PyTorchKR Papers

최신 논문

총 10,240편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.10793

An end-to-end attention-based approach for learning on graphs

There has been a recent surge in transformer-based architectures for learning on graphs, mainly motivated by attention as an effective learning mechanism and the desire to supersede handcrafted operators characteristic of message passing schemes. However, concerns over their empirical effectiveness, scalability, and complexity of the pre-processing steps have been raised, especially in relation to much simpler graph neural networks that typically perform on par with them across a wide range of benchmarks. To tackle these shortcomings, we consider graphs as sets of edges and propose a purely attention-based approach consisting of an encoder and an attention pooling mechanism. The encoder vertically interleaves masked and vanilla self-attention modules to learn an effective representations of edges, while allowing for tackling possible misspecifications in input graphs. Despite its simplicity, the approach outperforms fine-tuned message passing baselines and recently proposed transformer-based methods on more than 70 node and graph-level tasks, including challenging long-range benchmarks. Moreover, we demonstrate state-of-the-art performance across different tasks, ranging from molecular to vision graphs, and heterophilous node classification. The approach also outperforms graph neural networks and transformers in transfer learning settings, and scales much better than alternatives with a similar performance level or expressive power.

arXiv:2402.10251공식 코드 · Papers with Code

BrainWave: A Brain Signal Foundation Model for Clinical Applications

Neural electrical activity is fundamental to brain function, underlying a range of cognitive and behavioral processes, including movement, perception, decision-making, and consciousness. Abnormal patterns of neural signaling often indicate the presence of underlying brain diseases. The variability among individuals, the diverse array of clinical symptoms from various brain disorders, and the limited availability of diagnostic classifications, have posed significant barriers to formulating reliable model of neural signals for diverse application contexts. Here, we present BrainWave, the first foundation model for both invasive and non-invasive neural recordings, pretrained on more than 40,000 hours of electrical brain recordings (13.79 TB of data) from approximately 16,000 individuals. Our analysis show that BrainWave outperforms all other competing models and consistently achieves state-of-the-art performance in the diagnosis and identification of neurological disorders. We also demonstrate robust capabilities of BrainWave in enabling zero-shot transfer learning across varying recording conditions and brain diseases, as well as few-shot classification without fine-tuning, suggesting that BrainWave learns highly generalizable representations of neural signals. We hence believe that open-sourcing BrainWave will facilitate a wide range of clinical applications in medicine, paving the way for AI-driven approaches to investigate brain disorders and advance neuroscience research.

arXiv:2402.09437공식 코드 · Papers with Code

Managing Household Waste through Transfer Learning

As the world continues to face the challenges of climate change, it is crucial to consider the environmental impact of the technologies we use. In this study, we investigate the performance and computational carbon emissions of various transfer learning models for garbage classification. We examine the MobileNet, ResNet50, ResNet101, and EfficientNetV2S and EfficientNetV2M models. Our findings indicate that the EfficientNetV2 family achieves the highest accuracy, recall, f1-score, and IoU values. However, the EfficientNetV2M model requires more time and produces higher carbon emissions. ResNet50 outperforms ResNet110 in terms of accuracy, recall, f1-score, and IoU, but it has a larger carbon footprint. We conclude that EfficientNetV2S is the most sustainable and accurate model with 96.41% accuracy. Our research highlights the significance of considering the ecological impact of machine learning models in garbage classification.

arXiv:2402.09658

Towards Precision Cardiovascular Analysis in Zebrafish: The ZACAF Paradigm

Quantifying cardiovascular parameters like ejection fraction in zebrafish as a host of biological investigations has been extensively studied. Since current manual monitoring techniques are time-consuming and fallible, several image processing frameworks have been proposed to automate the process. Most of these works rely on supervised deep-learning architectures. However, supervised methods tend to be overfitted on their training dataset. This means that applying the same framework to new data with different imaging setups and mutant types can severely decrease performance. We have developed a Zebrafish Automatic Cardiovascular Assessment Framework (ZACAF) to quantify the cardiac function in zebrafish. In this work, we further applied data augmentation, Transfer Learning (TL), and Test Time Augmentation (TTA) to ZACAF to improve the performance for the quantification of cardiovascular function quantification in zebrafish. This strategy can be integrated with the available frameworks to aid other researchers. We demonstrate that using TL, even with a constrained dataset, the model can be refined to accommodate a novel microscope setup, encompassing diverse mutant types and accommodating various video recording protocols. Additionally, as users engage in successive rounds of TL, the model is anticipated to undergo substantial enhancements in both generalizability and accuracy. Finally, we applied this approach to assess the cardiovascular function in nrap mutant zebrafish, a model of cardiomyopathy.

arXiv:2402.09982

Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition

The face expression is the first thing we pay attention to when we want to understand a person's state of mind. Thus, the ability to recognize facial expressions in an automatic way is a very interesting research field. In this paper, because the small size of available training datasets, we propose a novel data augmentation technique that improves the performances in the recognition task. We apply geometrical transformations and build from scratch GAN models able to generate new synthetic images for each emotion type. Thus, on the augmented datasets we fine tune pretrained convolutional neural networks with different architectures. To measure the generalization ability of the models, we apply extra-database protocol approach, namely we train models on the augmented versions of training dataset and test them on two different databases. The combination of these techniques allows to reach average accuracy values of the order of 85\% for the InceptionResNetV2 model.

arXiv:2402.09234

Multi-Hierarchical Surrogate Learning for Structural Dynamical Crash Simulations Using Graph Convolutional Neural Networks

Crash simulations play an essential role in improving vehicle safety, design optimization, and injury risk estimation. Unfortunately, numerical solutions of such problems using state-of-the-art high-fidelity models require significant computational effort. Conventional data-driven surrogate modeling approaches create low-dimensional embeddings for evolving the dynamics in order to circumvent this computational effort. Most approaches directly operate on high-resolution data obtained from numerical discretization, which is both costly and complicated for mapping the flow of information over large spatial distances. Furthermore, working with a fixed resolution prevents the adaptation of surrogate models to environments with variable computing capacities, different visualization resolutions, and different accuracy requirements. We thus propose a multi-hierarchical framework for structurally creating a series of surrogate models for a kart frame, which is a good proxy for industrial-relevant crash simulations, at different levels of resolution. For multiscale phenomena, macroscale features are captured on a coarse surrogate, whereas microscale effects are resolved by finer ones. The learned behavior of the individual surrogates is passed from coarse to finer levels through transfer learning. In detail, we perform a mesh simplification on the kart model to obtain multi-resolution representations of it. We then train a graph-convolutional neural network-based surrogate that learns parameter-dependent low-dimensional latent dynamics on the coarsest representation. Subsequently, another, similarly structured surrogate is trained on the residual of the first surrogate using a finer resolution. This step can be repeated multiple times. By doing so, we construct multiple surrogates for the same system with varying hardware requirements and increasing accuracy.

arXiv:2402.09113

How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories

The rising successes of RL are propelled by combining smart algorithmic strategies and deep architectures to optimize the distribution of returns and visitations over the state-action space. A quantitative framework to compare the learning processes of these eclectic RL algorithms is currently absent but desired in practice. We address this gap by representing the learning process of an RL algorithm as a sequence of policies generated during training, and then studying the policy trajectory induced in the manifold of state-action occupancy measures. Using an optimal transport-based metric, we measure the length of the paths induced by the policy sequence yielded by an RL algorithm between an initial policy and a final optimal policy. Hence, we first define the 'Effort of Sequential Learning' (ESL). ESL quantifies the relative distance that an RL algorithm travels compared to the shortest path from the initial to the optimal policy. Further, we connect the dynamics of policies in the occupancy measure space and regret (another metric to understand the suboptimality of an RL algorithm), by defining the 'Optimal Movement Ratio' (OMR). OMR assesses the fraction of movements in the occupancy measure space that effectively reduce an analogue of regret. Finally, we derive approximation guarantees to estimate ESL and OMR with finite number of samples and without access to an optimal policy. Through empirical analyses across various environments and algorithms, we demonstrate that ESL and OMR provide insights into the exploration processes of RL algorithms and hardness of different tasks in discrete and continuous MDPs.

arXiv:2402.09315

Few-Shot Object Detection with Sparse Context Transformers

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain. As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion. We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art.

arXiv:2402.09367공식 코드 · Papers with Code

Evaluation of Activated Sludge Settling Characteristics from Microscopy Images with Deep Convolutional Neural Networks and Transfer Learning

Microbial communities play a key role in biological wastewater treatment processes. Activated sludge settling characteristics, for example, are affected by microbial community composition, varying by changes in operating conditions and influent characteristics of wastewater treatment plants (WWTPs). Timely assessment and prediction of changes in microbial composition leading to settling problems, such as filamentous bulking (FB), can prevent operational challenges, reductions in treatment efficiency, and adverse environmental impacts. This study presents an innovative computer vision-based approach to assess activated sludge-settling characteristics based on the morphological properties of flocs and filaments in microscopy images. Implementing the transfer learning of deep convolutional neural network (CNN) models, this approach aims to overcome the limitations of existing quantitative image analysis techniques. The offline microscopy image dataset was collected over two years, with weekly sampling at a full-scale industrial WWTP in Belgium. Multiple data augmentation techniques were employed to enhance the generalizability of the CNN models. Various CNN architectures, including Inception v3, ResNet18, ResNet152, ConvNeXt-nano, and ConvNeXt-S, were tested to evaluate their performance in predicting sludge settling characteristics. The sludge volume index was used as the final prediction variable, but the method can easily be adjusted to predict any other settling metric of choice. The results showed that the suggested CNN-based approach provides less labour-intensive, objective, and consistent assessments, while transfer learning notably minimises the training phase, resulting in a generalizable system that can be employed in real-time applications.

arXiv:2402.08907공식 코드 · Papers with Code

Subgraph Pooling: Tackling Negative Transfer on Graphs

Transfer learning aims to enhance performance on a target task by using knowledge from related tasks. However, when the source and target tasks are not closely aligned, it can lead to reduced performance, known as negative transfer. Unlike in image or text data, we find that negative transfer could commonly occur in graph-structured data, even when source and target graphs have semantic similarities. Specifically, we identify that structural differences significantly amplify the dissimilarities in the node embeddings across graphs. To mitigate this, we bring a new insight in this paper: for semantically similar graphs, although structural differences lead to significant distribution shift in node embeddings, their impact on subgraph embeddings could be marginal. Building on this insight, we introduce Subgraph Pooling (SP) by aggregating nodes sampled from a k-hop neighborhood and Subgraph Pooling++ (SP++) by a random walk, to mitigate the impact of graph structural differences on knowledge transfer. We theoretically analyze the role of SP in reducing graph discrepancy and conduct extensive experiments to evaluate its superiority under various settings. The proposed SP methods are effective yet elegant, which can be easily applied on top of any backbone Graph Neural Networks (GNNs). Our code and data are available at: https://github.com/Zehong-Wang/Subgraph-Pooling.

arXiv:2402.08594공식 코드 · Papers with Code

Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning

Prompt tuning, in which prompts are optimized to adapt large-scale pre-trained language models to downstream tasks instead of fine-tuning the full model parameters, has been shown to be particularly effective when the prompts are trained in a multi-task transfer learning setting. These methods generally involve individually training prompts for each source task and then aggregating them to provide the initialization of the prompt for the target task. However, this approach critically ignores the fact that some of the source tasks could be negatively or positively interfering with each other. We argue that when we extract knowledge from source tasks via training source prompts, we need to consider this correlation among source tasks for better transfer to target tasks. To this end, we propose a Bayesian approach where we work with the posterior distribution of prompts across source tasks. We obtain representative source prompts corresponding to the samples from the posterior utilizing Stein Variational Gradient Descent, which are then aggregated to constitute the initial target prompt. We show extensive experimental results on the standard benchmark NLP tasks, where our Bayesian multi-task transfer learning approach outperforms the state-of-the-art methods in many settings. Furthermore, our approach requires no auxiliary models other than the prompt itself, achieving a high degree of parameter efficiency.

arXiv:2402.08592

Convolutional Neural Networks Towards Facial Skin Lesions Detection

Facial analysis has emerged as a prominent area of research with diverse applications, including cosmetic surgery programs, the beauty industry, photography, and entertainment. Manipulating patient images often necessitates professional image processing software. This study contributes by providing a model that facilitates the detection of blemishes and skin lesions on facial images through a convolutional neural network and machine learning approach. The proposed method offers advantages such as simple architecture, speed and suitability for image processing while avoiding the complexities associated with traditional methods. The model comprises four main steps: area selection, scanning the chosen region, lesion diagnosis, and marking the identified lesion. Raw data for this research were collected from a reputable clinic in Tehran specializing in skincare and beauty services. The dataset includes administrative information, clinical data, and facial and profile images. A total of 2300 patient images were extracted from this raw data. A software tool was developed to crop and label lesions, with input from two treatment experts. In the lesion preparation phase, the selected area was standardized to 50 * 50 pixels. Subsequently, a convolutional neural network model was employed for lesion labeling. The classification model demonstrated high accuracy, with a measure of 0.98 for healthy skin and 0.97 for lesioned skin specificity. Internal validation involved performance indicators and cross-validation, while external validation compared the model's performance indicators with those of the transfer learning method using the Vgg16 deep network model. Compared to existing studies, the results of this research showcase the efficacy and desirability of the proposed model and methodology.

arXiv:2402.08578공식 코드 · Papers with Code

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing

Federated Learning (FL) has emerged as a promising solution in Edge Computing (EC) environments to process the proliferation of data generated by edge devices. By collaboratively optimizing the global machine learning models on distributed edge devices, FL circumvents the need for transmitting raw data and enhances user privacy. Despite practical successes, FL still confronts significant challenges including constrained edge device resources, multiple tasks deployment, and data heterogeneity. However, existing studies focus on mitigating the FL training costs of each single task whereas neglecting the resource consumption across multiple tasks in heterogeneous FL scenarios. In this paper, we propose Heterogeneous Federated Learning with Local Parameter Sharing (FedLPS) to fill this gap. FedLPS leverages principles from transfer learning to facilitate the deployment of multiple tasks on a single device by dividing the local model into a shareable encoder and task-specific encoders. To further reduce resource consumption, a channel-wise model pruning algorithm that shrinks the footprint of local models while accounting for both data and system heterogeneity is employed in FedLPS. Additionally, a novel heterogeneous model aggregation algorithm is proposed to aggregate the heterogeneous predictors in FedLPS. We implemented the proposed FedLPS on a real FL platform and compared it with state-of-the-art (SOTA) FL frameworks. The experimental results on five popular datasets and two modern DNN models illustrate that the proposed FedLPS significantly outperforms the SOTA FL frameworks by up to 4.88% and reduces the computational resource consumption by 21.3%. Our code is available at:https://github.com/jyzgh/FedLPS.

arXiv:2402.08184

Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation

Multi-Agent Reinforcement Learning (MARL) algorithms are widely adopted in tackling complex tasks that require collaboration and competition among agents in dynamic Multi-Agent Systems (MAS). However, learning such tasks from scratch is arduous and may not always be feasible, particularly for MASs with a large number of interactive agents due to the extensive sample complexity. Therefore, reusing knowledge gained from past experiences or other agents could efficiently accelerate the learning process and upscale MARL algorithms. In this study, we introduce a novel framework that enables transfer learning for MARL through unifying various state spaces into fixed-size inputs that allow one unified deep-learning policy viable in different scenarios within a MAS. We evaluated our approach in a range of scenarios within the StarCraft Multi-Agent Challenge (SMAC) environment, and the findings show significant enhancements in multi-agent learning performance using maneuvering skills learned from other scenarios compared to agents learning from scratch. Furthermore, we adopted Curriculum Transfer Learning (CTL), enabling our deep learning policy to progressively acquire knowledge and skills across pre-designed homogeneous learning scenarios organized by difficulty levels. This process promotes inter- and intra-agent knowledge transfer, leading to high multi-agent learning performance in more complicated heterogeneous scenarios.

arXiv:2402.08112공식 코드 · Papers with Code

A Competition Winning Deep Reinforcement Learning Agent in microRTS

Scripted agents have predominantly won the five previous iterations of the IEEE microRTS ($\mu$RTS) competitions hosted at CIG and CoG. Despite Deep Reinforcement Learning (DRL) algorithms making significant strides in real-time strategy (RTS) games, their adoption in this primarily academic competition has been limited due to the considerable training resources required and the complexity inherent in creating and debugging such agents. RAISocketAI is the first DRL agent to win the IEEE microRTS competition. In a benchmark without performance constraints, RAISocketAI regularly defeated the two prior competition winners. This first competition-winning DRL submission can be a benchmark for future microRTS competitions and a starting point for future DRL research. Iteratively fine-tuning the base policy and transfer learning to specific maps were critical to RAISocketAI's winning performance. These strategies can be used to economically train future DRL agents. Further work in Imitation Learning using Behavior Cloning and fine-tuning these models with DRL has proven promising as an efficient way to bootstrap models with demonstrated, competitive behaviors.

arXiv:2402.06674

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of fine-tuned neural networks both empirically and theoretically, the latter using a simplified model of fine-tuning. We show that the vulnerability of non-DP models when measured as the attacker advantage at fixed false positive rate reduces according to a simple power law as the number of examples per class increases, even for the most vulnerable points, but the dataset size needed for adequate protection of the most vulnerable points is very large.

arXiv:2402.07767공식 코드 · Papers with Code

Text Detoxification as Style Transfer in English and Hindi

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text style changes while its content is preserved. We present three approaches: knowledge transfer from a similar task, multi-task learning approach, combining sequence-to-sequence modeling with various toxicity classification tasks, and delete and reconstruct approach. To support our research, we utilize a dataset provided by Dementieva et al.(2021), which contains multiple versions of detoxified texts corresponding to toxic texts. In our experiments, we selected the best variants through expert human annotators, creating a dataset where each toxic sentence is paired with a single, appropriate detoxified version. Additionally, we introduced a small Hindi parallel dataset, aligning with a part of the English dataset, suitable for evaluation purposes. Our results demonstrate that our approach effectively balances text detoxication while preserving the actual content and maintaining fluency.

arXiv:2402.06948

Should I try multiple optimizers when fine-tuning pre-trained Transformers for NLP tasks? Should I tune their hyperparameters?

NLP research has explored different neural model architectures and sizes, datasets, training objectives, and transfer learning techniques. However, the choice of optimizer during training has not been explored as extensively. Typically, some variant of Stochastic Gradient Descent (SGD) is employed, selected among numerous variants, using unclear criteria, often with minimal or no tuning of the optimizer's hyperparameters. Experimenting with five GLUE datasets, two models (DistilBERT and DistilRoBERTa), and seven popular optimizers (SGD, SGD with Momentum, Adam, AdaMax, Nadam, AdamW, and AdaBound), we find that when the hyperparameters of the optimizers are tuned, there is no substantial difference in test performance across the five more elaborate (adaptive) optimizers, despite differences in training loss. Furthermore, tuning just the learning rate is in most cases as good as tuning all the hyperparameters. Hence, we recommend picking any of the best-behaved adaptive optimizers (e.g., Adam) and tuning only its learning rate. When no hyperparameter can be tuned, SGD with Momentum is the best choice.

arXiv:2402.06761

Embedding Compression for Teacher-to-Student Knowledge Transfer

Common knowledge distillation methods require the teacher model and the student model to be trained on the same task. However, the usage of embeddings as teachers has also been proposed for different source tasks and target tasks. Prior work that uses embeddings as teachers ignores the fact that the teacher embeddings are likely to contain irrelevant knowledge for the target task. To address this problem, we propose to use an embedding compression module with a trainable teacher transformation to obtain a compact teacher embedding. Results show that adding the embedding compression module improves the classification performance, especially for unsupervised teacher embeddings. Moreover, student models trained with the guidance of embeddings show stronger generalizability.

arXiv:2402.07595공식 코드 · Papers with Code

Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification

Medical image analysis frequently encounters data scarcity challenges. Transfer learning has been effective in addressing this issue while conserving computational resources. The recent advent of foundational models like the DINOv2, which uses the vision transformer architecture, has opened new opportunities in the field and gathered significant interest. However, DINOv2's performance on clinical data still needs to be verified. In this paper, we performed a glioma grading task using three clinical modalities of brain MRI data. We compared the performance of various pre-trained deep learning models, including those based on ImageNet and DINOv2, in a transfer learning context. Our focus was on understanding the impact of the freezing mechanism on performance. We also validated our findings on three other types of public datasets: chest radiography, fundus radiography, and dermoscopy. Our findings indicate that in our clinical dataset, DINOv2's performance was not as strong as ImageNet-based pre-trained models, whereas in public datasets, DINOv2 generally outperformed other models, especially when using the frozen mechanism. Similar performance was observed with various sizes of DINOv2 models across different tasks. In summary, DINOv2 is viable for medical image classification tasks, particularly with data resembling natural images. However, its effectiveness may vary with data that significantly differs from natural images such as MRI. In addition, employing smaller versions of the model can be adequate for medical task, offering resource-saving benefits. Our codes are available at https://github.com/GuanghuiFU/medical_DINOv2_eval.