodology mitigates the deviations in metallicity found in previous DL techniques due to the synthetic gap. We consolidated a DTL-based methodology to determine stellar parameters in M dwarfs from synthetic spectra, with no need for high-quality measurements involved in the knowledge transfer. These results suggest the great potential of DTL to mitigate the differences in feature distributions between the observations and the PHOENIX-ACES spectra.

arXiv:2405.06980

Fractals as Pre-training Datasets for Anomaly Detection and Localization

Anomaly detection is crucial in large-scale industrial manufacturing as it helps detect and localise defective parts. Pre-training feature extractors on large-scale datasets is a popular approach for this task. Stringent data security and privacy regulations and high costs and acquisition time hinder the availability and creation of such large datasets. While recent work in anomaly detection primarily focuses on the development of new methods built on such extractors, the importance of the data used for pre-training has not been studied. Therefore, we evaluated the performance of eight state-of-the-art methods pre-trained using dynamically generated fractal images on the famous benchmark datasets MVTec and VisA. In contrast to existing literature, which predominantly examines the transfer-learning capabilities of fractals, in this study, we compare models pre-trained with fractal images against those pre-trained with ImageNet, without subsequent fine-tuning. Although pre-training with ImageNet remains a clear winner, the results of fractals are promising considering that the anomaly detection task required features capable of discerning even minor visual variations. This opens up the possibility for a new research direction where feature extractors could be trained on synthetically generated abstract datasets reconciling the ever-increasing demand for data in machine learning while circumventing privacy and security concerns.

arXiv:2405.07869

Enhancing Clinically Significant Prostate Cancer Prediction in T2-weighted Images through Transfer Learning from Breast Cancer

In 2020, prostate cancer saw a staggering 1.4 million new cases, resulting in over 375,000 deaths. The accurate identification of clinically significant prostate cancer is crucial for delivering effective treatment to patients. Consequently, there has been a surge in research exploring the application of deep neural networks to predict clinical significance based on magnetic resonance images. However, these networks demand extensive datasets to attain optimal performance. Recently, transfer learning emerged as a technique that leverages acquired features from a domain with richer data to enhance the performance of a domain with limited data. In this paper, we investigate the improvement of clinically significant prostate cancer prediction in T2-weighted images through transfer learning from breast cancer. The results demonstrate a remarkable improvement of over 30% in leave-one-out cross-validation accuracy.

arXiv:2405.07827

Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor

Detecting an ingestion environment is an important aspect of monitoring dietary intake. It provides insightful information for dietary assessment. However, it is a challenging problem where human-based reviewing can be tedious, and algorithm-based review suffers from data imbalance and perceptual aliasing problems. To address these issues, we propose a neural network-based method with a two-stage training framework that tactfully combines fine-tuning and transfer learning techniques. Our method is evaluated on a newly collected dataset called ``UA Free Living Study", which uses an egocentric wearable camera, AIM-2 sensor, to simulate food consumption in free-living conditions. The proposed training framework is applied to common neural network backbones, combined with approaches in the general imbalanced classification field. Experimental results on the collected dataset show that our proposed method for automatic ingestion environment recognition successfully addresses the challenging data imbalance problem in the dataset and achieves a promising overall classification accuracy of 96.63%.

arXiv:2405.07295

Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer

Continual learning (CL) refers to an agent's capability to learn from a continuous stream of data and transfer knowledge without forgetting old information. One crucial aspect of CL is forward transfer, i.e., improved and faster learning on a new task by leveraging information from prior knowledge. While this ability comes naturally to biological brains, it poses a significant challenge for artificial intelligence (AI). Here, we suggest that environmental enrichment (EE) can be used as a biological model for studying forward transfer, inspiring human-like AI development. EE refers to animal studies that enhance cognitive, social, motor, and sensory stimulation and is a model for what, in humans, is referred to as 'cognitive reserve'. Enriched animals show significant improvement in learning speed and performance on new tasks, typically exhibiting forward transfer. We explore anatomical, molecular, and neuronal changes post-EE and discuss how artificial neural networks (ANNs) can be used to predict neural computation changes after enriched experiences. Finally, we provide a synergistic way of combining neuroscience and AI research that paves the path toward developing AI capable of rapid and efficient new task learning.