PyTorchKR Papers

최신 논문

총 10,240편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2406.12031공식 코드 · Papers with Code

Large Scale Transfer Learning for Tabular Data via Language Modeling

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TabuLa-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, proposing methods for tabular data filtering and quality control. Using the resulting dataset, which comprises over 2.1B rows from over 4M unique tables, we fine-tune a Llama 3-8B large language model (LLM) for tabular data prediction (classification and binned regression) using a novel packing and attention scheme for tabular prediction. Through evaluation across a test suite of 329 datasets, we find that TabuLa-8B has zero-shot accuracy on unseen tables that is over 15 percentage points (pp) higher than random guessing, a feat that is not possible with existing state-of-the-art tabular prediction models (e.g. XGBoost, TabPFN). In the few-shot setting (1-32 shots), without any fine-tuning on the target datasets, TabuLa-8B is 5-15 pp more accurate than XGBoost and TabPFN models that are explicitly trained on equal, or even up to 16x more data. We release our model, code, and data along with the publication of this paper.

arXiv:2406.12769

Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video

We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. Our key insight is to use latent features drawn from a learnable prior distribution conditioned on the underlying particle states to capture the invisible and complex physical properties. To achieve this, we train a parametrized prior learner given visual observations to approximate the visual posterior of inverse graphics, and both the particle states and the visual posterior are obtained from a learned neural renderer. The converged prior learner is embedded in our probabilistic physics engine, allowing us to perform novel simulations on unseen geometries, boundaries, and dynamics without knowledge of the true physical parameters. We validate our model in three ways: (i) novel scene simulation with the learned visual-world physics, (ii) future prediction of the observed fluid dynamics, and (iii) supervised particle simulation. Our model demonstrates strong performance in all three tasks.

arXiv:2406.12723공식 코드 · Papers with Code

BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity

As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establish several benchmark tasks. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, geographical, and size information. We propose three benchmark experiments to demonstrate the impact of the multi-modal data types on the classification and clustering accuracy. First, we pretrain a masked language model on the DNA barcode sequences of the BIOSCAN-5M dataset, and demonstrate the impact of using this large reference library on species- and genus-level classification performance. Second, we propose a zero-shot transfer learning task applied to images and DNA barcodes to cluster feature embeddings obtained from self-supervised learning, to investigate whether meaningful clusters can be derived from these representation embeddings. Third, we benchmark multi-modality by performing contrastive learning on DNA barcodes, image data, and taxonomic information. This yields a general shared embedding space enabling taxonomic classification using multiple types of information and modalities. The code repository of the BIOSCAN-5M Insect dataset is available at https://github.com/bioscan-ml/BIOSCAN-5M.

arXiv:2406.12698

Online-Adaptive Anomaly Detection for Defect Identification in Aircraft Assembly

Anomaly detection deals with detecting deviations from established patterns within data. It has various applications like autonomous driving, predictive maintenance, and medical diagnosis. To improve anomaly detection accuracy, transfer learning can be applied to large, pre-trained models and adapt them to the specific application context. In this paper, we propose a novel framework for online-adaptive anomaly detection using transfer learning. The approach adapts to different environments by selecting visually similar training images and online fitting a normality model to EfficientNet features extracted from the training subset. Anomaly detection is then performed by computing the Mahalanobis distance between the normality model and the test image features. Different similarity measures (SIFT/FLANN, Cosine) and normality models (MVG, OCSVM) are employed and compared with each other. We evaluate the approach on different anomaly detection benchmarks and data collected in controlled laboratory settings. Experimental results showcase a detection accuracy exceeding 0.975, outperforming the state-of-the-art ET-NET approach.

arXiv:2406.12683

Spatial Sequence Attention Network for Schizophrenia Classification from Structural Brain MR Images

Schizophrenia is a debilitating, chronic mental disorder that significantly impacts an individual's cognitive abilities, behavior, and social interactions. It is characterized by subtle morphological changes in the brain, particularly in the gray matter. These changes are often imperceptible through manual observation, demanding an automated approach to diagnosis. This study introduces a deep learning methodology for the classification of individuals with Schizophrenia. We achieve this by implementing a diversified attention mechanism known as Spatial Sequence Attention (SSA) which is designed to extract and emphasize significant feature representations from structural MRI (sMRI). Initially, we employ the transfer learning paradigm by leveraging pre-trained DenseNet to extract initial feature maps from the final convolutional block which contains morphological alterations associated with Schizophrenia. These features are further processed by the proposed SSA to capture and emphasize intricate spatial interactions and relationships across volumes within the brain. Our experimental studies conducted on a clinical dataset have revealed that the proposed attention mechanism outperforms the existing Squeeze & Excitation Network for Schizophrenia classification.

arXiv:2406.10671공식 코드 · Papers with Code

Augmenting Biomedical Named Entity Recognition with General-domain Resources

Training a neural network-based biomedical named entity recognition (BioNER) model usually requires extensive and costly human annotations. While several studies have employed multi-task learning with multiple BioNER datasets to reduce human effort, this approach does not consistently yield performance improvements and may introduce label ambiguity in different biomedical corpora. We aim to tackle those challenges through transfer learning from easily accessible resources with fewer concept overlaps with biomedical datasets. We proposed GERBERA, a simple-yet-effective method that utilized general-domain NER datasets for training. We performed multi-task learning to train a pre-trained biomedical language model with both the target BioNER dataset and the general-domain dataset. Subsequently, we fine-tuned the models specifically for the BioNER dataset. We systematically evaluated GERBERA on five datasets of eight entity types, collectively consisting of 81,410 instances. Despite using fewer biomedical resources, our models demonstrated superior performance compared to baseline models trained with additional BioNER datasets. Specifically, our models consistently outperformed the baseline models in six out of eight entity types, achieving an average improvement of 0.9% over the best baseline performance across eight entities. Our method was especially effective in amplifying performance on BioNER datasets characterized by limited data, with a 4.7% improvement in F1 scores on the JNLPBA-RNA dataset. This study introduces a new training method that leverages cost-effective general-domain NER datasets to augment BioNER models. This approach significantly improves BioNER model performance, making it a valuable asset for scenarios with scarce or costly biomedical datasets.

arXiv:2406.10861

Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions

Federated Learning (FL) is a distributed and privacy-preserving machine learning paradigm that coordinates multiple clients to train a model while keeping the raw data localized. However, this traditional FL poses some challenges, including privacy risks, data heterogeneity, communication bottlenecks, and system heterogeneity issues. To tackle these challenges, knowledge distillation (KD) has been widely applied in FL since 2020. KD is a validated and efficacious model compression and enhancement algorithm. The core concept of KD involves facilitating knowledge transfer between models by exchanging logits at intermediate or output layers. These properties make KD an excellent solution for the long-lasting challenges in FL. Up to now, there have been few reviews that summarize and analyze the current trend and methods for how KD can be applied in FL efficiently. This article aims to provide a comprehensive survey of KD-based FL, focusing on addressing the above challenges. First, we provide an overview of KD-based FL, including its motivation, basics, taxonomy, and a comparison with traditional FL and where KD should execute. We also analyze the critical factors in KD-based FL in the appendix, including teachers, knowledge, data, and methods. We discuss how KD can address the challenges in FL, including privacy protection, data heterogeneity, communication efficiency, and personalization. Finally, we discuss the challenges facing KD-based FL algorithms and future research directions. We hope this survey can provide insights and guidance for researchers and practitioners in the FL area.

arXiv:2406.10798

Federated Learning Optimization: A Comparative Study of Data and Model Exchange Strategies in Dynamic Networks

The promise and proliferation of large-scale dynamic federated learning gives rise to a prominent open question - is it prudent to share data or model across nodes, if efficiency of transmission and fast knowledge transfer are the prime objectives. This work investigates exactly that. Specifically, we study the choices of exchanging raw data, synthetic data, or (partial) model updates among devices. The implications of these strategies in the context of foundational models are also examined in detail. Accordingly, we obtain key insights about optimal data and model exchange mechanisms considering various environments with different data distributions and dynamic device and network connections. Across various scenarios that we considered, time-limited knowledge transfer efficiency can differ by up to 9.08\%, thus highlighting the importance of this work.

arXiv:2406.11048

Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modality

Federated learning (FL) has obtained tremendous progress in providing collaborative training solutions for distributed data silos with privacy guarantees. However, few existing works explore a more realistic scenario where the clients hold multiple data modalities. In this paper, we aim to solve a novel challenge in multi-modal federated learning (MFL) -- modality missing -- the clients may lose part of the modalities in their local data sets. To tackle the problems, we propose a novel multi-modal federated learning method, Federated Multi-modal contrastiVe training with Pre-trained completion (FedMVP), which integrates the large-scale pre-trained models to enhance the federated training. In the proposed FedMVP framework, each client deploys a large-scale pre-trained model with frozen parameters for modality completion and representation knowledge transfer, enabling efficient and robust local training. On the server side, we utilize generated data to uniformly measure the representation similarity among the uploaded client models and construct a graph perspective to aggregate them according to their importance in the system. We demonstrate that the model achieves superior performance over two real-world image-text classification datasets and is robust to the performance degradation caused by missing modality.

arXiv:2406.10501

Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition

Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner, leading to sub-optimal solutions. To this end, we propose a simple yet effective self-supervised contrastive learning framework to excavate rich context via spatial-temporal consistency from two distinct perspectives and learn instance discriminative representation for sign language recognition. On one hand, since the semantics of sign language are expressed by the cooperation of fine-grained hands and coarse-grained trunks, we utilize both granularity information and encode them into latent spaces. The consistency between hand and trunk features is constrained to encourage learning consistent representation of instance samples. On the other hand, inspired by the complementary property of motion and joint modalities, we first introduce first-order motion information into sign language modeling. Additionally, we further bridge the interaction between the embedding spaces of both modalities, facilitating bidirectional knowledge transfer to enhance sign language representation. Our method is evaluated with extensive experiments on four public benchmarks, and achieves new state-of-the-art performance with a notable margin. The source code is publicly available at https://github.com/sakura/Code.

arXiv:2406.11808

Faces of Experimental Pain: Transferability of Deep Learned Heat Pain Features to Electrical Pain

The limited size of pain datasets are a challenge in developing robust deep learning models for pain recognition. Transfer learning approaches are often employed in these scenarios. In this study, we investigate whether deep learned feature representation for one type of experimentally induced pain can be transferred to another. Participating in the AI4Pain challenge, our goal is to classify three levels of pain (No-Pain, Low-Pain, High-Pain). The challenge dataset contains data collected from 65 participants undergoing varying intensities of electrical pain. We utilize the video recording from the dataset to investigate the transferability of deep learned heat pain model to electrical pain. In our proposed approach, we leverage an existing heat pain convolutional neural network (CNN) - trained on BioVid dataset - as a feature extractor. The images from the challenge dataset are inputted to the pre-trained heat pain CNN to obtain feature vectors. These feature vectors are used to train two machine learning models: a simple feed-forward neural network and a long short-term memory (LSTM) network. Our approach was tested using the dataset's predefined training, validation, and testing splits. Our models outperformed the baseline of the challenge on both the validation and tests sets, highlighting the potential of models trained on other pain datasets for reliable feature extraction.

arXiv:2406.10815공식 코드 · Papers with Code

On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning

Supervised contrastive representation learning has been shown to be effective in various transfer learning scenarios. However, while asymmetric non-contrastive learning (ANCL) often outperforms its contrastive learning counterpart in self-supervised representation learning, the extension of ANCL to supervised scenarios is less explored. To bridge the gap, we study ANCL for supervised representation learning, coined SupSiam and SupBYOL, leveraging labels in ANCL to achieve better representations. The proposed supervised ANCL framework improves representation learning while avoiding collapse. Our analysis reveals that providing supervision to ANCL reduces intra-class variance, and the contribution of supervision should be adjusted to achieve the best performance. Experiments demonstrate the superiority of supervised ANCL across various datasets and tasks. The code is available at: https://github.com/JH-Oh-23/Sup-ANCL.

arXiv:2406.10785공식 코드 · Papers with Code

ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation

In this paper, we introduce \textbf{Share}d \textbf{Lo}w \textbf{R}ank \textbf{A}daptation (ShareLoRA), a Large Language Model (LLM) fine-tuning technique that balances parameter efficiency, adaptability, and robustness without compromising performance. By strategically sharing the low-rank weight matrices across different layers, ShareLoRA achieves 44\% to 96\% reduction in trainable parameters compared to standard LoRA, alongside a substantial decrease in memory overhead. This efficiency gain scales with model size, making ShareLoRA particularly advantageous for resource-constrained environments. Importantly, ShareLoRA not only maintains model performance but also exhibits robustness in both classification and generation tasks across diverse models, including RoBERTa, GPT-2, and LLaMA series (1, 2, and 3). It consistently outperforms LoRA in zero-shot, few-shot, and continual fine-tuning scenarios, achieving up to 1.2\% average accuracy improvement, and enhanced generalization across domains. In continual learning settings, ShareLoRA achieves 1.2\% higher accuracy on GSM8K, 0.6\% on HumanEval, and 0.5\% on both MMLU and MMLU-Pro. Our results demonstrate that ShareLoRA supports high-quality fine-tuning while offering strong generalization and continual adaptation across various model scales and diverse tasks.

arXiv:2406.10517

ADSNet: Cross-Domain LTV Prediction with an Adaptive Siamese Network in Advertising

Advertising platforms have evolved in estimating Lifetime Value (LTV) to better align with advertisers' true performance metric. However, the sparsity of real-world LTV data presents a significant challenge to LTV predictive model(i.e., pLTV), severely limiting the their capabilities. Therefore, we propose to utilize external data, in addition to the internal data of advertising platform, to expand the size of purchase samples and enhance the LTV prediction model of the advertising platform. To tackle the issue of data distribution shift between internal and external platforms, we introduce an Adaptive Difference Siamese Network (ADSNet), which employs cross-domain transfer learning to prevent negative transfer. Specifically, ADSNet is designed to learn information that is beneficial to the target domain. We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer. Additionally, we also design a Domain Adaptation Module as a bridge to connect different domains, reduce the distribution distance between them, and enhance the consistency of representation space distribution. We conduct extensive offline experiments and online A/B tests on a real advertising platform. Our proposed ADSNet method outperforms other methods, improving GINI by 2$\%$. The ablation study highlights the importance of the gain evaluation strategy in negative gain sample rejection and improving model performance. Additionally, ADSNet significantly improves long-tail prediction. The online A/B tests confirm ADSNet's efficacy, increasing online LTV by 3.47$\%$ and GMV by 3.89$\%$.

arXiv:2406.11087

DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models

Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in terms of resource consumption. This substantial size places a heavy load on memory resources, raising considerable practical concerns. In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy. DP-MemArc incorporates side network or reversible network designs to support a variety of differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves about 2.5 times in memory optimization but also ensures robust privacy protection, keeping user data secure and confidential. Extensive experiments have demonstrated that DP-MemArc effectively provides differential privacy-efficient fine-tuning across different task scenarios.

arXiv:2406.11068

A Unified View of Abstract Visual Reasoning Problems

The field of Abstract Visual Reasoning (AVR) encompasses a wide range of problems, many of which are inspired by human IQ tests. The variety of AVR tasks has resulted in state-of-the-art AVR methods being task-specific approaches. Furthermore, contemporary methods consider each AVR problem instance not as a whole, but in the form of a set of individual panels with particular locations and roles (context vs. answer panels) pre-assigned according to the task-specific arrangements. While these highly specialized approaches have recently led to significant progress in solving particular AVR tasks, considering each task in isolation hinders the development of universal learning systems in this domain. In this paper, we introduce a unified view of AVR tasks, where each problem instance is rendered as a single image, with no a priori assumptions about the number of panels, their location, or role. The main advantage of the proposed unified view is the ability to develop universal learning models applicable to various AVR tasks. What is more, the proposed approach inherently facilitates transfer learning in the AVR domain, as various types of problems share a common representation. The experiments conducted on four AVR datasets with Raven's Progressive Matrices and Visual Analogy Problems, and one real-world visual analogy dataset show that the proposed unified representation of AVR tasks poses a challenge to state-of-the-art Deep Learning (DL) AVR models and, more broadly, contemporary DL image recognition methods. In order to address this challenge, we introduce the Unified Model for Abstract Visual Reasoning (UMAVR) capable of dealing with various types of AVR problems in a unified manner. UMAVR outperforms existing AVR methods in selected single-task learning experiments, and demonstrates effective knowledge reuse in transfer learning and curriculum learning setups.

arXiv:2406.11061

A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning

We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a recognized benchmark task for assessing AVR abilities. Two knowledge transfer scenarios referring to the I-RAVEN dataset are investigated. Firstly, inspired by generalization assessment capabilities of the PGM dataset and popularity of I-RAVEN, we introduce Attributeless-I-RAVEN (A-I-RAVEN), a benchmark with 10 generalization regimes that allow to systematically test generalization of abstract rules applied to held-out attributes at various levels of complexity (primary and extended regimes). In contrast to PGM, A-I-RAVEN features compositionality, a variety of figure configurations, and does not require substantial computational resources. Secondly, we construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns, facilitating assessment of progressive knowledge acquisition in transfer learning setting. We evaluate 13 strong models from the AVR literature on the introduced datasets, revealing their specific shortcomings in generalization and knowledge transfer.

arXiv:2406.11023

Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data

One of the most significant obstacles in bearing fault diagnosis is a lack of labeled data for various fault types. Also, sensor-acquired data frequently lack labels and have a large amount of missing data. This paper tackles these issues by presenting the PTPAI method, which uses a physics-informed deep learning-based technique to generate synthetic labeled data. Labeled synthetic data makes up the source domain, whereas unlabeled data with missing data is present in the target domain. Consequently, imbalanced class problems and partial-set fault diagnosis hurdles emerge. To address these challenges, the RF-Mixup approach is used to handle imbalanced classes. As domain adaptation strategies, the MK-MMSD and CDAN are employed to mitigate the disparity in distribution between synthetic and actual data. Furthermore, the partial-set challenge is tackled by applying weighting methods at the class and instance levels. Experimental outcomes on the CWRU and JNU datasets indicate that the proposed approach effectively addresses these problems.

arXiv:2406.10973

ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts

Parameter-efficient fine-tuning (PEFT) techniques such as low-rank adaptation (LoRA) can effectively adapt large pre-trained foundation models to downstream tasks using only a small fraction (0.1%-10%) of the original trainable weights. An under-explored question of PEFT is in extending the pre-training phase without supervised labels; that is, can we adapt a pre-trained foundation model to a new domain via efficient self-supervised pre-training on this new domain? In this work, we introduce ExPLoRA, a highly effective technique to improve transfer learning of pre-trained vision transformers (ViTs) under domain shifts. Initializing a ViT with pre-trained weights on large, natural-image datasets such as from DinoV2 or MAE, ExPLoRA continues the unsupervised pre-training objective on a new domain, unfreezing 1-2 pre-trained ViT blocks and tuning all other layers with LoRA. We then fine-tune the resulting model only with LoRA on this new domain for supervised learning. Our experiments demonstrate state-of-the-art results on satellite imagery, even outperforming fully pre-training and fine-tuning ViTs. Using the DinoV2 training objective, we demonstrate up to 7.5% improvement in linear probing top-1 accuracy on downstream tasks while using <10% of the number of parameters that are used in prior fully-tuned state-of-the art approaches. Our ablation studies confirm the efficacy of our approach over other baselines, including PEFT and unfreezing more ViT blocks. Code is available on the project website: https://samar-khanna.github.io/ExPLoRA/

arXiv:2406.09638

RASPNet: A Benchmark Dataset for Radar Adaptive Signal Processing Applications

We present a large-scale dataset for radar adaptive signal processing (RASP) applications to support the development of data-driven models within the adaptive radar community. The dataset, RASPNet, exceeds 16 TB in size and comprises 100 realistic scenarios compiled over a variety of topographies and land types from across the contiguous United States. For each scenario, RASPNet consists of 10,000 clutter realizations from an airborne radar setting, which can be used to benchmark radar and complex-valued learning algorithms. RASPNet intends to fill a prominent gap in the availability of a large-scale, realistic dataset that standardizes the evaluation of adaptive radar processing techniques and complex-valued neural networks. We outline its construction, organization, and several applications, including a transfer learning example to demonstrate how RASPNet can be used for realistic adaptive radar processing scenarios.