arXiv subjects

Bin Yang

Publications and source records attributed to Bin Yang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching

Patch-wise Transformer based time series forecasting achieves superior accuracy. However, this superiority relies heavily on intricate model design with massive parameters, rendering both training and inference expensive, thus preventing their deployments on edge devices with limited resources and low latency requirements. In addition, existing methods often work in an autoregressive manner, which take into account only historical values, but ignore valuable, easy-to-obtain context information, such as weather forecasts, date and time of day. To contend with the two limitations, we propose LiPFormer, a novel Lightweight Patch-wise Transformer with weak data enriching. First, to simplify the Transformer backbone, LiPFormer employs a novel lightweight cross-patch attention and a linear transformation-based attention to eliminate Layer Normalization and Feed Forward Network, two heavy components in existing Transformers. Second, we propose a lightweight, weak data enriching module to provide additional, valuable weak supervision to the training. It enhances forecasting accuracy without significantly increasing model complexity as it does not involve expensive, human-labeling but using easily accessible context information. This facilitates the weak data enriching to plug-and-play on existing models. Extensive experiments on nine benchmark time series datasets demonstrate that LiPFormer outperforms state-of-the-art methods in accuracy, while significantly reducing parameter scale, training duration, and GPU memory usage. Deployment on an edge device reveals that LiPFormer takes only 1/3 inference time compared to classic Transformers. In addition, we demonstrate that the weak data enriching can integrate seamlessly into various Transformer based models to enhance their accuracy, suggesting its generality.

cs.LG↗

arXiv2025

DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting

Multivariate time series forecasting is crucial for various applications, such as financial investment, energy management, weather forecasting, and traffic optimization. However, accurate forecasting is challenging due to two main factors. First, real-world time series often show heterogeneous temporal patterns caused by distribution shifts over time. Second, correlations among channels are complex and intertwined, making it hard to model the interactions among channels precisely and flexibly. In this study, we address these challenges by proposing a general framework called DUET, which introduces dual clustering on the temporal and channel dimensions to enhance multivariate time series forecasting. First, we design a Temporal Clustering Module (TCM) that clusters time series into fine-grained distributions to handle heterogeneous temporal patterns. For different distribution clusters, we design various pattern extractors to capture their intrinsic temporal patterns, thus modeling the heterogeneity. Second, we introduce a novel Channel-Soft-Clustering strategy and design a Channel Clustering Module (CCM), which captures the relationships among channels in the frequency domain through metric learning and applies sparsification to mitigate the adverse effects of noisy channels. Finally, DUET combines TCM and CCM to incorporate both the temporal and channel dimensions. Extensive experiments on 25 real-world datasets from 10 application domains, demonstrate the state-of-the-art performance of DUET.

cs.LG↗

arXiv2025

MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version

Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they predominantly focus on the topological structures from single modality data, i.e., road networks, overlooking the geometric and contextual features associated with path-related images, e.g., remote sensing images. Similar to human understanding, integrating information from multiple modalities can provide a more comprehensive view, enhancing both representation accuracy and generalization. However, variations in information granularity impede the semantic alignment of road network-based paths (road paths) and image-based paths (image paths), while the heterogeneity of multi-modal data poses substantial challenges for effective fusion and utilization. In this paper, we propose a novel Multi-modal, Multi-granularity Path Representation Learning Framework (MM-Path), which can learn a generic path representation by integrating modalities from both road paths and image paths. To enhance the alignment of multi-modal data, we develop a multi-granularity alignment strategy that systematically associates nodes, road sub-paths, and road paths with their corresponding image patches, ensuring the synchronization of both detailed local information and broader global contexts. To address the heterogeneity of multi-modal data effectively, we introduce a graph-based cross-modal residual fusion component designed to comprehensively fuse information across different modalities and granularities. Finally, we conduct extensive experiments on two large-scale real-world datasets under two downstream tasks, validating the effectiveness of the proposed MM-Path. The code is available at: https://github.com/decisionintelligence/MM-Path.

cs.LG↗

arXiv2024

EasyTime: Time Series Forecasting Made Easy

Time series forecasting has important applications across diverse domains. EasyTime, the system we demonstrate, facilitates easy use of time-series forecasting methods by researchers and practitioners alike. First, EasyTime enables one-click evaluation, enabling researchers to evaluate new forecasting methods using the suite of diverse time series datasets collected in the preexisting time series forecasting benchmark (TFB). This is achieved by leveraging TFB's flexible and consistent evaluation pipeline. Second, when practitioners must perform forecasting on a new dataset, a nontrivial first step is often to find an appropriate forecasting method. EasyTime provides an Automated Ensemble module that combines the promising forecasting methods to yield superior forecasting accuracy compared to individual methods. Third, EasyTime offers a natural language Q&A module leveraging large language models. Given a question like "Which method is best for long term forecasting on time series with strong seasonality?", EasyTime converts the question into SQL queries on the database of results obtained by TFB and then returns an answer in natural language and charts. By demonstrating EasyTime, we intend to show how it is possible to simplify the use of time series forecasting and to offer better support for the development of new generations of time series forecasting methods.

cs.LG↗

arXiv2024

Distributed Computation Offloading for Energy Provision Minimization in WP-MEC Networks with Multiple HAPs

This paper investigates a wireless powered mobile edge computing (WP-MEC) network with multiple hybrid access points (HAPs) in a dynamic environment, where wireless devices (WDs) harvest energy from radio frequency (RF) signals of HAPs, and then compute their computation data locally (i.e., local computing mode) or offload it to the chosen HAPs (i.e., edge computing mode). In order to pursue a green computing design, we formulate an optimization problem that minimizes the long-term energy provision of the WP-MEC network subject to the energy, computing delay and computation data demand constraints. The transmit power of HAPs, the duration of the wireless power transfer (WPT) phase, the offloading decisions of WDs, the time allocation for offloading and the CPU frequency for local computing are jointly optimized adapting to the time-varying generated computation data and wireless channels of WDs. To efficiently address the formulated non-convex mixed integer programming (MIP) problem in a distributed manner, we propose a Two-stage Multi-Agent deep reinforcement learning-based Distributed computation Offloading (TMADO) framework, which consists of a high-level agent and multiple low-level agents. The high-level agent residing in all HAPs optimizes the transmit power of HAPs and the duration of the WPT phase, while each low-level agent residing in each WD optimizes its offloading decision, time allocation for offloading and CPU frequency for local computing. Simulation results show the superiority of the proposed TMADO framework in terms of the energy provision minimization.

cs.NI↗

arXiv2024

Pullback attractors for nonclassical diffusion equations with a delay operator

In this paper, we consider the asymptotic behavior of weak solutions for nonclassical non-autonomous diffusion equations with a delay operator in time-dependent spaces when the nonlinear function $g$ satisfies subcritical exponent growth conditions, the delay operator $φ(t, u_t)$ contains some hereditary characteristics and the external force $k \in L_{l o c}^{2}\left(\mathbb{R} ; L^{2}(Ω)\right)$. First, we prove the well-posedness of solutions by using the Faedo-Galerkin approximation method. Then after a series of elaborate energy estimates and calculations, we establish the existence and regularity of pullback attractors in time-dependent spaces $C_{\mathcal{H}_{t}(Ω)}$ and $C_{\mathcal{H}^{1}_{t}(Ω)}$, respectively.

math.AP↗

arXiv2024

TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Version

Due to the global trend towards urbanization, people increasingly move to and live in cities that then continue to grow. Traffic forecasting plays an important role in the intelligent transportation systems of cities as well as in spatio-temporal data mining. State-of-the-art forecasting is achieved by deep-learning approaches due to their ability to contend with complex spatio-temporal dynamics. However, existing methods assume the input is fixed-topology road networks and static traffic time series. These assumptions fail to align with urbanization, where time series are collected continuously and road networks evolve over time. In such settings, deep-learning models require frequent re-initialization and re-training, imposing high computational costs. To enable much more efficient training without jeopardizing model accuracy, we propose the Topological Evolution-aware Framework (TEAM) for traffic forecasting that incorporates convolution and attention. This combination of mechanisms enables better adaptation to newly collected time series, while being able to maintain learned knowledge from old time series. TEAM features a continual learning module based on the Wasserstein metric that acts as a buffer that can identify the most stable and the most changing network nodes. Then, only data related to stable nodes is employed for re-training when consolidating a model. Further, only data of new nodes and their adjacent nodes as well as data pertaining to changing nodes are used to re-train the model. Empirical studies with two real-world traffic datasets offer evidence that TEAM is capable of much lower re-training costs than existing methods are, without jeopardizing forecasting accuracy.

cs.LG↗

arXiv2024

Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model

In practice, domain shifts are likely to occur between training and test data, necessitating domain adaptation (DA) to adjust the pre-trained source model to the target domain. Recently, universal domain adaptation (UniDA) has gained attention for addressing the possibility of an additional category (label) shift between the source and target domain. This means new classes can appear in the target data, some source classes may no longer be present, or both at the same time. For practical applicability, UniDA methods must handle both source-free and online scenarios, enabling adaptation without access to the source data and performing batch-wise updates in parallel with prediction. In an online setting, preserving knowledge across batches is crucial. However, existing methods often require substantial memory, which is impractical because memory is limited and valuable, in particular on embedded systems. Therefore, we consider memory-efficiency as an additional constraint. To achieve memory-efficient online source-free universal domain adaptation (SF-UniDA), we propose a novel method that continuously captures the distribution of known classes in the feature space using a Gaussian mixture model (GMM). This approach, combined with entropy-based out-of-distribution detection, allows for the generation of reliable pseudo-labels. Finally, we combine a contrastive loss with a KL divergence loss to perform the adaptation. Our approach not only achieves state-of-the-art results in all experiments on the DomainNet and Office-Home datasets but also significantly outperforms the existing methods on the challenging VisDA-C dataset, setting a new benchmark for online SF-UniDA. Our code is available at https://github.com/pascalschlachter/GMM.

cs.CV↗

arXiv2024

Fully Automated Correlated Time Series Forecasting in Minutes

Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically designed models achieve higher accuracy than manually designed models. Given a forecasting task, which includes a dataset and a forecasting horizon, automated design methods automatically search for an optimal forecasting model for the task in a manually designed search space, and then train the identified model using the dataset to enable the forecasting. Existing automated methods face three challenges. First, the search space is constructed by human experts, rending the methods only semi-automated and yielding search spaces prone to subjective biases. Second, it is time consuming to search for an optimal model. Third, training the identified model for a new task is also costly. These challenges limit the practicability of automated methods in real-world settings. To contend with the challenges, we propose a fully automated and highly efficient correlated time series forecasting framework where the search and training can be done in minutes. The framework includes a data-driven, iterative strategy to automatically prune a large search space to obtain a high-quality search space for a new forecasting task. It includes a zero-shot search strategy to efficiently identify the optimal model in the customized search space. And it includes a fast parameter adaptation strategy to accelerate the training of the identified model. Experiments on seven benchmark datasets offer evidence that the framework is capable of state-of-the-art accuracy and is much more efficient than existing methods.

cs.LG↗

arXiv2024

Less is More: Efficient Time Series Dataset Condensation via Two-fold Modal Matching--Extended Version

The expanding instrumentation of processes throughout society with sensors yields a proliferation of time series data that may in turn enable important applications, e.g., related to transportation infrastructures or power grids. Machine-learning based methods are increasingly being used to extract value from such data. We provide means of reducing the resulting considerable computational and data storage costs. We achieve this by providing means of condensing large time series datasets such that models trained on the condensed data achieve performance comparable to those trained on the original, large data. Specifically, we propose a time series dataset condensation framework, TimeDC, that employs two-fold modal matching, encompassing frequency matching and training trajectory matching. Thus, TimeDC performs time series feature extraction and decomposition-driven frequency matching to preserve complex temporal dependencies in the reduced time series. Further, TimeDC employs curriculum training trajectory matching to ensure effective and generalized time series dataset condensation. To avoid memory overflow and to reduce the cost of dataset condensation, the framework includes an expert buffer storing pre-computed expert trajectories. Extensive experiments on real data offer insight into the effectiveness and efficiency of the proposed solutions.

cs.DB↗

arXiv2024

MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast

Many methods have been proposed for unsupervised time series anomaly detection. Despite some progress, research on predicting future anomalies is still relatively scarce. Predicting anomalies is particularly challenging due to the diverse reaction time and the lack of labeled data. To address these challenges, we propose MultiRC to integrate reconstructive and contrastive learning for joint learning of anomaly prediction and detection, with multi-scale structure and adaptive dominant period mask to deal with the diverse reaction time. MultiRC also generates negative samples to provide essential training momentum for the anomaly prediction tasks and prevent model degradation. We evaluate seven benchmark datasets from different fields. For both anomaly prediction and detection tasks, MultiRC outperforms existing state-of-the-art methods.

cs.LG↗

arXiv2024

Squeeze-and-Remember Block

Convolutional Neural Networks (CNNs) are important for many machine learning tasks. They are built with different types of layers: convolutional layers that detect features, dropout layers that help to avoid over-reliance on any single neuron, and residual layers that allow the reuse of features. However, CNNs lack a dynamic feature retention mechanism similar to the human brain's memory, limiting their ability to use learned information in new contexts. To bridge this gap, we introduce the "Squeeze-and-Remember" (SR) block, a novel architectural unit that gives CNNs dynamic memory-like functionalities. The SR block selectively memorizes important features during training, and then adaptively re-applies these features during inference. This improves the network's ability to make contextually informed predictions. Empirical results on ImageNet and Cityscapes datasets demonstrate the SR block's efficacy: integration into ResNet50 improved top-1 validation accuracy on ImageNet by 0.52% over dropout2d alone, and its application in DeepLab v3 increased mean Intersection over Union in Cityscapes by 0.20%. These improvements are achieved with minimal computational overhead. This show the SR block's potential to enhance the capabilities of CNNs in image processing tasks.

cs.CV↗

arXiv2024

Spectral Wavelet Dropout: Regularization in the Wavelet Domain

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which make the CNN dependent on their joint response rather than encouraging each part to learn a useful feature representation independently. Frequency domain manipulation is a powerful strategy for modifying data that has temporal and spatial coherence by utilizing frequency decomposition. This work introduces Spectral Wavelet Dropout (SWD), a novel regularization method that includes two variants: 1D-SWD and 2D-SWD. These variants improve CNN generalization by randomly dropping detailed frequency bands in the discrete wavelet decomposition of feature maps. Our approach distinguishes itself from the pre-existing Spectral "Fourier" Dropout (2D-SFD), which eliminates coefficients in the Fourier domain. Notably, SWD requires only a single hyperparameter, unlike the two required by SFD. We also extend the literature by implementing a one-dimensional version of Spectral "Fourier" Dropout (1D-SFD), setting the stage for a comprehensive comparison. Our evaluation shows that both 1D and 2D SWD variants have competitive performance on CIFAR-10/100 benchmarks relative to both 1D-SFD and 2D-SFD. Specifically, 1D-SWD has a significantly lower computational complexity compared to 1D/2D-SFD. In the Pascal VOC Object Detection benchmark, SWD variants surpass 1D-SFD and 2D-SFD in performance and demonstrate lower computational complexity during training.

cs.CV↗

arXiv2024

CNN Mixture-of-Depths

We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This method optimizes computational resources by dynamically selecting key channels in feature maps for focused processing within the convolutional blocks (Conv-Blocks), while skipping less relevant channels. Unlike conditional computation methods that require dynamic computation graphs, CNN MoD uses a static computation graph with fixed tensor sizes which improve hardware efficiency. It speeds up the training and inference processes without the need for customized CUDA kernels, unique loss functions, or finetuning. CNN MoD either matches the performance of traditional CNNs with reduced inference times, GMACs, and parameters, or exceeds their performance while maintaining similar inference times, GMACs, and parameters. For example, on ImageNet, ResNet86-MoD exceeds the performance of the standard ResNet50 by 0.45% with a 6% speedup on CPU and 5% on GPU. Moreover, ResNet75-MoD achieves the same performance as ResNet50 with a 25% speedup on CPU and 15% on GPU.

cs.CV↗

arXiv2024

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

Transformers for time series forecasting mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. We propose Pathformer, a multi-scale Transformer with adaptive pathways. It integrates both temporal resolution and temporal distance for multi-scale modeling. Multi-scale division divides the time series into different temporal resolutions using patches of various sizes. Based on the division of each scale, dual attention is performed over these patches to capture global correlations and local details as temporal dependencies. We further enrich the multi-scale Transformer with adaptive pathways, which adaptively adjust the multi-scale modeling process based on the varying temporal dynamics of the input, improving the accuracy and generalization of Pathformer. Extensive experiments on eleven real-world datasets demonstrate that Pathformer not only achieves state-of-the-art performance by surpassing all current models but also exhibits stronger generalization abilities under various transfer scenarios. The code is made available at https://github.com/decisionintelligence/pathformer.

cs.LG↗

arXiv2024

FAST Observations of Four Comets to Search for the Molecular Line Emissions between 1.0 and 1.5 GHz Frequencies

We used the Five-hundred-meter Aperture Spherical radio Telescope (FAST) to search for the molecular emissions in the L-band between 1.0 and 1.5 GHz toward four comets, C/2020 F3 (NEOWISE), C/2020 R4 (ATLAS), C/2021 A1 (Leonard), and 67P/Churyumov-Gerasimenko during or after their perihelion passages. Thousands of molecular transition lines fall in this low-frequency range, many attributed to complex organic or prebiotic molecules. We conducted a blind search for the possible molecular lines in this frequency range in those comets and could not identify clear signals of molecular emissions in the data. Although several molecules have been detected at high frequencies of great than 100 GHz in comets, our results confirm that it is challenging to detect molecular transitions in the L-band frequency ranges. The non-detection of L-band molecular lines in the cometary environment could rule out the possibility of unusually strong lines, which could be caused by the masers or non-LTE effects. Although the line strengths are predicted to be weak, for FAST, using the ultra-wide bandwidth receiver and improving the radio frequency interference environments would enhance the detectability of those molecular transitions at low frequencies in the future.

astro-ph.EP↗

arXiv2024

A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models

In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its variants. The study systematically examines prompt-based techniques and existing test-time adaptation methods, aiming to improve the robustness under distribution shift in diverse real-world scenarios. Specifically, the investigation covers various prompt engineering strategies, including handcrafted prompts, prompt ensembles, and prompt learning techniques. Additionally, we introduce a vision-text-space ensemble that substantially enhances average performance compared to text-space-only ensembles. Since online test-time adaptation has shown to be effective to mitigate performance drops under distribution shift, the study extends its scope to evaluate the effectiveness of existing test-time adaptation methods that were originally designed for vision-only classification models. Through extensive experimental evaluations conducted across multiple datasets and diverse model architectures, the research demonstrates the effectiveness of these adaptation strategies. Code is available at: https://github.com/mariodoebler/test-time-adaptation

cs.CV↗

arXiv2024

SVS-GAN: Leveraging GANs for Semantic Video Synthesis

In recent years, there has been a growing interest in Semantic Image Synthesis (SIS) through the use of Generative Adversarial Networks (GANs) and diffusion models. This field has seen innovations such as the implementation of specialized loss functions tailored for this task, diverging from the more general approaches in Image-to-Image (I2I) translation. While the concept of Semantic Video Synthesis (SVS)$\unicode{x2013}$the generation of temporally coherent, realistic sequences of images from semantic maps$\unicode{x2013}$is newly formalized in this paper, some existing methods have already explored aspects of this field. Most of these approaches rely on generic loss functions designed for video-to-video translation or require additional data to achieve temporal coherence. In this paper, we introduce the SVS-GAN, a framework specifically designed for SVS, featuring a custom architecture and loss functions. Our approach includes a triple-pyramid generator that utilizes SPADE blocks. Additionally, we employ a U-Net-based network for the image discriminator, which performs semantic segmentation for the OASIS loss. Through this combination of tailored architecture and objective engineering, our framework aims to bridge the existing gap between SIS and SVS, outperforming current state-of-the-art models on datasets like Cityscapes and KITTI-360.

cs.CV↗