PyTorchKR Papers

최신 논문

총 264편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2307.05104공식 코드 · Papers with Code

A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI

Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.

arXiv:2306.05501공식 코드 · Papers with Code

Robust Explainer Recommendation for Time Series Classification

Time series classification is a task which deals with temporal sequences, a prevalent data type common in domains such as human activity recognition, sports analytics and general sensing. In this area, interest in explainability has been growing as explanation is key to understand the data and the model better. Recently, a great variety of techniques have been proposed and adapted for time series to provide explanation in the form of saliency maps, where the importance of each data point in the time series is quantified with a numerical value. However, the saliency maps can and often disagree, so it is unclear which one to use. This paper provides a novel framework to quantitatively evaluate and rank explanation methods for time series classification. We show how to robustly evaluate the informativeness of a given explanation method (i.e., relevance for the classification task), and how to compare explanations side-by-side. The goal is to recommend the best explainer for a given time series classification dataset. We propose AMEE, a Model-Agnostic Explanation Evaluation framework, for recommending saliency-based explanations for time series classification. In this approach, data perturbation is added to the input time series guided by each explanation. Our results show that perturbing discriminative parts of the time series leads to significant changes in classification accuracy, which can be used to evaluate each explanation. To be robust to different types of perturbations and different types of classifiers, we aggregate the accuracy loss across perturbations and classifiers. This novel approach allows us to recommend the best explainer among a set of different explainers, including random and oracle explainers. We provide a quantitative and qualitative analysis for synthetic datasets, a variety of timeseries datasets, as well as a real-world case study with known expert ground truth.

arXiv:2306.04641공식 코드 · Papers with Code

Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning

Human activity recognition (HAR) is a time series classification task that focuses on identifying the motion patterns from human sensor readings. Adequate data is essential but a major bottleneck for training a generalizable HAR model, which assists customization and optimization of online web applications. However, it is costly in time and economy to collect large-scale labeled data in reality, i.e., the low-resource challenge. Meanwhile, data collected from different persons have distribution shifts due to different living habits, body shapes, age groups, etc. The low-resource and distribution shift challenges are detrimental to HAR when applying the trained model to new unseen subjects. In this paper, we propose a novel approach called Diverse and Discriminative representation Learning (DDLearn) for generalizable low-resource HAR. DDLearn simultaneously considers diversity and discrimination learning. With the constructed self-supervised learning task, DDLearn enlarges the data diversity and explores the latent activity properties. Then, we propose a diversity preservation module to preserve the diversity of learned features by enlarging the distribution divergence between the original and augmented domains. Meanwhile, DDLearn also enhances semantic discrimination by learning discriminative representations with supervised contrastive learning. Extensive experiments on three public HAR datasets demonstrate that our method significantly outperforms state-of-art methods by an average accuracy improvement of 9.5% under the low-resource distribution shift scenarios, while being a generic, explainable, and flexible framework. Code is available at: https://github.com/microsoft/robustlearn.

arXiv:2305.19798공식 코드 · Papers with Code

Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation

Recently, a new line of works has emerged to understand and improve self-attention in Transformers by treating it as a kernel machine. However, existing works apply the methods for symmetric kernels to the asymmetric self-attention, resulting in a nontrivial gap between the analytical understanding and numerical implementation. In this paper, we provide a new perspective to represent and optimize self-attention through asymmetric Kernel Singular Value Decomposition (KSVD), which is also motivated by the low-rank property of self-attention normally observed in deep layers. Through asymmetric KSVD, $i$) a primal-dual representation of self-attention is formulated, where the optimization objective is cast to maximize the projection variances in the attention outputs; $ii$) a novel attention mechanism, i.e., Primal-Attention, is proposed via the primal representation of KSVD, avoiding explicit computation of the kernel matrix in the dual; $iii$) with KKT conditions, we prove that the stationary solution to the KSVD optimization in Primal-Attention yields a zero-value objective. In this manner, KSVD optimization can be implemented by simply minimizing a regularization loss, so that low-rank property is promoted without extra decomposition. Numerical experiments show state-of-the-art performance of our Primal-Attention with improved efficiency. Moreover, we demonstrate that the deployed KSVD optimization regularizes Primal-Attention with a sharper singular value decay than that of the canonical self-attention, further verifying the great potential of our method. To the best of our knowledge, this is the first work that provides a primal-dual representation for the asymmetric kernel in self-attention and successfully applies it to modeling and optimization.

arXiv:2305.18811공식 코드 · Papers with Code

PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series

PyPOTS is an open-source Python library dedicated to data mining and analysis on multivariate partially-observed time series, i.e. incomplete time series with missing values, A.K.A. irregularlysampled time series. Particularly, it provides easy access to diverse algorithms categorized into four tasks: imputation, classification, clustering, and forecasting. The included models contain probabilistic approaches as well as neural-network methods, with a well-designed and fully-documented programming interface for both academic researchers and industrial professionals to use. With robustness and scalability in its design philosophy, best practices of software construction, for example, unit testing, continuous integration (CI) and continuous delivery (CD), code coverage, maintainability evaluation, interactive tutorials, and parallelization, are carried out as principles during the development of PyPOTS. The toolkit is available on both Python Package Index (PyPI) and Anaconda. PyPOTS is open-source and publicly available on GitHub https://github.com/WenjieDu/PyPOTS.

arXiv:2305.16642공식 코드 · Papers with Code

Improving Position Encoding of Transformers for Multivariate Time Series Classification

Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy of position encoding in time series analysis is not well-studied and remains controversial, e.g., whether it is better to inject absolute position encoding or relative position encoding, or a combination of them. In order to clarify this, we first review existing absolute and relative position encoding methods when applied in time series classification. We then proposed a new absolute position encoding method dedicated to time series data called time Absolute Position Encoding (tAPE). Our new method incorporates the series length and input embedding dimension in absolute position encoding. Additionally, we propose computationally Efficient implementation of Relative Position Encoding (eRPE) to improve generalisability for time series. We then propose a novel multivariate time series classification (MTSC) model combining tAPE/eRPE and convolution-based input encoding named ConvTran to improve the position and data embedding of time series data. The proposed absolute and relative position encoding methods are simple and efficient. They can be easily integrated into transformer blocks and used for downstream tasks such as forecasting, extrinsic regression, and anomaly detection. Extensive experiments on 32 multivariate time-series datasets show that our model is significantly more accurate than state-of-the-art convolution and transformer-based models. Code and models are open-sourced at \url{https://github.com/Navidfoumani/ConvTran}.

arXiv:2305.10352공식 코드 · Papers with Code

Appliance Detection Using Very Low-Frequency Smart Meter Time Series

In recent years, smart meters have been widely adopted by electricity suppliers to improve the management of the smart grid system. These meters usually collect energy consumption data at a very low frequency (every 30min), enabling utilities to bill customers more accurately. To provide more personalized recommendations, the next step is to detect the appliances owned by customers, which is a challenging problem, due to the very-low meter reading frequency. Even though the appliance detection problem can be cast as a time series classification problem, with many such classifiers having been proposed in the literature, no study has applied and compared them on this specific problem. This paper presents an in-depth evaluation and comparison of state-of-the-art time series classifiers applied to detecting the presence/absence of diverse appliances in very low-frequency smart meter data. We report results with five real datasets. We first study the impact of the detection quality of 13 different appliances using 30min sampled data, and we subsequently propose an analysis of the possible detection performance gain by using a higher meter reading frequency. The results indicate that the performance of current time series classifiers varies significantly. Some of them, namely deep learning-based classifiers, provide promising results in terms of accuracy (especially for certain appliances), even using 30min sampled data, and are scalable to the large smart meter time series collections of energy consumption data currently available to electricity suppliers. Nevertheless, our study shows that more work is needed in this area to further improve the accuracy of the proposed solutions. This paper appeared in ACM e-Energy 2023.

arXiv:2305.10059공식 코드 · Papers with Code

A hybrid feature learning approach based on convolutional kernels for ATM fault prediction using event-log data

Predictive Maintenance (PdM) methods aim to facilitate the scheduling of maintenance work before equipment failure. In this context, detecting early faults in automated teller machines (ATMs) has become increasingly important since these machines are susceptible to various types of unpredictable failures. ATMs track execution status by generating massive event-log data that collect system messages unrelated to the failure event. Predicting machine failure based on event logs poses additional challenges, mainly in extracting features that might represent sequences of events indicating impending failures. Accordingly, feature learning approaches are currently being used in PdM, where informative features are learned automatically from minimally processed sensor data. However, a gap remains to be seen on how these approaches can be exploited for deriving relevant features from event-log-based data. To fill this gap, we present a predictive model based on a convolutional kernel (MiniROCKET and HYDRA) to extract features from the original event-log data and a linear classifier to classify the sample based on the learned features. The proposed methodology is applied to a significant real-world collected dataset. Experimental results demonstrated how one of the proposed convolutional kernels (i.e. HYDRA) exhibited the best classification performance (accuracy of 0.759 and AUC of 0.693). In addition, statistical analysis revealed that the HYDRA and MiniROCKET models significantly overcome one of the established state-of-the-art approaches in time series classification (InceptionTime), and three non-temporal ML methods from the literature. The predictive model was integrated into a container-based decision support system to support operators in the timely maintenance of ATMs.

arXiv:2305.01429공식 코드 · Papers with Code

Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression

Time Series Extrinsic Regression (TSER) involves using a set of training time series to form a predictive model of a continuous response variable that is not directly related to the regressor series. The TSER archive for comparing algorithms was released in 2022 with 19 problems. We increase the size of this archive to 63 problems and reproduce the previous comparison of baseline algorithms. We then extend the comparison to include a wider range of standard regressors and the latest versions of TSER models used in the previous study. We show that none of the previously evaluated regressors can outperform a regression adaptation of a standard classifier, rotation forest. We introduce two new TSER algorithms developed from related work in time series classification. FreshPRINCE is a pipeline estimator consisting of a transform into a wide range of summary features followed by a rotation forest regressor. DrCIF is a tree ensemble that creates features from summary statistics over random intervals. Our study demonstrates that both algorithms, along with InceptionTime, exhibit significantly better performance compared to the other 18 regressors tested. More importantly, these two proposals (DrCIF and FreshPRINCE) models are the only ones that significantly outperform the standard rotation forest regressor.

arXiv:2304.13029공식 코드 · Papers with Code

Bake off redux: a review and experimental evaluation of recent time series classification algorithms

In 2017, a research paper compared 18 Time Series Classification (TSC) algorithms on 85 datasets from the University of California, Riverside (UCR) archive. This study, commonly referred to as a `bake off', identified that only nine algorithms performed significantly better than the Dynamic Time Warping (DTW) and Rotation Forest benchmarks that were used. The study categorised each algorithm by the type of feature they extract from time series data, forming a taxonomy of five main algorithm types. This categorisation of algorithms alongside the provision of code and accessible results for reproducibility has helped fuel an increase in popularity of the TSC field. Over six years have passed since this bake off, the UCR archive has expanded to 112 datasets and there have been a large number of new algorithms proposed. We revisit the bake off, seeing how each of the proposed categories have advanced since the original publication, and evaluate the performance of newer algorithms against the previous best-of-category using an expanded UCR archive. We extend the taxonomy to include three new categories to reflect recent developments. Alongside the originally proposed distance, interval, shapelet, dictionary and hybrid based algorithms, we compare newer convolution and feature based algorithms as well as deep learning approaches. We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category. Overall, we find that two recently proposed algorithms, Hydra+MultiROCKET and HIVE-COTEv2, perform significantly better than other approaches on both the current and new TSC problems.

arXiv:2304.11265공식 코드 · Papers with Code

Time Series Classification for Detecting Parkinson's Disease from Wrist Motions

Parkinson's disease (PD) is a neurodegenerative condition characterized by frequently changing motor symptoms, necessitating continuous symptom monitoring for more targeted treatment. Classical time series classification and deep learning techniques have demonstrated limited efficacy in monitoring PD symptoms using wearable accelerometer data due to complex PD movement patterns and the small size of available datasets. We investigate InceptionTime and RandOm Convolutional KErnel Transform (ROCKET) as they are promising for PD symptom monitoring, with InceptionTime's high learning capacity being well-suited to modeling complex movement patterns while ROCKET is suited to small datasets. With random search methodology, we identify the highest-scoring InceptionTime architecture and compare its performance to ROCKET with a ridge classifier and a multi-layer perceptron (MLP) on wrist motion data from PD patients. Our findings indicate that all approaches are suitable for estimating tremor severity and bradykinesia presence but encounter challenges in detecting dyskinesia. ROCKET demonstrates superior performance in identifying dyskinesia, whereas InceptionTime exhibits slightly better performance in tremor and bradykinesia detection. Notably, both methods outperform the multi-layer perceptron. In conclusion, InceptionTime exhibits the capability to classify complex wrist motion time series and holds the greatest potential for continuous symptom monitoring in PD.

arXiv:2304.05800공식 코드 · Papers with Code

Proximity Forest 2.0: A new effective and scalable similarity-based classifier for time series

Time series classification (TSC) is a challenging task due to the diversity of types of feature that may be relevant for different classification tasks, including trends, variance, frequency, magnitude, and various patterns. To address this challenge, several alternative classes of approach have been developed, including similarity-based, features and intervals, shapelets, dictionary, kernel, neural network, and hybrid approaches. While kernel, neural network, and hybrid approaches perform well overall, some specialized approaches are better suited for specific tasks. In this paper, we propose a new similarity-based classifier, Proximity Forest version 2.0 (PF 2.0), which outperforms previous state-of-the-art similarity-based classifiers across the UCR benchmark and outperforms state-of-the-art kernel, neural network, and hybrid methods on specific datasets in the benchmark that are best addressed by similarity-base methods. PF 2.0 incorporates three recent advances in time series similarity measures -- (1) computationally efficient early abandoning and pruning to speedup elastic similarity computations; (2) a new elastic similarity measure, Amerced Dynamic Time Warping (ADTW); and (3) cost function tuning. It rationalizes the set of similarity measures employed, reducing the eight base measures of the original PF to three and using the first derivative transform with all similarity measures, rather than a limited subset. We have implemented both PF 1.0 and PF 2.0 in a single C++ framework, making the PF framework more efficient.

arXiv:2304.05078공식 코드 · Papers with Code

TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification

Multivariate time series classification (MTSC) is an important data mining task, which can be effectively solved by popular deep learning technology. Unfortunately, the existing deep learning-based methods neglect the hidden dependencies in different dimensions and also rarely consider the unique dynamic features of time series, which lack sufficient feature extraction capability to obtain satisfactory classification accuracy. To address this problem, we propose a novel temporal dynamic graph neural network (TodyNet) that can extract hidden spatio-temporal dependencies without undefined graph structure. It enables information flow among isolated but implicit interdependent variables and captures the associations between different time slots by dynamic graph mechanism, which further improves the classification performance of the model. Meanwhile, the hierarchical representations of graphs cannot be learned due to the limitation of GNNs. Thus, we also design a temporal graph pooling layer to obtain a global graph-level representation for graph learning with learnable temporal parameters. The dynamic graph, graph information propagation, and temporal convolution are jointly learned in an end-to-end framework. The experiments on 26 UEA benchmark datasets illustrate that the proposed TodyNet outperforms existing deep learning-based methods in the MTSC tasks.

arXiv:2304.01236공식 코드 · Papers with Code

Astronomical image time series classification using CONVolutional attENTION (ConvEntion)

Aims. The treatment of astronomical image time series has won increasing attention in recent years. Indeed, numerous surveys following up on transient objects are in progress or under construction, such as the Vera Rubin Observatory Legacy Survey for Space and Time (LSST), which is poised to produce huge amounts of these time series. The associated scientific topics are extensive, ranging from the study of objects in our galaxy to the observation of the most distant supernovae for measuring the expansion of the universe. With such a large amount of data available, the need for robust automatic tools to detect and classify celestial objects is growing steadily. Methods. This study is based on the assumption that astronomical images contain more information than light curves. In this paper, we propose a novel approach based on deep learning for classifying different types of space objects directly using images. We named our approach ConvEntion, which stands for CONVolutional attENTION. It is based on convolutions and transformers, which are new approaches for the treatment of astronomical image time series. Our solution integrates spatio-temporal features and can be applied to various types of image datasets with any number of bands. Results. In this work, we solved various problems the datasets tend to suffer from and we present new results for classifications using astronomical image time series with an increase in accuracy of 13%, compared to state-of-the-art approaches that use image time series, and a 12% increase, compared to approaches that use light curves.

arXiv:2303.17995공식 코드 · Papers with Code

Neural Network Entropy (NNetEn): Entropy-Based EEG Signal and Chaotic Time Series Classification, Python Package for NNetEn Calculation

Entropy measures are effective features for time series classification problems. Traditional entropy measures, such as Shannon entropy, use probability distribution function. However, for the effective separation of time series, new entropy estimation methods are required to characterize the chaotic dynamic of the system. Our concept of Neural Network Entropy (NNetEn) is based on the classification of special datasets in relation to the entropy of the time series recorded in the reservoir of the neural network. NNetEn estimates the chaotic dynamics of time series in an original way and does not take into account probability distribution functions. We propose two new classification metrics: R2 Efficiency and Pearson Efficiency. The efficiency of NNetEn is verified on separation of two chaotic time series of sine mapping using dispersion analysis. For two close dynamic time series (r = 1.1918 and r = 1.2243), the F-ratio has reached the value of 124 and reflects high efficiency of the introduced method in classification problems. The electroenceph-alography signal classification for healthy persons and patients with Alzheimer disease illustrates the practical application of the NNetEn features. Our computations demonstrate the synergistic effect of increasing classification accuracy when applying traditional entropy measures and the NNetEn concept conjointly. An implementation of the algorithms in Python is presented.

arXiv:2303.12533공식 코드 · Papers with Code

Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach

Improvements in Earth observation by satellites allow for imagery of ever higher temporal and spatial resolution. Leveraging this data for agricultural monitoring is key for addressing environmental and economic challenges. Current methods for crop segmentation using temporal data either rely on annotated data or are heavily engineered to compensate the lack of supervision. In this paper, we present and compare datasets and methods for both supervised and unsupervised pixel-wise segmentation of satellite image time series (SITS). We also introduce an approach to add invariance to spectral deformations and temporal shifts to classical prototype-based methods such as K-means and Nearest Centroid Classifier (NCC). We study different levels of supervision and show this simple and highly interpretable method achieves the best performance in the low data regime and significantly improves the state of the art for unsupervised classification of agricultural time series on four recent SITS datasets.

arXiv:2303.09489공식 코드 · Papers with Code

Effectively Modeling Time Series with Simple Discrete State Spaces

Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs) are classical models for time series, and prior works combine SSMs with deep learning layers for efficient sequence modeling. However, we find fundamental limitations with these prior approaches, proving their SSM representations cannot express autoregressive time series processes. We thus introduce SpaceTime, a new state-space time series architecture that improves all three criteria. For expressivity, we propose a new SSM parameterization based on the companion matrix -- a canonical representation for discrete-time processes -- which enables SpaceTime's SSM layers to learn desirable autoregressive processes. For long horizon forecasting, we introduce a "closed-loop" variation of the companion SSM, which enables SpaceTime to predict many future time-steps by generating its own layer-wise inputs. For efficient training and inference, we introduce an algorithm that reduces the memory and compute of a forward pass with the companion matrix. With sequence length $\ell$ and state-space size $d$, we go from $\tilde{O}(d \ell)$ na\"ively to $\tilde{O}(d + \ell)$. In experiments, our contributions lead to state-of-the-art results on extensive and diverse benchmarks, with best or second-best AUROC on 6 / 7 ECG and speech time series classification, and best MSE on 14 / 16 Informer forecasting tasks. Furthermore, we find SpaceTime (1) fits AR($p$) processes that prior deep SSMs fail on, (2) forecasts notably more accurately on longer horizons than prior state-of-the-art, and (3) speeds up training on real-world ETTh1 data by 73% and 80% relative wall-clock time over Transformers and LSTMs.

arXiv:2303.08103공식 코드 · Papers with Code

Multi-task Meta Label Correction for Time Series Prediction

Time series classification faces two unavoidable problems. One is partial feature information and the other is poor label quality, which may affect model performance. To address the above issues, we create a label correction method to time series data with meta-learning under a multi-task framework. There are three main contributions. First, we train the label correction model with a two-branch neural network in the outer loop. While in the model-agnostic inner loop, we use pre-existing classification models in a multi-task way and jointly update the meta-knowledge so as to help us achieve adaptive labeling on complex time series. Second, we devise new data visualization methods for both image patterns of the historical data and data in the prediction horizon. Finally, we test our method with various financial datasets, including XOM, S\&P500, and SZ50. Results show that our method is more effective and accurate than some existing label correction techniques.

arXiv:2303.05517공식 코드 · Papers with Code

On the Soundness of XAI in Prognostics and Health Management (PHM)

The aim of Predictive Maintenance, within the field of Prognostics and Health Management (PHM), is to identify and anticipate potential issues in the equipment before these become critical. The main challenge to be addressed is to assess the amount of time a piece of equipment will function effectively before it fails, which is known as Remaining Useful Life (RUL). Deep Learning (DL) models, such as Deep Convolutional Neural Networks (DCNN) and Long Short-Term Memory (LSTM) networks, have been widely adopted to address the task, with great success. However, it is well known that this kind of black box models are opaque decision systems, and it may be hard to explain its outputs to stakeholders (experts in the industrial equipment). Due to the large number of parameters that determine the behavior of these complex models, understanding the reasoning behind the predictions is challenging. This work presents a critical and comparative revision on a number of XAI methods applied on time series regression model for PM. The aim is to explore XAI methods within time series regression, which have been less studied than those for time series classification. The model used during the experimentation is a DCNN trained to predict the RUL of an aircraft engine. The methods are reviewed and compared using a set of metrics that quantifies a number of desirable properties that any XAI method should fulfill. The results show that GRAD-CAM is the most robust method, and that the best layer is not the bottom one, as is commonly seen within the context of Image Processing.

arXiv:2303.00320공식 코드 · Papers with Code

TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders

Enhancing the expressive capacity of deep learning-based time series models with self-supervised pre-training has become ever-increasingly prevalent in time series classification. Even though numerous efforts have been devoted to developing self-supervised models for time series data, we argue that the current methods are not sufficient to learn optimal time series representations due to solely unidirectional encoding over sparse point-wise input units. In this work, we propose TimeMAE, a novel self-supervised paradigm for learning transferrable time series representations based on transformer networks. The distinct characteristics of the TimeMAE lie in processing each time series into a sequence of non-overlapping sub-series via window-slicing partitioning, followed by random masking strategies over the semantic units of localized sub-series. Such a simple yet effective setting can help us achieve the goal of killing three birds with one stone, i.e., (1) learning enriched contextual representations of time series with a bidirectional encoding scheme; (2) increasing the information density of basic semantic units; (3) efficiently encoding representations of time series using transformer networks. Nevertheless, it is a non-trivial to perform reconstructing task over such a novel formulated modeling paradigm. To solve the discrepancy issue incurred by newly injected masked embeddings, we design a decoupled autoencoder architecture, which learns the representations of visible (unmasked) positions and masked ones with two different encoder modules, respectively. Furthermore, we construct two types of informative targets to accomplish the corresponding pretext tasks. One is to create a tokenizer module that assigns a codeword to each masked region, allowing the masked codeword classification (MCC) task to be completed effectively...