PyTorchKR Papers

최신 논문

총 11,126편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.14914

Trading via Selective Classification

A binary classifier that tries to predict if the price of an asset will increase or decrease naturally gives rise to a trading strategy that follows the prediction and thus always has a position in the market. Selective classification extends a binary or many-class classifier to allow it to abstain from making a prediction for certain inputs, thereby allowing a trade-off between the accuracy of the resulting selective classifier against coverage of the input feature space. Selective classifiers give rise to trading strategies that do not take a trading position when the classifier abstains. We investigate the application of binary and ternary selective classification to trading strategy design. For ternary classification, in addition to classes for the price going up or down, we include a third class that corresponds to relatively small price moves in either direction, and gives the classifier another way to avoid making a directional prediction. We use a walk-forward train-validate-test approach to evaluate and compare binary and ternary, selective and non-selective classifiers across several different feature sets based on four classification approaches: logistic regression, random forests, feed-forward, and recurrent neural networks. We then turn these classifiers into trading strategies for which we perform backtests on commodity futures markets. Our empirical results demonstrate the potential of selective classification for trading.

arXiv:2110.14731

Vision Transformer for Classification of Breast Ultrasound Images

Medical ultrasound (US) imaging has become a prominent modality for breast cancer imaging due to its ease-of-use, low-cost and safety. In the past decade, convolutional neural networks (CNNs) have emerged as the method of choice in vision applications and have shown excellent potential in automatic classification of US images. Despite their success, their restricted local receptive field limits their ability to learn global context information. Recently, Vision Transformer (ViT) designs that are based on self-attention between image patches have shown great potential to be an alternative to CNNs. In this study, for the first time, we utilize ViT to classify breast US images using different augmentation strategies. The results are provided as classification accuracy and Area Under the Curve (AUC) metrics, and the performance is compared with the state-of-the-art CNNs. The results indicate that the ViT models have comparable efficiency with or even better than the CNNs in classification of US breast images.

arXiv:2110.14215

Beyond Classification: Knowledge Distillation using Multi-Object Impressions

Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recently identified many scenarios where the training data may not be available due to data privacy or sensitivity concerns and have proposed solutions under this restrictive constraint for the classification task. Unlike existing works, we, for the first time, solve a much more challenging problem, i.e., "KD for object detection with zero knowledge about the training data and its statistics". Our proposed approach prepares pseudo-targets and synthesizes corresponding samples (termed as "Multi-Object Impressions"), using only the pretrained Faster RCNN Teacher network. We use this pseudo-dataset as a transfer set to conduct zero-shot KD for object detection. We demonstrate the efficacy of our proposed method through several ablations and extensive experiments on benchmark datasets like KITTI, Pascal and COCO. Our approach with no training samples, achieves a respectable mAP of 64.2% and 55.5% on the student with same and half capacity while performing distillation from a Resnet-18 Teacher of 73.3% mAP on KITTI.

arXiv:2110.14243공식 코드 · Papers with Code

Online Selective Classification with Limited Feedback

Motivated by applications to resource-limited and safety-critical domains, we study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. For example, this may model an adaptive decision to invoke more resources on this instance. Two salient aspects of the setting we consider are that the data may be non-realisable, due to which abstention may be a valid long-term action, and that feedback is only received when the learner abstains, which models the fact that reliable labels are only available when the resource intensive processing is invoked. Within this framework, we explore strategies that make few mistakes, while not abstaining too many times more than the best-in-hindsight error-free classifier from a given class. That is, the one that makes no mistakes, while abstaining the fewest number of times. We construct simple versioning-based schemes for any $\mu \in (0,1],$ that make most $T^\mu$ mistakes while incurring \smash{$\tilde{O}(T^{1-\mu})$} excess abstention against adaptive adversaries. We further show that this dependence on $T$ is tight, and provide illustrative experiments on realistic datasets.

arXiv:2110.14012공식 코드 · Papers with Code

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNN). Nonetheless, uncertainty estimation for non-independent node-level predictions is under-explored. In this work, we explore uncertainty quantification for node classification in three ways: (1) We derive three axioms explicitly characterizing the expected predictive uncertainty behavior in homophilic attributed graphs. (2) We propose a new model Graph Posterior Network (GPN) which explicitly performs Bayesian posterior updates for predictions on interdependent nodes. GPN provably obeys the proposed axioms. (3) We extensively evaluate GPN and a strong set of baselines on semi-supervised node classification including detection of anomalous features, and detection of left-out classes. GPN outperforms existing approaches for uncertainty estimation in the experiments.

arXiv:2110.13992

Leveraging Local Temporal Information for Multimodal Scene Classification

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level representations. In this paper, we propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames. This enables the model to understand the video at various granularities. We illustrate the performance of our models on the large scale YoutTube-8M data set on the task of video categorization and further analyze the results to showcase improvement.

arXiv:2110.13948공식 코드 · Papers with Code

Boosted CVaR Classification

Many modern machine learning tasks require models with high tail performance, i.e. high performance over the worst-off samples in the dataset. This problem has been widely studied in fields such as algorithmic fairness, class imbalance, and risk-sensitive decision making. A popular approach to maximize the model's tail performance is to minimize the CVaR (Conditional Value at Risk) loss, which computes the average risk over the tails of the loss. However, for classification tasks where models are evaluated by the zero-one loss, we show that if the classifiers are deterministic, then the minimizer of the average zero-one loss also minimizes the CVaR zero-one loss, suggesting that CVaR loss minimization is not helpful without additional assumptions. We circumvent this negative result by minimizing the CVaR loss over randomized classifiers, for which the minimizers of the average zero-one loss and the CVaR zero-one loss are no longer the same, so minimizing the latter can lead to better tail performance. To learn such randomized classifiers, we propose the Boosted CVaR Classification framework which is motivated by a direct relationship between CVaR and a classical boosting algorithm called LPBoost. Based on this framework, we design an algorithm called $\alpha$-AdaLPBoost. We empirically evaluate our proposed algorithm on four benchmark datasets and show that it achieves higher tail performance than deterministic model training methods.

arXiv:2110.14144공식 코드 · Papers with Code

Physically Explainable CNN for SAR Image Classification

Integrating the special electromagnetic characteristics of Synthetic Aperture Radar (SAR) in deep neural networks is essential in order to enhance the explainability and physics awareness of deep learning. In this paper, we first propose a novel physically explainable convolutional neural network for SAR image classification, namely physics guided and injected learning (PGIL). It comprises three parts: (1) explainable models (XM) to provide prior physics knowledge, (2) physics guided network (PGN) to encode the knowledge into physics-aware features, and (3) physics injected network (PIN) to adaptively introduce the physics-aware features into classification pipeline for label prediction. A hybrid Image-Physics SAR dataset format is proposed for evaluation, with both Sentinel-1 and Gaofen-3 SAR data being experimented. The results show that the proposed PGIL substantially improve the classification performance in case of limited labeled data compared with the counterpart data-driven CNN and other pre-training methods. Additionally, the physics explanations are discussed to indicate the interpretability and the physical consistency preserved in the predictions. We deem the proposed method would promote the development of physically explainable deep learning in SAR image interpretation field.

arXiv:2110.14131

Temporal Knowledge Distillation for On-device Audio Classification

Improving the performance of on-device audio classification models remains a challenge given the computational limits of the mobile environment. Many studies leverage knowledge distillation to boost predictive performance by transferring the knowledge from large models to on-device models. However, most lack a mechanism to distill the essence of the temporal information, which is crucial to audio classification tasks, or similar architecture is often required. In this paper, we propose a new knowledge distillation method designed to incorporate the temporal knowledge embedded in attention weights of large transformer-based models into on-device models. Our distillation method is applicable to various types of architectures, including the non-attention-based architectures such as CNNs or RNNs, while retaining the original network architecture during inference. Through extensive experiments on both an audio event detection dataset and a noisy keyword spotting dataset, we show that our proposed method improves the predictive performance across diverse on-device architectures.

arXiv:2110.13494

Meta-Learning for Multi-Label Few-Shot Classification

Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within a query (e.g., an image) by just observing a few supporting examples. In doing so, we first propose a benchmark for Few-Shot Learning (FSL) with multiple labels per sample. Next, we discuss and extend several solutions specifically designed to address the conventional and single-label FSL, to work in the multi-label regime. Lastly, we introduce a neural module to estimate the label count of a given sample by exploiting the relational inference. We will show empirically the benefit of the label count module, the label propagation algorithm, and the extensions of conventional FSL methods on three challenging datasets, namely MS-COCO, iMaterialist, and Open MIC. Overall, our thorough experiments suggest that the proposed label-propagation algorithm in conjunction with the neural label count module (NLC) shall be considered as the method of choice.

arXiv:2110.13859

Defensive Tensorization

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as factorized tensor layers. Tensor dropout is then applied in the latent subspace, therefore resulting in dense reconstructed weights, without the sparsity or perturbations typically induced by the randomization.Our approach can be readily integrated with any arbitrary neural architecture and combined with techniques like adversarial training. We empirically demonstrate the effectiveness of our approach on standard image classification benchmarks. We validate the versatility of our approach across domains and low-precision architectures by considering an audio classification task and binary networks. In all cases, we demonstrate improved performance compared to prior works.

arXiv:2110.13656

CLLD: Contrastive Learning with Label Distance for Text Classification

Existed pre-trained models have achieved state-of-the-art performance on various text classification tasks. These models have proven to be useful in learning universal language representations. However, the semantic discrepancy between similar texts cannot be effectively distinguished by advanced pre-trained models, which have a great influence on the performance of hard-to-distinguish classes. To address this problem, we propose a novel Contrastive Learning with Label Distance (CLLD) in this work. Inspired by recent advances in contrastive learning, we specifically design a classification method with label distance for learning contrastive classes. CLLD ensures the flexibility within the subtle differences that lead to different label assignments, and generates the distinct representations for each class having similarity simultaneously. Extensive experiments on public benchmarks and internal datasets demonstrate that our method improves the performance of pre-trained models on classification tasks. Importantly, our experiments suggest that the learned label distance relieve the adversarial nature of interclasses.

arXiv:2110.13652

A Precision Diagnostic Framework of Renal Cell Carcinoma on Whole-Slide Images using Deep Learning

Diagnostic pathology, which is the basis and gold standard of cancer diagnosis, provides essential information on the prognosis of the disease and vital evidence for clinical treatment. Tumor region detection, subtype and grade classification are the fundamental diagnostic indicators for renal cell carcinoma (RCC) in whole-slide images (WSIs). However, pathological diagnosis is subjective, differences in observation and diagnosis between pathologists is common in hospitals with inadequate diagnostic capacity. The main challenge for developing deep learning based RCC diagnostic system is the lack of large-scale datasets with precise annotations. In this work, we proposed a deep learning-based framework for analyzing histopathological images of patients with renal cell carcinoma, which has the potential to achieve pathologist-level accuracy in diagnosis. A deep convolutional neural network (InceptionV3) was trained on the high-quality annotated dataset of The Cancer Genome Atlas (TCGA) whole-slide histopathological image for accurate tumor area detection, classification of RCC subtypes, and ISUP grades classification of clear cell carcinoma subtypes. These results suggest that our framework can help pathologists in the detection of cancer region and classification of subtypes and grades, which could be applied to any cancer type, providing auxiliary diagnosis and promoting clinical consensus.

arXiv:2110.13082

An Evolutionary Correlation-aware Feature Selection Method for Classification Problems

The population-based optimization algorithms have provided promising results in feature selection problems. However, the main challenges are high time complexity. Moreover, the interaction between features is another big challenge in FS problems that directly affects the classification performance. In this paper, an estimation of distribution algorithm is proposed to meet three goals. Firstly, as an extension of EDA, the proposed method generates only two individuals in each iteration that compete based on a fitness function and evolve during the algorithm, based on our proposed update procedure. Secondly, we provide a guiding technique for determining the number of features for individuals in each iteration. As a result, the number of selected features of the final solution will be optimized during the evolution process. The two mentioned advantages can increase the convergence speed of the algorithm. Thirdly, as the main contribution of the paper, in addition to considering the importance of each feature alone, the proposed method can consider the interaction between features. Thus, it can deal with complementary features and consequently increase classification performance. To do this, we provide a conditional probability scheme that considers the joint probability distribution of selecting two features. The introduced probabilities successfully detect correlated features. Experimental results on a synthetic dataset with correlated features prove the performance of our proposed approach facing these types of features. Furthermore, the results on 13 real-world datasets obtained from the UCI repository show the superiority of the proposed method in comparison with some state-of-the-art approaches.

arXiv:2110.12870

Data-driven intrinsic localized mode detection and classification in one-dimensional crystal lattice model

In this work we propose Support Vector Machine classification algorithms to classify onedimensional crystal lattice waves from locally sampled data. Different learning datasets of particle displacements, momenta and energy density values are considered. Efficiency of the classification algorithms is further improved by two dimensionality reduction techniques: Principal Component Analysis and Locally Linear Embedding. Robustness of classifiers is investigated and demonstrated. Developed algorithms are successfully applied to detect localized intrinsic modes in three numerical simulations considering a case of two localized stationary breather solutions, a single stationary breather solution in noisy background and two mobile breather collision.

arXiv:2110.12035공식 코드 · Papers with Code

Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification

Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification. However, current GNNs are mostly built under the balanced data-splitting, which is inconsistent with many real-world networks where the number of training nodes can be extremely imbalanced among the classes. Thus, directly utilizing current GNNs on imbalanced data would generate coarse representations of nodes in minority classes and ultimately compromise the classification performance. This therefore portends the importance of developing effective GNNs for handling imbalanced graph data. In this work, we propose a novel Distance-wise Prototypical Graph Neural Network (DPGNN), which proposes a class prototype-driven training to balance the training loss between majority and minority classes and then leverages distance metric learning to differentiate the contributions of different dimensions of representations and fully encode the relative position of each node to each class prototype. Moreover, we design a new imbalanced label propagation mechanism to derive extra supervision from unlabeled nodes and employ self-supervised learning to smooth representations of adjacent nodes while separating inter-class prototypes. Comprehensive node classification experiments and parameter analysis on multiple networks are conducted and the proposed DPGNN almost always significantly outperforms all other baselines, which demonstrates its effectiveness in imbalanced node classification. The implementation of DPGNN is available at \url{https://github.com/YuWVandy/DPGNN}.

arXiv:2110.13006

Gradient-based Quadratic Multiform Separation

Classification as a supervised learning concept is an important content in machine learning. It aims at categorizing a set of data into classes. There are several commonly-used classification methods nowadays such as k-nearest neighbors, random forest, and support vector machine. Each of them has its own pros and cons, and none of them is invincible for all kinds of problems. In this thesis, we focus on Quadratic Multiform Separation (QMS), a classification method recently proposed by Michael Fan et al. (2019). Its fresh concept, rich mathematical structure, and innovative definition of loss function set it apart from the existing classification methods. Inspired by QMS, we propose utilizing a gradient-based optimization method, Adam, to obtain a classifier that minimizes the QMS-specific loss function. In addition, we provide suggestions regarding model tuning through explorations of the relationships between hyperparameters and accuracies. Our empirical result shows that QMS performs as good as most classification methods in terms of accuracy. Its superior performance is almost comparable to those of gradient boosting algorithms that win massive machine learning competitions.

arXiv:2110.12292

Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks

Federated learning enables many local devices to train a deep learning model jointly without sharing the local data. Currently, most of federated training schemes learns a global model by averaging the parameters of local models. However, most of these training schemes suffer from high communication cost resulted from transmitting full local model parameters. Moreover, directly averaging model parameters leads to a significant performance degradation, due to the class-imbalanced non-iid data on different devices. Especially for the real life federated learning tasks involving extreme classification, (1) communication becomes the main bottleneck since the model size increases proportionally to the number of output classes; (2) extreme classification (such as user recommendation) normally have extremely imbalanced classes and heterogeneous data on different devices. To overcome this problem, we propose federated multiple label hashing (FedMLH), which leverages label hashing to simultaneously reduce the model size (up to 3.40X decrease) with communication cost (up to 18.75X decrease) and achieves significant better accuracy (up to 35.5%} relative accuracy improvement) and faster convergence rate (up to 5.5X increase) for free on the federated extreme classification tasks compared to federated average algorithm.

arXiv:2110.12285

Generalized Resubstitution for Classification Error Estimation

We propose the family of generalized resubstitution classifier error estimators based on empirical measures. These error estimators are computationally efficient and do not require re-training of classifiers. The plain resubstitution error estimator corresponds to choosing the standard empirical measure. Other choices of empirical measure lead to bolstered, posterior-probability, Gaussian-process, and Bayesian error estimators; in addition, we propose bolstered posterior-probability error estimators as a new family of generalized resubstitution estimators. In the two-class case, we show that a generalized resubstitution estimator is consistent and asymptotically unbiased, regardless of the distribution of the features and label, if the corresponding generalized empirical measure converges uniformly to the standard empirical measure and the classification rule has a finite VC dimension. A generalized resubstitution estimator typically has hyperparameters that can be tuned to control its bias and variance, which adds flexibility. Numerical experiments with various classification rules trained on synthetic data assess the thefinite-sample performance of several representative generalized resubstitution error estimators. In addition, results of an image classification experiment using the LeNet-5 convolutional neural network and the MNIST data set demonstrate the potential of this class of error estimators in deep learning for computer vision.

arXiv:2110.13094

Gophormer: Ego-Graph Transformer for Node Classification

Transformers have achieved remarkable performance in a myriad of fields including natural language processing and computer vision. However, when it comes to the graph mining area, where graph neural network (GNN) has been the dominant paradigm, transformers haven't achieved competitive performance, especially on the node classification task. Existing graph transformer models typically adopt fully-connected attention mechanism on the whole input graph and thus suffer from severe scalability issues and are intractable to train in data insufficient cases. To alleviate these issues, we propose a novel Gophormer model which applies transformers on ego-graphs instead of full-graphs. Specifically, Node2Seq module is proposed to sample ego-graphs as the input of transformers, which alleviates the challenge of scalability and serves as an effective data augmentation technique to boost model performance. Moreover, different from the feature-based attention strategy in vanilla transformers, we propose a proximity-enhanced attention mechanism to capture the fine-grained structural bias. In order to handle the uncertainty introduced by the ego-graph sampling, we further propose a consistency regularization and a multi-sample inference strategy for stabilized training and testing, respectively. Extensive experiments on six benchmark datasets are conducted to demonstrate the superiority of Gophormer over existing graph transformers and popular GNNs, revealing the promising future of graph transformers.