PyTorchKR Papers

최신 논문

총 10,240편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2302.07335

Intelligent Model Update Strategy for Sequential Recommendation

Modern online platforms are increasingly employing recommendation systems to address information overload and improve user engagement. There is an evolving paradigm in this research field that recommendation network learning occurs both on the cloud and on edges with knowledge transfer in between (i.e., edge-cloud collaboration). Recent works push this field further by enabling edge-specific context-aware adaptivity, where model parameters are updated in real-time based on incoming on-edge data. However, we argue that frequent data exchanges between the cloud and edges often lead to inefficiency and waste of communication/computation resources, as considerable parameter updates might be redundant. To investigate this problem, we introduce Intelligent Edge-Cloud Parameter Request Model, abbreviated as IntellectReq. IntellectReq is designed to operate on edge, evaluating the cost-benefit landscape of parameter requests with minimal computation and communication overhead. We formulate this as a novel learning task, aimed at the detection of out-of-distribution data, thereby fine-tuning adaptive communication strategies. Further, we employ statistical mapping techniques to convert real-time user behavior into a normal distribution, thereby employing multi-sample outputs to quantify the model's uncertainty and thus its generalization capabilities. Rigorous empirical validation on four widely-adopted benchmarks evaluates our approach, evidencing a marked improvement in the efficiency and generalizability of edge-cloud collaborative and dynamic recommendation systems.

arXiv:2302.07350

Graph schemas as abstractions for transfer learning, inference, and planning

Transferring latent structure from one environment or problem to another is a mechanism by which humans and animals generalize with very little data. Inspired by cognitive and neurobiological insights, we propose graph schemas as a mechanism of abstraction for transfer learning. Graph schemas start with latent graph learning where perceptually aliased observations are disambiguated in the latent space using contextual information. Latent graph learning is also emerging as a new computational model of the hippocampus to explain map learning and transitive inference. Our insight is that a latent graph can be treated as a flexible template -- a schema -- that models concepts and behaviors, with slots that bind groups of latent nodes to the specific observations or groundings. By treating learned latent graphs (schemas) as prior knowledge, new environments can be quickly learned as compositions of schemas and their newly learned bindings. We evaluate graph schemas on two previously published challenging tasks: the memory & planning game and one-shot StreetLearn, which are designed to test rapid task solving in novel environments. Graph schemas can be learned in far fewer episodes than previous baselines, and can model and plan in a few steps in novel variations of these tasks. We also demonstrate learning, matching, and reusing graph schemas in more challenging 2D and 3D environments with extensive perceptual aliasing and size variations, and show how different schemas can be composed to model larger and more complex environments. To summarize, our main contribution is a unified system, inspired and grounded in cognitive science, that facilitates rapid transfer learning of new environments using schemas via map-induction and composition that handles perceptual aliasing.

arXiv:2302.06598

Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning

Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their decision making process. TracIn (Pruthi et al., 2020) is one such gradient-based method which explains model inferences based on the influence of training examples. In this paper, we explore the use of TracIn to improve model performance in the parameter-efficient tuning (PET) setting. We develop conversational safety classifiers via the prompt-tuning PET method and show how the unique characteristics of the PET regime enable TracIn to identify the cause for certain misclassifications by LLMs. We develop a new methodology for using gradient-based explainability techniques to improve model performance, G-BAIR: gradient-based automated iterative recovery. We show that G-BAIR can recover LLM performance on benchmarks after manually corrupting training labels. This suggests that influence methods like TracIn can be used to automatically perform data cleaning, and introduces the potential for interactive debugging and relabeling for PET-based transfer learning methods.

arXiv:2302.05702

Cross-center Early Sepsis Recognition by Medical Knowledge Guided Collaborative Learning for Data-scarce Hospitals

There are significant regional inequities in health resources around the world. It has become one of the most focused topics to improve health services for data-scarce hospitals and promote health equity through knowledge sharing among medical institutions. Because electronic medical records (EMRs) contain sensitive personal information, privacy protection is unavoidable and essential for multi-hospital collaboration. In this paper, for a common disease in ICU patients, sepsis, we propose a novel cross-center collaborative learning framework guided by medical knowledge, SofaNet, to achieve early recognition of this disease. The Sepsis-3 guideline, published in 2016, defines that sepsis can be diagnosed by satisfying both suspicion of infection and Sequential Organ Failure Assessment (SOFA) greater than or equal to 2. Based on this knowledge, SofaNet adopts a multi-channel GRU structure to predict SOFA values of different systems, which can be seen as an auxiliary task to generate better health status representations for sepsis recognition. Moreover, we only achieve feature distribution alignment in the hidden space during cross-center collaborative learning, which ensures secure and compliant knowledge transfer without raw data exchange. Extensive experiments on two open clinical datasets, MIMIC-III and Challenge, demonstrate that SofaNet can benefit early sepsis recognition when hospitals only have limited EMRs.

arXiv:2302.05675

Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks

Collaboration between healthcare institutions can significantly lessen the imbalance in medical resources across various geographic areas. However, directly sharing diagnostic information between institutions is typically not permitted due to the protection of patients' highly sensitive privacy. As a novel privacy-preserving machine learning paradigm, federated learning (FL) makes it possible to maximize the data utility among multiple medical institutions. These feature-enrichment FL techniques are referred to as vertical FL (VFL). Traditional VFL can only benefit multi-parties' shared samples, which strongly restricts its application scope. In order to improve the information-sharing capability and innovation of various healthcare-related institutions, and then to establish a next-generation open medical collaboration network, we propose a unified framework for vertical federated knowledge transfer mechanism (VFedTrans) based on a novel cross-hospital representation distillation component. Specifically, our framework includes three steps. First, shared samples' federated representations are extracted by collaboratively modeling multi-parties' joint features with current efficient vertical federated representation learning methods. Second, for each hospital, we learn a local-representation-distilled module, which can transfer the knowledge from shared samples' federated representations to enrich local samples' representations. Finally, each hospital can leverage local samples' representations enriched by the distillation module to boost arbitrary downstream machine learning tasks. The experiments on real-life medical datasets verify the knowledge transfer effectiveness of our framework.

arXiv:2302.06433

Label-efficient Time Series Representation Learning: A Review

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semi-supervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross-domain, based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field.

arXiv:2302.06120공식 코드 · Papers with Code

Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task

RNA, whose functionality is largely determined by its structure, plays an important role in many biological activities. The prediction of pairwise structural proximity between each nucleotide of an RNA sequence can characterize the structural information of the RNA. Historically, this problem has been tackled by machine learning models using expert-engineered features and trained on scarce labeled datasets. Here, we find that the knowledge learned by a protein-coevolution Transformer-based deep neural network can be transferred to the RNA contact prediction task. As protein datasets are orders of magnitude larger than those for RNA contact prediction, our findings and the subsequent framework greatly reduce the data scarcity bottleneck. Experiments confirm that RNA contact prediction through transfer learning using a publicly available protein model is greatly improved. Our findings indicate that the learned structural patterns of proteins can be transferred to RNAs, opening up potential new avenues for research.

arXiv:2302.06605공식 코드 · Papers with Code

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 6 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, and VQA) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter.

arXiv:2302.05927

Transfer Learning for Bayesian Optimization: A Survey

A wide spectrum of design and decision problems, including parameter tuning, A/B testing and drug design, intrinsically are instances of black-box optimization. Bayesian optimization (BO) is a powerful tool that models and optimizes such expensive "black-box" functions. However, at the beginning of optimization, vanilla Bayesian optimization methods often suffer from slow convergence issue due to inaccurate modeling based on few trials. To address this issue, researchers in the BO community propose to incorporate the spirit of transfer learning to accelerate optimization process, which could borrow strength from the past tasks (source tasks) to accelerate the current optimization problem (target task). This survey paper first summarizes transfer learning methods for Bayesian optimization from four perspectives: initial points design, search space design, surrogate model, and acquisition function. Then it highlights its methodological aspects and technical details for each approach. Finally, it showcases a wide range of applications and proposes promising future directions.

arXiv:2302.06548공식 코드 · Papers with Code

Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning

Tomorrow's robots will need to distinguish useful information from noise when performing different tasks. A household robot for instance may continuously receive a plethora of information about the home, but needs to focus on just a small subset to successfully execute its current chore. Filtering distracting inputs that contain irrelevant data has received little attention in the reinforcement learning literature. To start resolving this, we formulate a problem setting in reinforcement learning called the $\textit{extremely noisy environment}$ (ENE), where up to $99\%$ of the input features are pure noise. Agents need to detect which features provide task-relevant information about the state of the environment. Consequently, we propose a new method termed $\textit{Automatic Noise Filtering}$ (ANF), which uses the principles of dynamic sparse training in synergy with various deep reinforcement learning algorithms. The sparse input layer learns to focus its connectivity on task-relevant features, such that ANF-SAC and ANF-TD3 outperform standard SAC and TD3 by a large margin, while using up to $95\%$ fewer weights. Furthermore, we devise a transfer learning setting for ENEs, by permuting all features of the environment after 1M timesteps to simulate the fact that other information sources can become relevant as the world evolves. Again, ANF surpasses the baselines in final performance and sample complexity. Our code is available at https://github.com/bramgrooten/automatic-noise-filtering

arXiv:2302.05990공식 코드 · Papers with Code

Exploiting Graph Structured Cross-Domain Representation for Multi-Domain Recommendation

Multi-domain recommender systems benefit from cross-domain representation learning and positive knowledge transfer. Both can be achieved by introducing a specific modeling of input data (i.e. disjoint history) or trying dedicated training regimes. At the same time, treating domains as separate input sources becomes a limitation as it does not capture the interplay that naturally exists between domains. In this work, we efficiently learn multi-domain representation of sequential users' interactions using graph neural networks. We use temporal intra- and inter-domain interactions as contextual information for our method called MAGRec (short for Multi-domAin Graph-based Recommender). To better capture all relations in a multi-domain setting, we learn two graph-based sequential representations simultaneously: domain-guided for recent user interest, and general for long-term interest. This approach helps to mitigate the negative knowledge transfer problem from multiple domains and improve overall representation. We perform experiments on publicly available datasets in different scenarios where MAGRec consistently outperforms state-of-the-art methods. Furthermore, we provide an ablation study and discuss further extensions of our method.

arXiv:2302.05195

Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime

Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality. However, the lack of trained cytopathologists hinders its widespread implementation in low-resource settings. Deep learning-based telecytology diagnosis emerges as an appealing alternative, but it requires the collection of large annotated training datasets, which is costly and time-consuming. In this paper, we demonstrate that the abundance of unlabeled images that can be extracted from Pap smear test whole slide images presents a fertile ground for self-supervised learning methods, yielding performance improvements relative to readily available pre-trained models for various downstream tasks. In particular, we propose \textbf{C}ervical \textbf{C}ell \textbf{C}opy-\textbf{P}asting ($\texttt{C}^{3}\texttt{P}$) as an effective augmentation method, which enables knowledge transfer from open-source and labeled single-cell datasets to unlabeled tiles. Not only does $\texttt{C}^{3}\texttt{P}$ outperforms naive transfer from single-cell images, but we also demonstrate its advantageous integration into multiple instance learning methods. Importantly, all our experiments are conducted on our introduced \textit{in-house} dataset comprising liquid-based cytology Pap smear images obtained using low-cost technologies. This aligns with our objective of leveraging deep learning-based telecytology for diagnosis in low-resource settings.

arXiv:2302.05105

Text recognition on images using pre-trained CNN

A text on an image often stores important information and directly carries high level semantics, makes it as important source of information and become a very active research topic. Many studies have shown that the use of CNN-based neural networks is quite effective and accurate for image classification which is the basis of text recognition. It can also be more enhanced by using transfer learning from pre-trained model trained on ImageNet dataset as an initial weight. In this research, the recognition is trained by using Chars74K dataset and the best model results then tested on some samples of IIIT-5K-Dataset. The research results showed that the best accuracy is the model that trained using VGG-16 architecture applied with image transformation of rotation 15{\deg}, image scale of 0.9, and the application of gaussian blur effect. The research model has an accuracy of 97.94% for validation data, 98.16% for test data, and 95.62% for the test data from IIIT-5K-Dataset. Based on these results, it can be concluded that pre-trained CNN can produce good accuracy for text recognition, and the model architecture that used in this study can be used as reference material in the development of text detection systems in the future

arXiv:2302.04954

Mixed formulation of physics-informed neural networks for thermo-mechanically coupled systems and heterogeneous domains

Physics-informed neural networks (PINNs) are a new tool for solving boundary value problems by defining loss functions of neural networks based on governing equations, boundary conditions, and initial conditions. Recent investigations have shown that when designing loss functions for many engineering problems, using first-order derivatives and combining equations from both strong and weak forms can lead to much better accuracy, especially when there are heterogeneity and variable jumps in the domain. This new approach is called the mixed formulation for PINNs, which takes ideas from the mixed finite element method. In this method, the PDE is reformulated as a system of equations where the primary unknowns are the fluxes or gradients of the solution, and the secondary unknowns are the solution itself. In this work, we propose applying the mixed formulation to solve multi-physical problems, specifically a stationary thermo-mechanically coupled system of equations. Additionally, we discuss both sequential and fully coupled unsupervised training and compare their accuracy and computational cost. To improve the accuracy of the network, we incorporate hard boundary constraints to ensure valid predictions. We then investigate how different optimizers and architectures affect accuracy and efficiency. Finally, we introduce a simple approach for parametric learning that is similar to transfer learning. This approach combines data and physics to address the limitations of PINNs regarding computational cost and improves the network's ability to predict the response of the system for unseen cases. The outcomes of this work will be useful for many other engineering applications where deep learning is employed on multiple coupled systems of equations for fast and reliable computations.

arXiv:2302.05441

Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features

Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts. In some situations, target data labels may be expensive to obtain, so we may only have access to a limited number of target data points. To make the most of a very small target dataset, we propose a lightweight, sample-efficient approach that learns a diverse set of features and adapts to a target distribution by interpolating these features. Our approach, Project and Probe (Pro$^2$), first learns a linear projection that maps a pre-trained embedding onto orthogonal directions while being predictive of labels in the source dataset. The goal of this step is to learn a variety of predictive features, so that at least some of them remain useful after distribution shift. Pro$^2$ then learns a linear classifier on top of these projected features using a small target dataset. Theoretically, we find that Pro$^2$ results in more sample-efficient generalization by inducing a favorable bias-variance tradeoff. Our experiments on four datasets, with multiple distribution shift settings for each, show that Pro$^2$ improves performance by 5-15% when given limited target data compared to prior methods such as standard linear probing.

논문 ID: document/9698904

Enhanced dynamic sign language recognition using slowfast networks

In this paper, we use the SlowFast Networks developed by the Facebook research team to enhance the accuracy of dynamic sign language recognition. Firstly, we prepared the Word-Level American Sign Language (WLASL) dataset so each sign can be considered an action. We used the pre-trained SLOWFAST_8×8_R50 model provided on the official PySlowFast Github repository to initialize the weights of our model and fine-tune using the WLASL dataset and performed a parameter sweeping to fit the Dynamic Sign Language Recognition task. Through this transfer learning approach, we introduced a new state-of-the-art accuracy on the WLASL300 (300 words e.g., 300 classes) dataset with an improvement of 23.2 % top-1 accuracy compared to the previous state-of-the-art introduced in the WLASL paper using an I3D model. The top-1 accuracy was improved from 56.14% to 79.34% and the top-5 accuracy from 79.94% to 90.31%.

arXiv:2302.04917

ChemVise: Maximizing Out-of-Distribution Chemical Detection with the Novel Application of Zero-Shot Learning

Accurate chemical sensors are vital in medical, military, and home safety applications. Training machine learning models to be accurate on real world chemical sensor data requires performing many diverse, costly experiments in controlled laboratory settings to create a data set. In practice even expensive, large data sets may be insufficient for generalization of a trained model to a real-world testing distribution. Rather than perform greater numbers of experiments requiring exhaustive mixtures of chemical analytes, this research proposes learning approximations of complex exposures from training sets of simple ones by using single-analyte exposure signals as building blocks of a multiple-analyte space. We demonstrate this approach to synthetic sensor responses surprisingly improves the detection of out-of-distribution obscured chemical analytes. Further, we pair these synthetic signals to targets in an information-dense representation space utilizing a large corpus of chemistry knowledge. Through utilization of a semantically meaningful analyte representation spaces along with synthetic targets we achieve rapid analyte classification in the presence of obscurants without corresponding obscured-analyte training data. Transfer learning for supervised learning with molecular representations makes assumptions about the input data. Instead, we borrow from the natural language and natural image processing literature for a novel approach to chemical sensor signal classification using molecular semantics for arbitrary chemical sensor hardware designs.

arXiv:2302.04870공식 코드 · Papers with Code

Offsite-Tuning: Transfer Learning without Full Model

Transfer learning is important for foundation models to adapt to downstream tasks. However, many foundation models are proprietary, so users must share their data with model owners to fine-tune the models, which is costly and raise privacy concerns. Moreover, fine-tuning large foundation models is computation-intensive and impractical for most downstream users. In this paper, we propose Offsite-Tuning, a privacy-preserving and efficient transfer learning framework that can adapt billion-parameter foundation models to downstream data without access to the full model. In offsite-tuning, the model owner sends a light-weight adapter and a lossy compressed emulator to the data owner, who then fine-tunes the adapter on the downstream data with the emulator's assistance. The fine-tuned adapter is then returned to the model owner, who plugs it into the full model to create an adapted foundation model. Offsite-tuning preserves both parties' privacy and is computationally more efficient than the existing fine-tuning methods that require access to the full model weights. We demonstrate the effectiveness of offsite-tuning on various large language and vision foundation models. Offsite-tuning can achieve comparable accuracy as full model fine-tuning while being privacy-preserving and efficient, achieving 6.5x speedup and 5.6x memory reduction. Code is available at https://github.com/mit-han-lab/offsite-tuning.

arXiv:2302.04852공식 코드 · Papers with Code

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks

We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and common layer types (e.g., convolutional or linear). We provide a fast vectorized implementation on commodity CPUs, and show that it can yield speedups in end-to-end runtime experiments, both in transfer learning using already-sparsified networks, and in training sparse networks from scratch. Thus, our results provide the first support for sparse training on commodity hardware.

arXiv:2302.04527공식 코드 · Papers with Code

Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer

The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural Networks (CNNs) in computer vision, many researchers developed CNN-based algorithms to recognize distracted driving from a dashcam and warn the driver against unsafe behaviors. However, current models have too many parameters, which is unfeasible for vehicle-mounted computing. This work proposes a novel knowledge-distillation-based framework to solve this problem. The proposed framework first constructs a high-performance teacher network by progressively strengthening the robustness to illumination changes from shallow to deep layers of a CNN. Then, the teacher network is used to guide the architecture searching process of a student network through knowledge distillation. After that, we use the teacher network again to transfer knowledge to the student network by knowledge distillation. Experimental results on the Statefarm Distracted Driver Detection Dataset and AUC Distracted Driver Dataset show that the proposed approach is highly effective for recognizing distracted driving behaviors from photos: (1) the teacher network's accuracy surpasses the previous best accuracy; (2) the student network achieves very high accuracy with only 0.42M parameters (around 55% of the previous most lightweight model). Furthermore, the student network architecture can be extended to a spatial-temporal 3D CNN for recognizing distracted driving from video clips. The 3D student network largely surpasses the previous best accuracy with only 2.03M parameters on the Drive&Act Dataset. The source code is available at https://github.com/Dichao-Liu/Lightweight_Distracted_Driver_Recognition_with_Distillation-Based_NAS_and_Knowledge_Transfer.