PyTorchKR Papers

최신 논문

총 9,217편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2411.05880

Towards Equitable ASD Diagnostics: A Comparative Study of Machine and Deep Learning Models Using Behavioral and Facial Data

Autism Spectrum Disorder (ASD) is often underdiagnosed in females due to gender-specific symptom differences overlooked by conventional diagnostics. This study evaluates machine learning models, particularly Random Forest and convolutional neural networks, for enhancing ASD diagnosis through structured data and facial image analysis. Random Forest achieved 100% validation accuracy across datasets, highlighting its ability to manage complex relationships and reduce false negatives, which is crucial for early intervention and addressing gender biases. In image-based analysis, MobileNet outperformed the baseline CNN, achieving 87% accuracy, though a 30% validation loss suggests possible overfitting, requiring further optimization for robustness in clinical settings. Future work will emphasize hyperparameter tuning, regularization, and transfer learning. Integrating behavioral data with facial analysis could improve diagnosis for underdiagnosed groups. These findings suggest Random Forest's high accuracy and balanced precision-recall metrics could enhance clinical workflows. MobileNet's lightweight structure also shows promise for resource-limited environments, enabling accessible ASD screening. Addressing model explainability and clinician trust will be vital.

arXiv:2411.06839

LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models

In this paper, we propose a novel LLM-Neo framework that efficiently transfers knowledge from a large language model (LLM) teacher to a compact student. Initially, we revisit the knowledge distillation (KD) and low-rank adaption (LoRA), and argue that they share the same paradigm. Inspired by this observation, we explore the strategy that combines LoRA and KD to enhance the efficiency of knowledge transfer. We first summarize some guidelines for this design and further develop the LLM-Neo. Experimental results on compressing Llama 2 and Llama 3 show that LLM-Neo outperforms various baselines. Further analysis demonstrates the robustness of the proposed LLM-Neo on variants of LoRA. The trained models have been available at \href{https://huggingface.co/collections/yang31210999/llm-neo-66e3c882f5579b829ff57eba}{this repository}.

arXiv:2411.06565공식 코드 · Papers with Code

Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction

The rapid advancement of machine learning has unlocked numerous opportunities for materials science, particularly in accelerating the design and analysis of materials. However, a significant challenge lies in the scarcity and high cost of obtaining high-quality materials datasets. While foundation models pre-trained on large datasets have excelled in fields like natural language processing by leveraging latent features through transfer learning, their application in materials science remains limited. Here, we present a foundation model specifically designed for composite materials. Pre-trained on a dataset of short-fiber composites to learn robust latent features, the model accurately predicts homogenized stiffness during transfer learning, even with limited training data. Additionally, our model effectively predicts the material's nonlinear behavior by transferring these learned features to an Interaction-based Material Network, which is a constitutive surrogate model. These results demonstrate the potential of our foundation model to capture complex material behaviors. Our findings validate the feasibility and effectiveness of foundation models in composite materials. We anticipate extending this approach to more complex three-dimensional composite materials, polycrystalline materials, and beyond. Moreover, this framework enables high-accuracy predictions even when experimental data are scarce, paving the way for more efficient and cost-effective materials design and analysis.

arXiv:2411.05028공식 코드 · Papers with Code

Leveraging Transfer Learning and Multiple Instance Learning for HER2 Automatic Scoring of H\&E Whole Slide Images

Expression of human epidermal growth factor receptor 2 (HER2) is an important biomarker in breast cancer patients who can benefit from cost-effective automatic Hematoxylin and Eosin (H\&E) HER2 scoring. However, developing such scoring models requires large pixel-level annotated datasets. Transfer learning allows prior knowledge from different datasets to be reused while multiple-instance learning (MIL) allows the lack of detailed annotations to be mitigated. The aim of this work is to examine the potential of transfer learning on the performance of deep learning models pre-trained on (i) Immunohistochemistry (IHC) images, (ii) H\&E images and (iii) non-medical images. A MIL framework with an attention mechanism is developed using pre-trained models as patch-embedding models. It was found that embedding models pre-trained on H\&E images consistently outperformed the others, resulting in an average AUC-ROC value of $0.622$ across the 4 HER2 scores ($0.59-0.80$ per HER2 score). Furthermore, it was found that using multiple-instance learning with an attention layer not only allows for good classification results to be achieved, but it can also help with producing visual indication of HER2-positive areas in the H\&E slide image by utilising the patch-wise attention weights.

arXiv:2411.05188

AGE2HIE: Transfer Learning from Brain Age to Predicting Neurocognitive Outcome for Infant Brain Injury

Hypoxic-Ischemic Encephalopathy (HIE) affects 1 to 5 out of every 1,000 newborns, with 30% to 50% of cases resulting in adverse neurocognitive outcomes. However, these outcomes can only be reliably assessed as early as age 2. Therefore, early and accurate prediction of HIE-related neurocognitive outcomes using deep learning models is critical for improving clinical decision-making, guiding treatment decisions and assessing novel therapies. However, a major challenge in developing deep learning models for this purpose is the scarcity of large, annotated HIE datasets. We have assembled the first and largest public dataset, however it contains only 156 cases with 2-year neurocognitive outcome labels. In contrast, we have collected 8,859 normal brain black Magnetic Resonance Imagings (MRIs) with 0-97 years of age that are available for brain age estimation using deep learning models. In this paper, we introduce AGE2HIE to transfer knowledge learned by deep learning models from healthy controls brain MRIs to a diseased cohort, from structural to diffusion MRIs, from regression of continuous age estimation to prediction of the binary neurocognitive outcomes, and from lifespan age (0-97 years) to infant (0-2 weeks). Compared to training from scratch, transfer learning from brain age estimation significantly improves not only the prediction accuracy (3% or 2% improvement in same or multi-site), but also the model generalization across different sites (5% improvement in cross-site validation).

arXiv:2411.05597공식 코드 · Papers with Code

Predicting Stroke through Retinal Graphs and Multimodal Self-supervised Learning

Early identification of stroke is crucial for intervention, requiring reliable models. We proposed an efficient retinal image representation together with clinical information to capture a comprehensive overview of cardiovascular health, leveraging large multimodal datasets for new medical insights. Our approach is one of the first contrastive frameworks that integrates graph and tabular data, using vessel graphs derived from retinal images for efficient representation. This method, combined with multimodal contrastive learning, significantly enhances stroke prediction accuracy by integrating data from multiple sources and using contrastive learning for transfer learning. The self-supervised learning techniques employed allow the model to learn effectively from unlabeled data, reducing the dependency on large annotated datasets. Our framework showed an AUROC improvement of 3.78% from supervised to self-supervised approaches. Additionally, the graph-level representation approach achieved superior performance to image encoders while significantly reducing pre-training and fine-tuning runtimes. These findings indicate that retinal images are a cost-effective method for improving cardiovascular disease predictions and pave the way for future research into retinal and cerebral vessel connections and the use of graph-based retinal vessel representations.

arXiv:2411.04404

Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation

Monocular depth estimation has shown promise in general imaging tasks, aiding in localization and 3D reconstruction. While effective in various domains, its application to bronchoscopic images is hindered by the lack of labeled data, challenging the use of supervised learning methods. In this work, we propose a transfer learning framework that leverages synthetic data with depth labels for training and adapts domain knowledge for accurate depth estimation in real bronchoscope data. Our network demonstrates improved depth prediction on real footage using domain adaptation compared to training solely on synthetic data, validating our approach.

arXiv:2411.04644공식 코드 · Papers with Code

wav2sleep: A Unified Multi-Modal Approach to Sleep Stage Classification from Physiological Signals

Accurate classification of sleep stages from less obtrusive sensor measurements such as the electrocardiogram (ECG) or photoplethysmogram (PPG) could enable important applications in sleep medicine. Existing approaches to this problem have typically used deep learning models designed and trained to operate on one or more specific input signals. However, the datasets used to develop these models often do not contain the same sets of input signals. Some signals, particularly PPG, are much less prevalent than others, and this has previously been addressed with techniques such as transfer learning. Additionally, only training on one or more fixed modalities precludes cross-modal information transfer from other sources, which has proved valuable in other problem domains. To address this, we introduce wav2sleep, a unified model designed to operate on variable sets of input signals during training and inference. After jointly training on over 10,000 overnight recordings from six publicly available polysomnography datasets, including SHHS and MESA, wav2sleep outperforms existing sleep stage classification models across test-time input combinations including ECG, PPG, and respiratory signals.

arXiv:2411.02587

A Big Data-empowered System for Real-time Detection of Regional Discriminatory Comments on Vietnamese Social Media

Regional discrimination is a persistent social issue in Vietnam. While existing research has explored hate speech in the Vietnamese language, the specific issue of regional discrimination remains under-addressed. Previous studies primarily focused on model development without considering practical system implementation. In this work, we propose a task called Detection of Regional Discriminatory Comments on Vietnamese Social Media, leveraging the power of machine learning and transfer learning models. We have built the ViRDC (Vietnamese Regional Discrimination Comments) dataset, which contains comments from social media platforms, providing a valuable resource for further research and development. Our approach integrates streaming capabilities to process real-time data from social media networks, ensuring the system's scalability and responsiveness. We developed the system on the Apache Spark framework to efficiently handle increasing data inputs during streaming. Our system offers a comprehensive solution for the real-time detection of regional discrimination in Vietnam.

arXiv:2411.03372

Energy Price Modelling: A Comparative Evaluation of four Generations of Forecasting Methods

Energy is a critical driver of modern economic systems. Accurate energy price forecasting plays an important role in supporting decision-making at various levels, from operational purchasing decisions at individual business organizations to policy-making. A significant body of literature has looked into energy price forecasting, investigating a wide range of methods to improve accuracy and inform these critical decisions. Given the evolving landscape of forecasting techniques, the literature lacks a thorough empirical comparison that systematically contrasts these methods. This paper provides an in-depth review of the evolution of forecasting modeling frameworks, from well-established econometric models to machine learning methods, early sequence learners such LSTMs, and more recent advancements in deep learning with transformer networks, which represent the cutting edge in forecasting. We offer a detailed review of the related literature and categorize forecasting methodologies into four model families. We also explore emerging concepts like pre-training and transfer learning, which have transformed the analysis of unstructured data and hold significant promise for time series forecasting. We address a gap in the literature by performing a comprehensive empirical analysis on these four family models, using data from the EU energy markets, we conduct a large-scale empirical study, which contrasts the forecasting accuracy of different approaches, focusing especially on alternative propositions for time series transformers.

arXiv:2411.03941

Fine-tuning -- a Transfer Learning approach

Secondary research use of Electronic Health Records (EHRs) is often hampered by the abundance of missing data in this valuable resource. Missingness in EHRs occurs naturally as a result of the data recording practices during routine clinical care, but handling it is crucial to the precision of medical analysis and the decision-making that follows. The literature contains a variety of imputation methodologies based on deep neural networks. Those aim to overcome the dynamic, heterogeneous and multivariate missingness patterns of EHRs, which cannot be handled by classical and statistical imputation methods. However, all existing deep imputation methods rely on end-to-end pipelines that incorporate both imputation and downstream analyses, e.g. classification. This coupling makes it difficult to assess the quality of imputation and takes away the flexibility of re-using the imputer for a different task. Furthermore, most end-to-end deep architectures tend to use complex networks to perform the downstream task, in addition to the already sophisticated deep imputation network. We, therefore ask if the high performance reported in the literature is due to the imputer or the classifier and further ask if an optimised state-of-the-art imputer is used, a simpler classifier can achieve comparable performance. This paper explores the development of a modular, deep learning-based imputation and classification pipeline, specifically built to leverage the capabilities of state-of-the-art imputation models for downstream classification tasks. Such a modular approach enables a) objective assessment of the quality of the imputer and classifier independently, and b) enables the exploration of the performance of simpler classification architectures using an optimised imputer.

arXiv:2411.03618

Cross Feature Fusion of Fundus Image and Generated Lesion Map for Referable Diabetic Retinopathy Classification

Diabetic Retinopathy (DR) is a primary cause of blindness, necessitating early detection and diagnosis. This paper focuses on referable DR classification to enhance the applicability of the proposed method in clinical practice. We develop an advanced cross-learning DR classification method leveraging transfer learning and cross-attention mechanisms. The proposed method employs the Swin U-Net architecture to segment lesion maps from DR fundus images. The Swin U-Net segmentation model, enriched with DR lesion insights, is transferred to generate a lesion map. Both the fundus image and its segmented lesion map are used as complementary inputs for the classification model. A cross-attention mechanism is deployed to improve the model's ability to capture fine-grained details from the input pairs. Our experiments, utilizing two public datasets, FGADR and EyePACS, demonstrate a superior accuracy of 94.6%, surpassing current state-of-the-art methods by 4.4%. To this end, we aim for the proposed method to be seamlessly integrated into clinical workflows, enhancing accuracy and efficiency in identifying referable DR.

arXiv:2411.03263

Proxy-informed Bayesian transfer learning with unknown sources

Generalization outside the scope of one's training data requires leveraging prior knowledge about the effects that transfer, and the effects that don't, between different data sources. Bayesian transfer learning is a principled paradigm for specifying this knowledge, and refining it on the basis of data from the source (training) and target (prediction) tasks. We address the challenging transfer learning setting where the learner (i) cannot fine-tune in the target task, and (ii) does not know which source data points correspond to the same task (i.e., the data sources are unknown). We propose a proxy-informed robust method for probabilistic transfer learning (PROMPT), which provides a posterior predictive estimate tailored to the structure of the target task, without requiring the learner have access to any outcome information from the target task. Instead, PROMPT relies on the availability of proxy information. PROMPT uses the same proxy information for two purposes: (i) estimation of effects specific to the target task, and (ii) construction of a robust reweighting of the source data for estimation of effects that transfer between tasks. We provide theoretical results on the effect of this reweighting on the risk of negative transfer, and demonstrate application of PROMPT in two synthetic settings.

arXiv:2411.03064

Exploiting the Segment Anything Model (SAM) for Lung Segmentation in Chest X-ray Images

Segment Anything Model (SAM), a new AI model from Meta AI released in April 2023, is an ambitious tool designed to identify and separate individual objects within a given image through semantic interpretation. The advanced capabilities of SAM are the result of its training with millions of images and masks, and a few days after its release, several researchers began testing the model on medical images to evaluate its performance in this domain. With this perspective in focus -- i.e., optimizing work in the healthcare field -- this work proposes the use of this new technology to evaluate and study chest X-ray images. The approach adopted for this work, with the aim of improving the model's performance for lung segmentation, involved a transfer learning process, specifically the fine-tuning technique. After applying this adjustment, a substantial improvement was observed in the evaluation metrics used to assess SAM's performance compared to the masks provided by the datasets. The results obtained by the model after the adjustments were satisfactory and similar to cutting-edge neural networks, such as U-Net.

arXiv:2411.02941

A Mamba Foundation Model for Time Series Forecasting

Time series foundation models have demonstrated strong performance in zero-shot learning, making them well-suited for predicting rapidly evolving patterns in real-world applications where relevant training data are scarce. However, most of these models rely on the Transformer architecture, which incurs quadratic complexity as input length increases. To address this, we introduce TSMamba, a linear-complexity foundation model for time series forecasting built on the Mamba architecture. The model captures temporal dependencies through both forward and backward Mamba encoders, achieving high prediction accuracy. To reduce reliance on large datasets and lower training costs, TSMamba employs a two-stage transfer learning process that leverages pretrained Mamba LLMs, allowing effective time series modeling with a moderate training set. In the first stage, the forward and backward backbones are optimized via patch-wise autoregressive prediction; in the second stage, the model trains a prediction head and refines other components for long-term forecasting. While the backbone assumes channel independence to manage varying channel numbers across datasets, a channel-wise compressed attention module is introduced to capture cross-channel dependencies during fine-tuning on specific multivariate datasets. Experiments show that TSMamba's zero-shot performance is comparable to state-of-the-art time series foundation models, despite using significantly less training data. It also achieves competitive or superior full-shot performance compared to task-specific prediction models. The code will be made publicly available.

arXiv:2411.00969

Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior

Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world deployment. To address this, researchers often reduce model size by pruning parameters based on their magnitude or sensitivity. Previous research has demonstrated the limitations of magnitude pruning, especially in the context of transfer learning for modern NLP tasks. In this paper, we introduce a new magnitude-based pruning algorithm called mixture Gaussian prior pruning (MGPP), which employs a mixture Gaussian prior for regularization. MGPP prunes non-expressive weights under the guidance of the mixture Gaussian prior, aiming to retain the model's expressive capability. Extensive evaluations across various NLP tasks, including natural language understanding, question answering, and natural language generation, demonstrate the superiority of MGPP over existing pruning methods, particularly in high sparsity settings. Additionally, we provide a theoretical justification for the consistency of the sparse transformer, shedding light on the effectiveness of the proposed pruning method.

arXiv:2411.01195

Transfer Learning for Finetuning Large Language Models

As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently, practitioners face a multitude of complex choices when searching for an optimal finetuning pipeline for large language models. To reduce the complexity for practitioners, we investigate transfer learning for finetuning large language models and aim to transfer knowledge about configurations from related finetuning tasks to a new task. In this work, we transfer learn finetuning by meta-learning performance and cost surrogate models for grey-box meta-optimization from a new meta-dataset. Counter-intuitively, we propose to rely only on transfer learning for new datasets. Thus, we do not use task-specific Bayesian optimization but prioritize knowledge transferred from related tasks over task-specific feedback. We evaluate our method on eight synthetic question-answer datasets and a meta-dataset consisting of 1,800 runs of finetuning Microsoft's Phi-3. Our transfer learning is superior to zero-shot, default finetuning, and meta-optimization baselines. Our results demonstrate the transferability of finetuning to adapt large language models more effectively.

arXiv:2411.02127

Supervised Transfer Learning Framework for Fault Diagnosis in Wind Turbines

Common challenges in fault diagnosis include the lack of labeled data and the need to build models for each domain, resulting in many models that require supervision. Transfer learning can help tackle these challenges by learning cross-domain knowledge. Many approaches still require at least some labeled data in the target domain, and often provide unexplainable results. To this end, we propose a supervised transfer learning framework for fault diagnosis in wind turbines that operates in an Anomaly-Space. This space was created using SCADA data and vibration data and was built and provided to us by our research partner. Data within the Anomaly-Space can be interpreted as anomaly scores for each component in the wind turbine, making each value intuitive to understand. We conducted cross-domain evaluation on the train set using popular supervised classifiers like Random Forest, Light-Gradient-Boosting-Machines and Multilayer Perceptron as metamodels for the diagnosis of bearing and sensor faults. The Multilayer Perceptron achieved the highest classification performance. This model was then used for a final evaluation in our test set. The results show, that the proposed framework is able to detect cross-domain faults in the test set with a high degree of accuracy by using one single classifier, which is a significant asset to the diagnostic team.

arXiv:2411.02065

AM Flow: Adapters for Temporal Processing in Action Recognition

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of \textit{video} classification. Video foundation models suffer from the requirement of extensive pretraining and a large training time. Towards mitigating such limitations, we propose "\textit{Attention Map (AM) Flow}" for image models, a method for identifying pixels relevant to motion in each input video frame. In this context, we propose two methods to compute AM flow, depending on camera motion. AM flow allows the separation of spatial and temporal processing, while providing improved results over combined spatio-temporal processing (as in video models). Adapters, one of the popular techniques in parameter efficient transfer learning, facilitate the incorporation of AM flow into pretrained image models, mitigating the need for full-finetuning. We extend adapters to "\textit{temporal processing adapters}" by incorporating a temporal processing unit into the adapters. Our work achieves faster convergence, therefore reducing the number of epochs needed for training. Moreover, we endow an image model with the ability to achieve state-of-the-art results on popular action recognition datasets. This reduces training time and simplifies pretraining. We present experiments on Kinetics-400, Something-Something v2, and Toyota Smarthome datasets, showcasing state-of-the-art or comparable results.

arXiv:2411.00556

LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering

We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as direct inputs, our framework injects these features into an intermediate layer of any CF model, allowing the model to reconstruct and leverage the embeddings internally. This model-agnostic approach works with a wide range of CF models without requiring architectural changes, making it adaptable to various recommendation scenarios. Our framework is built for easy integration and modification, providing researchers and developers with a powerful tool for extending CF model capabilities through efficient knowledge transfer. We demonstrate its effectiveness through experiments on the MovieLens and Amazon datasets, where it consistently improves baseline CF models. Experimental studies showed that LLM-KT is competitive with the state-of-the-art methods in context-aware settings but can be applied to a broader range of CF models than current approaches.