Long-term, high-fidelity simulation of slow-changing physical systems, such as the ocean and climate, presents a fundamental challenge in scientific computing. Traditional autoregressive machine learning models often fail in these tasks as minor errors accumulate and lead to rapid forecast degradation. To address this problem, we propose NeuralOM, a general neural operator framework designed for simulating complex, slow-changing dynamics. NeuralOM's core consists of two key innovations: (1) a Progressive Residual Correction Framework that decomposes the forecasting task into a series of fine-grained refinement steps, effectively suppressing long-term error accumulation; and (2) a Physics-Guided Graph Network whose built-in adaptive messaging mechanism explicitly models multi-scale physical interactions, such as gradient-driven flows and multiplicative couplings, thereby enhancing physical consistency while maintaining computational efficiency. We validate NeuralOM on the challenging task of global Subseasonal-to-Seasonal (S2S) ocean simulation. Extensive experiments demonstrate that NeuralOM not only surpasses state-of-the-art models in forecast accuracy and long-term stability, but also excels in simulating extreme events. For instance, at a 60-day lead time, NeuralOM achieves a 13.3% lower RMSE compared to the best-performing baseline, offering a stable, efficient, and physically-aware paradigm for data-driven scientific computing.

Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collaboration topology, which has become a focal point for automated design research. However, existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures, significantly limiting their adaptability to task-specific requirements. To address these limitations, we reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly. We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch. Conditioned on a natural language task query, ARG-Designer sequentially and dynamically determines the required number of agents, selects their appropriate roles from an extensible pool, and establishes the optimal communication links between them. This generative approach creates a customized topology in a flexible and extensible manner, precisely tailored to the unique demands of different tasks. Extensive experiments across six diverse benchmarks demonstrate that ARG-Designer not only achieves state-of-the-art performance but also enjoys significantly greater token efficiency and enhanced extensibility.

Time series forecasting is fundamental to diverse applications, with recent approaches leverage large vision models (LVMs) to capture temporal patterns through visual representations. We reveal that while vision models enhance forecasting performance, 99% of their parameters are unnecessary for time series tasks. Through cross-modal analysis, we find that time series align with low-level textural features but not high-level semantics, which can impair forecasting accuracy. We propose OccamVTS, a knowledge distillation framework that extracts only the essential 1% of predictive information from LVMs into lightweight networks. Using pre-trained LVMs as privileged teachers, OccamVTS employs pyramid-style feature alignment combined with correlation and feature distillation to transfer beneficial patterns while filtering out semantic noise. Counterintuitively, this aggressive parameter reduction improves accuracy by eliminating overfitting to irrelevant visual features while preserving essential temporal patterns. Extensive experiments across multiple benchmark datasets demonstrate that OccamVTS consistently achieves state-of-the-art performance with only 1% of the original parameters, particularly excelling in few-shot and zero-shot scenarios.

LLM-based multi-agent systems exhibit strong collaborative capabilities but often suffer from redundant communication and excessive token overhead. Existing methods typically enhance efficiency through pretrained GNNs or greedy algorithms, but often isolate pre- and post-task optimization, lacking a unified strategy. To this end, we present SafeSieve, a progressive and adaptive multi-agent pruning algorithm that dynamically refines the inter-agent communication through a novel dual-mechanism. SafeSieve integrates initial LLM-based semantic evaluation with accumulated performance feedback, enabling a smooth transition from heuristic initialization to experience-driven refinement. Unlike existing greedy Top-k pruning methods, SafeSieve employs 0-extension clustering to preserve structurally coherent agent groups while eliminating ineffective links. Experiments across benchmarks (SVAMP, HumanEval, etc.) showcase that SafeSieve achieves 94.01% average accuracy while reducing token usage by 12.4%-27.8%. Results further demonstrate robustness under prompt injection attacks (1.23% average accuracy drop). In heterogeneous settings, SafeSieve reduces deployment costs by 13.3% while maintaining performance. These results establish SafeSieve as an efficient, GPU-free, and scalable framework for practical multi-agent systems. Our code can be found below.

Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

State Space Models (SSMs) have emerged as a powerful framework for sequence modeling in recent years. By approximating continuous dynamical systems and applying discretization techniques, SSMs are particularly well-suited for modeling time-series data. However, despite their growing popularity, most existing applications of SSMs in time-series forecasting treat the models as black boxes. Besides, the underlying mechanisms that contribute to their effectiveness remain unclear, and common claims regarding their advantages in efficiency and expressiveness are not fully substantiated. To address these gaps, this paper establishes a theoretical connection between SSMs and classical spectral transformations from signal processing, thereby providing a more interpretable foundation. Furthermore, we conduct comprehensive ablation studies to examine the properties of different SSM configurations. Our goal is to offer both theoretical insight and empirical guidance for future research on SSM-based approaches in time-series forecasting.

While LLMs show promise in automating educational content creation, their ability to generate questions that stimulate higher-order thinking remains understudied. This work evaluates six widely used LLMs through a Bloom's Taxonomy lens, focusing on their capacity to transcend rote memorization and achieve cognitive leaps. Using a hybrid human-AI evaluation protocol, we generate and analyze 20,700 questions across computer science, K-12 math, and social-science domains. Key contributions include: (1) a fine-grained prompting strategy that reduces question repetitiveness by 24.45% for Qwen2.5-7B-Instruct, and increases the proportion of higher-order cognitive-level outputs by 11.53% for InternLM3-8B-Instruct; (2) quantitative metrics for cognitive shift intensity (CogShift) and category drift, revealing InternLM3's superior performance in multi-level transitions; (3) an interpretability analysis revealing metric-level correlations that enhance the transparency of Chain-of-Thought prompting. Our findings highlight the importance of cognitive-aware prompt design and provide benchmarks for deploying LLMs in personalized learning systems.

Retrieval-Augmented Generation (RAG) systems are increasingly central to robust AI, enhancing large language model (LLM) faithfulness by incorporating external knowledge. However, our study unveils a critical, overlooked vulnerability: their profound susceptibility to subtle symbolic perturbations, particularly through near-imperceptible emotional icons (e.g., "(@_@)") that can catastrophically mislead retrieval, termed EmoRAG. We demonstrate that injecting a single emoticon into a query makes it nearly 100% likely to retrieve semantically unrelated texts, which contain a matching emoticon. Our extensive experiment across general question-answering and code domains, using a range of state-of-the-art retrievers and generators, reveals three key findings: (I) Single-Emoticon Disaster: Minimal emoticon injections cause maximal disruptions, with a single emoticon almost 100% dominating RAG output. (II) Positional Sensitivity: Placing an emoticon at the beginning of a query can cause severe perturbation, with F1-Scores exceeding 0.92 across all datasets. (III) Parameter-Scale Vulnerability: Counterintuitively, models with larger parameters exhibit greater vulnerability to the interference. We provide an in-depth analysis to uncover the underlying mechanisms of these phenomena. Furthermore, we raise a critical concern regarding the robustness assumption of current RAG systems, envisioning a threat scenario where an adversary exploits this vulnerability to manipulate the RAG system. We evaluate standard defenses and find them insufficient against EmoRAG. To address this, we propose targeted defenses, analyzing their strengths and limitations in mitigating emoticon-based perturbations. Finally, we outline future directions for building robust RAG systems.

Seeing clearly with high resolution is a foundation of Multimodal Large Language Models (MLLMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the important tokens most relevant to the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a 'less is more' pattern, where utilizing fewer but more informative local image tokens leads to improved performance. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed MLLM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data.

Source-free domain adaptation (SFDA) is a challenging, yet valuable task within unsupervised domain adaptation (UDA), which adapts pretrained models to diverse unlabeled target domains while safeguarding the data security of the source domain. However, existing SFDA methods primarily focus on computer vision applications, often overlooking the unique characteristics of time series, such as temporal dependencies and sequential nature. Moreover, the fine-tuning paradigm of current SFDA methods is typically limited to posterior adaptation, focusing solely on constraining the statistical properties of model outputs. We argue that this black-box paradigm lacks semantic interpretability and risks aligning with spurious contextual noise, leading to negative transfer. This necessitates a paradigm evolution from blind statistical adaptation to interpretable adaptation. To this end, we introduce model salience as a quantifiable proxy of semantic interpretability, representing the importance weights a trained model assigns to specific temporal fragments. Accordingly, we propose a novel fine-tuning paradigm for time-series SFDA, termed PrEPoA, which integrates Prior Evaluation of model salience with Posterior Adaptation. In the prior evaluation stage, a key pattern reconstruction (KPR) module based on a sensitive masking mechanism is designed to quantify the model salience, while a novel interpattern triplet loss is introduced to calibrate it. In the posterior adaptation stage, robust prototype clustering (RPC) generates trustworthy reference labels as pseudo-ground truth for adaptation. Comprehensive experiments on the wireless sensor data mining (WISDM), human activity recognition (HAR), heterogeneity HAR (HHAR), machine fault diagnosis (MFD), and sleep stage classification (SSC) datasets demonstrate the superiority of our PrEPoA framework compared to nine UDA and seven SFDA methods. Furthermore, we experimentally validate that PrEPoA serves as a plug-and-play module that effectively incorporated into other SFDA methods.

Knowledge tagging for questions is vital in modern intelligent educational applications, including learning progress diagnosis, practice question recommendations, and course content organization. Traditionally, these annotations have been performed by pedagogical experts, as the task demands not only a deep semantic understanding of question stems and knowledge definitions but also a strong ability to link problem-solving logic with relevant knowledge concepts. With the advent of advanced natural language processing (NLP) algorithms, such as pre-trained language models and large language models (LLMs), pioneering studies have explored automating the knowledge tagging process using various machine learning models. In this paper, we investigate the use of a multi-agent system to address the limitations of previous algorithms, particularly in handling complex cases involving intricate knowledge definitions and strict numerical constraints. By demonstrating its superior performance on the publicly available math question knowledge tagging dataset, MathKnowCT, we highlight the significant potential of an LLM-based multi-agent system in overcoming the challenges that previous methods have encountered. Finally, through an in-depth discussion of the implications of automating knowledge tagging, we underscore the promising future of deploying LLM-based algorithms in educational contexts.

Urban socioeconomic indicator prediction aims to infer various metrics related to sustainable development in diverse urban landscapes using data-driven methods. However, prevalent pretrained models, particularly those reliant on satellite imagery, face dual challenges. Firstly, concentrating solely on macro-level patterns from satellite data may introduce bias, lacking nuanced details at micro levels, such as architectural details at a place. Secondly, the text generated by the precursor work UrbanCLIP, which fully utilizes the extensive knowledge of LLMs, frequently exhibits issues such as hallucination and homogenization, resulting in a lack of reliable quality. In response to these issues, we devise a novel framework entitled UrbanVLP based on Vision-Language Pretraining. Our UrbanVLP seamlessly integrates multi-granularity information from both macro (satellite) and micro (street-view) levels, overcoming the limitations of prior pretrained models. Moreover, it introduces automatic text generation and calibration, providing a robust guarantee for producing high-quality text descriptions of urban imagery. Rigorous experiments conducted across six socioeconomic indicator prediction tasks underscore its superior performance.

Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.

Students frequently make mistakes while solving mathematical problems, and traditional error correction methods are both time-consuming and labor-intensive. This paper introduces an innovative Virtual AI Teacher system designed to autonomously analyze and correct student Errors (VATE). Leveraging advanced large language models (LLMs) like GPT-4, the system uses student drafts as a primary source for error analysis, which enhances understanding of the student's learning process. It incorporates sophisticated prompt engineering and maintains an error pool to reduce computational overhead. The AI-driven system also features a real-time dialogue component for efficient student interaction. Our approach demonstrates significant advantages over traditional and machine learning-based error correction methods, including reduced educational costs, high scalability, and superior generalizability. The system has been deployed in Squirrel AI's learning platform for elementary mathematics education, where it achieves 78.3% accuracy in error analysis and shows a marked improvement in student learning efficiency. Satisfaction surveys indicate a strong positive reception, highlighting the system's potential to transform educational practices.

Hang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu, Yanling Chen, Yichi Song, Qingsong Wen, Hui Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Hanjun Luo, Yingbin Jin, Yiran Wang, Xinfeng Li, Tong Shang, Xuecheng Liu, Ruizhe Chen, Kun Wang, Hanan Salam, Qingsong Wen, Zuozhu Liu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Jingheng Ye, Shen Wang, Deqing Zou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Ruitong Liu, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

To ensure high-quality communication, it’s of great value to use digital pre-distortion (DPD) to linearize the core component power amplifier (PA) of terahertz/mmWave transceiver. In this work, we propose transfer learning with Transformer and LSTM for DPD of terahertz/mmWave transceiver, which uses Transformer based PA behavioral model to train effective and lightweight LSTM model for DPD. To collect and analyze the signal data of terahertz/mmWave transceiver, we set up a physical platform for the D-band system. Through experiments, we show that the proposed method is capable of significantly reducing in-band and out-band distortion while avoiding the excessive complexity of DPD models.

Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the real world, including: 1) small data scale leads to a large performance variance; 2) reliance on model-based annotations results in restricted data quality; 3) insufficient task difficulty, especially caused by the limited image resolution. To tackle these issues, we introduce MME-RealWorld. Specifically, we collect more than $300$ K images from public datasets and the Internet, filtering $13,366$ high-quality images for annotation. This involves the efforts of professional $25$ annotators and $7$ experts in MLLMs, contributing to $29,429$ question-answer pairs that cover $43$ subtasks across $5$ real-world scenarios, extremely challenging even for humans. As far as we know, **MME-RealWorld is the largest manually annotated benchmark to date, featuring the highest resolution and a targeted focus on real-world applications**. We further conduct a thorough evaluation involving $29$ prominent MLLMs, such as GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Our results show that even the most advanced models struggle with our benchmarks, where none of them reach 60\% accuracy. The challenges of perceiving high-resolution images and understanding complex real-world scenarios remain urgent issues to be addressed. The data and evaluation code are released in our Project Page.

In this paper, we use the Fire Dynamics Simulator (FDS) combined with the {\fontfamily{lmtt}\selectfont \textit{supercomputer}} support to create a \textbf{C}ombustion \textbf{K}inetics (CK) dataset for machine learning and scientific research. This dataset captures the development of fires in industrial parks with high-precision Computational Fluid Dynamics (CFD) simulations. It includes various physical fields such as temperature and pressure, and covers multiple environmental combinations for exploring \underline{multi-physics} field coupling phenomena. Additionally, we evaluate several advanced machine learning architectures across our {\fontfamily{lmtt}\selectfont {Open-CK}} benchmark using a substantial computational setup of 64 NVIDIA A100 GPUs: \ding{182} vision backbone; \ding{183} spatio-temporal predictive models; \ding{184} operator learning frameworks. These architectures uniquely excel at handling complex physical field data. We also introduce three benchmarks to demonstrate their potential in enhancing the exploration of downstream tasks: (a) capturing continuous changes in combustion kinetics; (b) a neural partial differential equation solver for learning temperature fields and turbulence; (c) reconstruction of sparse physical observations. The Open-CK dataset and benchmarks aim to advance research in combustion kinetics driven by machine learning, providing a reliable baseline for developing and comparing cutting-edge technologies and models. We hope to further promote the application of deep learning in earth sciences. Our project is available at \url{https://github.com/whscience/Open-CK}.

Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications. In response, we introduce Time-MoE, a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models while reducing inference costs. By leveraging a sparse mixture-of-experts (MoE) design, Time-MoE enhances computational efficiency by activating only a subset of networks for each prediction, reducing computational load while maintaining high model capacity. This allows Time-MoE to scale effectively without a corresponding increase in inference costs. Time-MoE comprises a family of decoder-only transformer models that operate in an auto-regressive manner and support flexible forecasting horizons with varying input context lengths. We pre-trained these models on our newly introduced large-scale data Time-300B, which spans over 9 domains and encompassing over 300 billion time points. For the first time, we scaled a time series foundation model up to 2.4 billion parameters, achieving significantly improved forecasting precision. Our results validate the applicability of scaling laws for training tokens and model size in the context of time series forecasting. Compared to dense models with the same number of activated parameters or equivalent computation budgets, our models consistently outperform them by large margin. These advancements position Time-MoE as a state-of-the-art solution for tackling real-world time series forecasting challenges with superior capability, efficiency, and flexibility. Code is available at https://github.com/Time-MoE/Time-MoE

Accurate weather forecasts are important for disaster prevention, agricultural planning, etc. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive and fail to fully leverage rapidly growing historical data. In recent years, deep learning models have made significant progress in weather forecasting, but challenges remain, such as balancing global and regional high-resolution forecasts, excessive smoothing in extreme event predictions, and insufficient dynamic system modeling. To address these issues, this paper proposes a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks. By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region to capture local high-frequency features. We introduce an adaptive messaging mechanism, using dynamic gating units to deeply integrate node and edge features for more accurate extreme event forecasting. For high-resolution regional forecasts, we propose a neural nested grid method to mitigate boundary information loss. Experimental results show that OneForecast performs excellently across global to regional scales and short-term to long-term forecasts, especially in extreme event predictions. Codes link: \url{https://github.com/YuanGao-YG/OneForecast}.

Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely, vision captures intricate temporal patterns but lacks semantic context, limiting the complementary potential of these modalities. To address this, we propose Time-VLM, a novel multimodal framework that leverages pre-trained Vision-Language Models (VLMs) to bridge temporal, visual, and textual modalities for enhanced forecasting. Our framework comprises three key components: (1) a Retrieval-Augmented Learner, which extracts enriched temporal features through memory bank interactions; (2) a Vision-Augmented Learner, which encodes time series as informative images; and (3) a Text-Augmented Learner, which generates contextual textual descriptions. These components collaborate with frozen pre-trained VLMs to produce multimodal embeddings, which are then fused with temporal features for final prediction. Extensive experiments demonstrate that Time-VLM achieves superior performance, particularly in few-shot and zero-shot scenarios, thereby establishing a new direction for multimodal time series forecasting. Code is available at https://github.com/CityMind-Lab/ICML25-TimeVLM.

The inherent non-stationarity of time series in practical applications poses significant challenges for accurate forecasting. This paper tackles the concept drift problem where the underlying distribution or environment of time series changes. To better describe the characteristics and effectively model concept drifts, we first classify them into macro-drift (stable, long-term changes) and micro-drift (sudden, short-term fluctuations). Next, we propose a unified meta-learning framework called LEAF (Learning to Extrapolate and Adjust for Forecasting), where an extrapolation module is first introduced to track and extrapolate the prediction model in latent space considering macro-drift, and then an adjustment module incorporates meta-learnable surrogate loss to capture sample-specific micro-drift patterns. LEAF’s dual-stage approach effectively addresses diverse concept drifts and is model-agnostic which can be compatible with any deep prediction model. We further provide theoretical analysis to justify why the proposed framework can handle macro-drift and micro-drift. To facilitate further research in this field, we release three electric load time series datasets collected from real-world scenarios, exhibiting diverse and typical concept drifts. Extensive experiments on multiple datasets demonstrate the effectiveness of LEAF.

Missing values are ubiquitous in multivariate time series (MTS) data, posing significant challenges for accurate analysis and downstream applications. In recent years, deep learning-based methods have successfully handled missing data by leveraging complex temporal dependencies and learned data distributions. In this survey, we provide a comprehensive summary of deep learning approaches for multivariate time series imputation (MTSI) tasks. We propose a novel taxonomy that categorizes existing methods based on two key perspectives: imputation uncertainty and neural network architecture. Furthermore, we summarize existing MTSI toolkits with a particular emphasis on the PyPOTS Ecosystem, which provides an integrated and standardized foundation for MTSI research. Finally, we discuss key challenges and future research directions, which give insight for further MTSI research. This survey aims to serve as a valuable resource for researchers and practitioners in the field of time series analysis and missing data imputation tasks. A well-maintained MTSI paper and tool list is available at https://github.com/WenjieDu/Awesome_Imputation.

Many real-world applications contain data in the form of multivariate time series (TS) with the hierarchical structure, where classic methods forecasting each TS independently are inadequate for coherency (i.e., satisfying the hierarchical aggregation constraints).Furthermore, the discrepancies between statistical properties of different levels can be huge, exacerbated by non-Gaussian distributions and non-linear correlations.In this paper, we propose a novel end-to-end hierarchical TS forecasting model, i.e., a Flow-based Reconcile Transformer (FRT).FRT employs a conditional normalizing flow-based autoregressive transformer, to represent complex data distribution, while simultaneously reconciling the forecasts to ensure coherency.Go beyond other state-of-the-art methods, FRT accomplishes forecasting and reconciliation simultaneously, while avoiding any post-processing steps.Moreover, FRT is a deep model that does not rely on any strong assumptions such as unbiased estimates or Gaussian distribution.Our experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of our company's data center) and the results demonstrate the efficacy of our proposed method.Our method has been implemented extensively within the production environments of a prominent global payment company.It has emerged as a cornerstone for workload forecasting within their data center and plays a critical role in the optimization of cloud computing resource allocation across * Both authors contributed equally to this research.

Recently, frequency transformation (FT) has been increasingly incorporated into deep learning models to significantly enhance state-of-the-art accuracy and efficiency in time series analysis. The advantages of FT, such as high efficiency and a global view, have been rapidly explored and exploited in various time series tasks and applications, demonstrating the promising potential of FT as a new deep learning paradigm for time series analysis. Despite the growing attention and the proliferation of research in this emerging field, there is currently a lack of a systematic review and in-depth analysis of deep learning-based time series models with FT. It is also unclear why FT can enhance time series analysis and what its limitations are in the field. To address these gaps, we present a comprehensive review that systematically investigates and summarizes the recent research advancements in deep learning-based time series analysis with FT. Specifically, we explore the primary approaches used in current models that incorporate FT, the types of neural networks that leverage FT, and the representative FT-equipped models in deep time series analysis. We propose a novel taxonomy to categorize the existing methods in this field, providing a structured overview of the diverse approaches employed in incorporating FT into deep learning models for time series analysis. Finally, we highlight the advantages and limitations of FT for time series modeling and identify potential future research directions that can further contribute to the community of time series analysis.

Spatio-Temporal (ST) data science, which includes sensing, managing, and mining large-scale data across space and time, is fundamental to understanding complex systems in domains such as urban computing, climate science, and intelligent transportation. Traditional deep learning approaches have significantly advanced this field, particularly in the stage of ST data mining. However, these models remain task-specific and often require extensive labeled data. Inspired by the success of Foundation Models (FM), especially large language models, researchers have begun exploring the concept of Spatio-Temporal Foundation Models (STFMs) to enhance adaptability and generalization across diverse ST tasks. Unlike prior architectures, STFMs empower the entire workflow of ST data science, ranging from data sensing, management, to mining, thereby offering a more holistic and scalable approach. Despite rapid progress, a systematic study of STFMs for ST data science remains lacking. This survey aims to provide a comprehensive review of STFMs, categorizing existing methodologies and identifying key research directions to advance ST general intelligence.

The proposed ''SciSoc LLM Workshop: Large Language Models for Scientific and Societal Advances'' aims to explore the profound implications and potential of Large Language Models (LLMs) in driving forward scientific inquiry and addressing critical societal challenges. As LLMs such as GPT-4 continue to redefine boundaries in both complexity and capability, their integration into the scientific and societal domains is not just beneficial but essential. In particular, LLMs have demonstrated substantial value in improving our understanding of complex datasets and generating insights across various fields such as healthcare, environmental science, education, and public policy. By bringing together experts and enthusiasts from diverse fields, the workshop aims to foster a comprehensive understanding of how LLMs can redefine traditional research methodologies. Participants will explore innovative ways to harness the power of LLMs for greater efficiency and innovation in their respective fields, potentially catalyzing a new era of scientific and societal advancement.

Accurate periodicity detection of performance metrics in cloud platform is essential for enhancing monitoring accuracy and ensure service quality of cloud computing. However, in real-world industrial settings, such as large-scale cloud computing platform MaxCompute at Alibaba Cloud, performance metrics often exhibit complex multi-periodicity and temporal nonstationarity. Additionally, these metrics are frequently contaminated by noise and anomalies, rendering traditional periodicity detection methods ineffective. To address these challenges, this paper proposes a robust and general period detection method with low deployment cost and high usability. The method employs Empirical Mode Decomposition (EMD) to decompose complex time series into Intrinsic Mode Functions (IMFs), isolating noise, periodic, and trend components. Significant periods are identified using statistical tests to eliminate irrelevant components, while an automatic clustering mechanism mitigates the mode-mixing problem inherent in EMD. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method outperforms state-of-the-art periodicity detection techniques, achieving over 10% and 17% performance improvements in public single and multiple periodicity detection tasks, respectively. Deployed in Alibaba Cloud's MaxCompute platform, it monitors millions of tasks, resulting in a 7.8% increase in fault detection coverage and enabling faults to be detected 13.15% more rapidly. The method's low deployment cost and user-friendly implementation make it highly accessible and practical for diverse cloud monitoring applications.

A supply chain is the network of entities and processes involved in the production and distribution of a commodity. Supply chains are a critical backbone across industries like retail, manufacturing, healthcare, and automotive, driving everything from product availability to operational efficiency and customer satisfaction. Modern supply chains are 1) non-cooperative, functioning as fragmented systems where isolated technologies solve individual problems without integration, and 2) unadaptable, failing to adjust to real-time data and uncertainties, like demand fluctuations and regulatory changes. As a result, frequent manual overrides are required, as even small errors can lead to significant financial losses, strained customer relationships, or reputational damage. Modern Artificial Intelligence (AI) advancements offer great potential to unify fragmented supply chains into a seamless, adaptive system while enhancing automation, decision-making, and transparency. In this workshop, we will examine critical supply chain challenges and demonstrate how AI can provide accurate, efficient, and scalable solutions.

Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods.Deep learning (DL) models offer efficiency and accuracy but often ignore physical laws, limiting interpretability and generalization.We propose PhyDL-NWP, a physicsguided deep learning framework that integrates physical equations with latent force parameterization into data-driven models.It predicts weather variables from arbitrary spatiotemporal coordinates, computes physical terms via automatic differentiation, and uses a physics-informed loss to align predictions with governing dynamics.PhyDL-NWP enables resolution-free downscaling by modeling weather as a continuous function and fine-tunes pre-trained models with minimal overhead, achieving up to 170× faster inference with only 55K parameters.Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.

Time series data is now pervasive across domains such as healthcare, finance, entertainment, and transportation, driven by advances in sensing technologies that enable continuous data collection. The resulting increase in data volume and complexity poses significant challenges to traditional analysis methods, calling for the development of advanced, interdisciplinary approaches to temporal data mining. This workshop aims to: (1) identify key challenges in learning from time series data, including irregular sampling, spatiotemporal dependencies, and uncertainty quantification; (2) explore recent advances in algorithmic, statistical, theoretical, and systems-based solutions-ranging from classical methods to emerging techniques involving large language models (LLMs); and (3) foster collaboration by highlighting open problems and novel research directions in time series analysis. Bridging theory and practice, the workshop provides a platform for researchers and practitioners from academia, industry, and government to exchange ideas, discuss technical challenges, and showcase practical applications. Contributions from related areas such as AI, machine learning, data science, and statistics are strongly encouraged.

Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal events with segments of time points) and unlabeled data (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, the huge label information gap between training data and targets makes the task challenging. In this study, we formulate the above imperfect information as noisy labels and propose NRdetector, a noise-resilient framework that incorporates confidence-based sample selection, robust segment-level learning, and data-centric point-level detection for multivariate time series anomaly detection. Particularly, to bridge the information gap between noisy segment-level labels and missing point-level labels, we develop a novel loss function that can effectively mitigate the label noise and consider the temporal features. It encourages the smoothness of consecutive points and the separability of points from segments with different labels. Extensive experiments on real-world multivariate time series datasets with 11 different evaluation metrics demonstrate that NRdetector consistently achieves robust results across multiple real-world datasets, outperforming various baselines adapted to operate in our setting.

The field of information retrieval has significantly transformed with the integration of AI technologies. AI agents, especially those leveraging LLMs and vast computational power, have revolutionized in- formation retrieval, processing, and presentation. LLM agents, with advanced memory, reasoning, and planning capabilities, can perform complex tasks, engage in coherent conversations, and provide personalized responses. Despite these advancements, challenges such as ensuring relevance and accuracy, mitigating biases, providing real-time responses, and maintaining data security remain. This workshop aims to explore these challenges, share innovative solutions, and discuss future directions. It will provide a platform to bring together researchers and practitioners to discuss the latest theoretical advancements and practical implementations of AI agents in information retrieval. Topics include AI in search, recommendation, and personalization systems. By gathering a diverse group of experts, the workshop seeks to deepen the understanding of AI agents in information retrieval, advance the field, and enhance its societal impact. Participants will gain insights into cutting-edge research and emerging trends, and foster knowledge exchange and collaboration within the community.

The ever-increasing sensor service, though opening a precious path and providing a deluge of earth system data for deep-learning-oriented earth science, sadly introduce a daunting obstacle to their industrial level deployment. Concretely, earth science systems rely heavily on the extensive deployment of sensors, however, the data collection from sensors is constrained by complex geographical and social factors, making it challenging to achieve comprehensive coverage and uniform deployment. To alleviate the obstacle, traditional approaches to sensor deployment utilize specific algorithms to design and deploy sensors. These methods dynamically adjust the activation times of sensors to optimize the detection process across each sub-region. Regrettably, formulating an activation strategy generally based on historical observations and geographic characteristics, which make the methods and resultant models were neither simple nor practical. Worse still, the complex technical design may ultimately lead to a model with weak generalizability. In this paper, we introduce for the first time the concept of spatio-temporal data dynamic sparse training and are committed to adaptively, dynamically filtering important sensor distributions. To our knowledge, this is the first proposal (termed DynST) of an industry-level deployment optimization concept at the data level. However, due to the existence of the temporal dimension, pruning of spatio-temporal data may lead to conflicts at different timestamps. To achieve this goal, we employ dynamic merge technology, along with ingenious dimensional mapping to mitigate potential impacts caused by the temporal aspect. During the training process, DynST utilize iterative pruning and sparse training, repeatedly identifying and dynamically removing sensor perception areas that contribute the least to future predictions.

With the rapid evolution of Large Language Models (LLMs), LLMbased agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems.This evolution stems from empowering LLMs with additional modules such as memory, tools, environment, and even other agents.However, this advancement has also introduced more complex issues of trustworthiness, which previous research focusing solely on LLMs could not cover.In this survey, we propose the TrustAgent framework, a comprehensive study on the trustworthiness of agents, characterized by modular taxonomy, multi-dimensional connotations, and * Miao Yu and Fanci Meng contribute equally to this paper.

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image. Empirical experiments underscore the persistence of this bias, as MLLMs often provide confident answers even in the absence of relevant images or given incongruent visual inputs. To rectify these biases and redirect the model's focus toward visual information, we propose two simple, training-free strategies. First, for tasks such as classification or multi-choice question answering, we introduce a ''Post-Hoc Debias'' method using an affine calibration step to adjust the output distribution. This approach ensures uniform answer scores when the image is absent, acting as an effective regularization technique to alleviate the influence of LLM priors. For more intricate open-ended generation tasks, we extend this method to ''Visual Debias Decoding'', which mitigates bias by contrasting token log-probabilities conditioned on a correct image versus a meaningless one. Additionally, our investigation sheds light on the instability of MLLMs across various decoding configurations. Through systematic exploration of different settings, we achieve significant performance improvements-surpassing previously reported results-and raise concerns about the fairness of current evaluation practices. Comprehensive experiments substantiate the effectiveness of our proposed strategies in mitigating biases. These strategies not only prove beneficial in minimizing hallucinations but also contribute to the generation of more helpful and precise illustrations.

Spatio-temporal data mining (STDM) has become crucial in multimedia, driven by the surge of multimodal data from remote sensing, IoT sensors, social media, surveillance systems, mobile devices, and crowdsourced platforms. Traditional single-modal methods, though successful, struggle to capture real-world complexity. Integrating multiple modalities yields richer, more accurate insights, boosting spatio-temporal analysis. This half-day tutorial, MM4ST: Multimodal Learning for STDM, offers a comprehensive overview, covering STDM fundamentals, challenges in aligning and fusing heterogeneous data, advanced multimodal modeling techniques, and emerging research directions. Attendees will acquire practical knowledge to develop scalable and robust spatio-temporal mining solutions. All materials will be publicly available online.

Recent efficient sequence modeling methods, such as Gated DeltaNet, TTT, and RWKV-7, have achieved performance improvements by supervising the recurrent memory management through the Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear attentions (e.g., GLA), these models introduce interactions between the recurrent state and the key vector, resulting in a bilinear recursive structure. In this paper, we first introduce the concept of Bilinear RNNs with a comprehensive analysis on the advantages and limitations of these models. Then based on the closed-loop control theory, we propose a novel Bilinear RNN variant named Comba, which adopts a scalar-plus-low-rank state transition, with both state feedback and output feedback corrections. We also implement a hardware-efficient chunk-wise parallel kernel in Triton and train models with 340M/1.3B parameters on a large-scale corpus. Comba demonstrates its superior performance and computation efficiency on both language modeling and vision tasks.

Explaining time series classification models is crucial, particularly in high-stakes applications such as healthcare and finance, where transparency and trust play a critical role. Although numerous time series classification methods have identified key subsequences, known as shapelets, as core features for achieving state-of-the-art performance and validating their pivotal role in classification outcomes, existing post-hoc time series explanation (PHTSE) methods primarily focus on timestep-level feature attribution. These explanation methods overlook the fundamental prior that classification outcomes are predominantly driven by key shapelets. To bridge this gap, we present ShapeX, an innovative framework that segments time series into meaningful shapelet-driven segments and employs Shapley values to assess their saliency. At the core of ShapeX lies the Shapelet Describe-and-Detect (SDD) framework, which effectively learns a diverse set of shapelets essential for classification. We further demonstrate that ShapeX produces explanations which reveal causal relationships instead of just correlations, owing to the atomicity properties of shapelets. Experimental results on both synthetic and real-world datasets demonstrate that ShapeX outperforms existing methods in identifying the most relevant subsequences, enhancing both the precision and causal fidelity of time series explanations.

Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectively finetune TSFMs on specific downstream tasks. While naive finetuning can yield performance gains, we argue that it falls short of fully leveraging TSFMs' capabilities, often resulting in overfitting and suboptimal performance. Given the diverse temporal patterns across sampling scales and the inherent multi-scale forecasting capabilities of TSFMs, we adopt a causal perspective to analyze finetuning process, through which we highlight the critical importance of explicitly modeling multiple scales and reveal the shortcomings of naive approaches. Focusing on encoder-based TSFMs, we propose Multiscale finetuning (MSFT), a simple yet general framework that explicitly integrates multi-scale modeling into the finetuning process. Experimental results on three different backbones (Moirai, Moment and Units) demonstrate that TSFMs finetuned with MSFT not only outperform naive and typical parameter efficient finetuning methods but also surpass state-of-the-art deep learning methods. Codes are available at https://github.com/zqiao11/MSFT.

Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance. Although various self-correction methods have been proposed, a comprehensive evaluation of these methods remains largely unexplored, and the question of whether LLMs can truly correct themselves is a matter of significant interest and concern. In this study, we introduce CorrectBench, a benchmark developed to evaluate the effectiveness of self-correction strategies, including intrinsic, external, and fine-tuned approaches, across three tasks: commonsense reasoning, mathematical reasoning, and code generation. Our findings reveal that: 1) Self-correction methods can improve accuracy, especially for complex reasoning tasks; 2) Mixing different self-correction strategies yields further improvements, though it reduces efficiency; 3) Reasoning LLMs (e.g., DeepSeek-V3) have limited optimization under additional self-correction methods and have high time costs. Interestingly, a comparatively simple chain-of-thought (CoT) baseline demonstrates competitive accuracy and efficiency. These results underscore the potential of self-correction to enhance LLM's reasoning performance while highlighting the ongoing challenge of improving their efficiency. Consequently, we advocate for further research focused on optimizing the balance between reasoning capabilities and operational efficiency.

Watermarking LLM-generated text is critical for content attribution and misinformation prevention, yet existing methods compromise text quality and require white-box model access with logit manipulation or training, which exclude API-based models and multilingual scenarios. We propose SAEMark, an **inference-time framework** for *multi-bit* watermarking that embeds personalized information through *feature-based rejection sampling*, fundamentally different from logit-based or rewriting-based approaches: we **do not modify model outputs directly** and require only **black-box access**, while naturally supporting multi-bit message embedding and generalizing across diverse languages and domains. We instantiate the framework using *Sparse Autoencoders* as deterministic feature extractors and provide theoretical worst-case analysis relating watermark accuracy to computational budget. Experiments across 4 datasets demonstrate strong watermarking performance on English, Chinese, and code while preserving text quality. SAEMark establishes a new paradigm for **scalable, quality-preserving watermarks** that work seamlessly with closed-source LLMs across languages and domains.

To meet the demand for high-speed and high-quality communication in next 6G satellite communication, it is very necessary and urgent to study the behavioral modeling of 6G satellite communication power amplifiers (PAs). In satellite communication, PAs face the situation of high dynamic and wide bandwidth and exhibit strong nonlinearity and strong memory effects. In this case, we need to study Transformer architectures that can better handle long sequence data and further explore the inherent characteristics of the PA signal data. In this article, we propose a behavioral modeling method of PAs named augmented real-valued time-delay transformer (ARVTDform). ARVTDform is an augmented transformer-based method, which can capture long-range dependencies between the PA signal data and has powerful nonlinear modeling capabilities. To simulate the working status of the satellite PAs, we set up two physical platforms and collect and analyze twelve datasets. To the best of our knowledge, this is the first time real satellite data has been used for behavioral modeling. Extensive experiments on the collected datasets further demonstrate that our transformer-based method is more suitable for handing PAs with strong nonlinearity and strong memory effects in terms of normalized mean square error (NMSE). Finally, we discuss the major challenge and list the potential future work that may contribute to the sustained development of high-performance transceivers.

Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and their expressive power is bounded by our extended first-order Weisfeiler-Leman algorithm on discrete-time dynamic graphs. To make our findings useful in practice on valid instantiations, we discuss related constraints in detail and outline a theoretical blueprint for designing spatial and temporal modules in spectral domains. Building on these insights and to demonstrate how powerful spectral-temporal GNNs are based on our framework, we propose a simple instantiation named Temporal Graph Gegenbauer Convolution (TGGC), which significantly outperforms most existing models with only linear components and shows better model efficiency.

In practical scenarios, time series forecasting necessitates not only accuracy but also efficiency. Consequently, the exploration of model architectures remains a perennially trending topic in research. To address these challenges, we propose a novel backbone architecture named Time Evidence Fusion Network (TEFN) from the perspective of information fusion. Specifically, we introduce the Basic Probability Assignment (BPA) Module based on evidence theory to capture the uncertainty of multivariate time series data from both channel and time dimensions. Additionally, we develop a novel multi-source information fusion method to effectively integrate the two distinct dimensions from BPA output, leading to improved forecasting accuracy. Lastly, we conduct extensive experiments to demonstrate that TEFN achieves performance comparable to state-of-the-art methods while maintaining significantly lower complexity and reduced training time. Also, our experiments show that TEFN exhibits high robustness, with minimal error fluctuations during hyperparameter selection. Furthermore, due to the fact that BPA is derived from fuzzy theory, TEFN offers a high degree of interpretability. Therefore, the proposed TEFN balances accuracy, efficiency, stability, and interpretability, making it a desirable solution for time series forecasting.

In time series anomaly detection (TSAD), the scarcity of labeled data poses a challenge to the development of accurate models. Unsupervised domain adaptation (UDA) offers a solution by leveraging labeled data from a related domain to detect anomalies in an unlabeled target domain. However, existing UDA methods assume consistent anomalous classes across domains. To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness. Additionally, our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain, ensuring comprehensive feature representation learning and domain-invariant feature extraction. Finally, an effective Center-based Entropy Classifier (CEC) accurately learns normal boundaries in the source domain. Extensive evaluations on multiple real-world datasets and a synthetic dataset highlight DACAD's superior performance in transferring knowledge across domains and mitigating the challenge of limited labeled data in TSAD.

Large language model (LLM) applications in cloud root cause analysis (RCA) have been actively explored recently. However, current methods are still reliant on manual workflow settings and do not unleash LLMs' decision-making and environment interaction capabilities. We present RCAgent, a tool-augmented LLM autonomous agent framework for practical and privacy-aware industrial RCA usage. Running on an internally deployed model rather than GPT families, RCAgent is capable of free-form data collection and comprehensive analysis with tools. Our framework combines a variety of enhancements, including a unique Self-Consistency for action trajectories, and a suite of methods for context management, stabilization, and importing domain knowledge. Our experiments show RCAgent's evident and consistent superiority over ReAct across all aspects of RCA--predicting root causes, solutions, evidence, and responsibilities--and tasks covered or uncovered by current rules, as validated by both automated metrics and human evaluations. Furthermore, RCAgent has already been integrated into the diagnosis and issue discovery workflow of the Real-time Compute Platform for Apache Flink of Alibaba Cloud.

The field of information retrieval has significantly transformed with the integration of AI technologies. AI agents, especially those leveraging LLMs and vast computational power, have revolutionized information retrieval, processing, and presentation. LLM agents, with advanced memory, reasoning, and planning capabilities, can perform complex tasks, engage in coherent conversations, and provide personalized responses. Despite these advancements, challenges such as ensuring relevance and accuracy, mitigating biases, providing real-time responses, and maintaining data security remain. This workshop aims to explore these challenges, share innovative solutions, and discuss future directions. It will provide a platform to bring together researchers, practitioners to discuss the latest theoretical advancements and practical implementations of AI agents in information retrieval. Topics include AI in search, recommendation, and personalization systems. By gathering a diverse group of experts, the workshop seeks to deepen the understanding of AI agents in information retrieval, advance the field, and enhance its societal impact. Participants will gain insights into cutting-edge research, emerging trends, and foster knowledge exchange and collaboration within the community.

Time series anomaly detection is of significant importance in many real-world applications, including finance, healthcare, network security, industrial equipment, complex computing systems, and space probes. Most of these applications involve multi-sensor systems, thus how to perform multivariate time series anomaly detection (MTSAD) has garnered widespread attention. This broad attention has fueled extensive research endeavors aimed to innovate and develop methods and techniques to improve the efficiency and precision of anomaly detection on multivariate time series data, including both classic machine learning methods and deep learning methods. However, evaluating the performance of these methods remains challenging due to the limited availability of public benchmark datasets for MTSAD, which are often criticized for various reasons. Additionally, there is no consensus on the best metrics for time series anomaly detection, further complicating MTSAD research. In this paper, we advance the benchmarking of time series anomaly detection by addressing datasets, evaluation metrics, and algorithm comparison. To the best of our knowledge, we have generated the largest real-world datasets for MTSAD using the Hologres AIOps system in the Alibaba Cloud platform. We review and compare popular evaluation metrics including recently proposed ones. To evaluate classic machine learning and recent deep learning methods fairly, we have conducted extensive comparisons of these methods on various datasets. We believe that our benchmarks and datasets will promote reproducible results and accelerate the progress of MTSAD research.

Time series forecasting is a critical and challenging task in practical application. Recent advancements in pre-trained foundation models for time series forecasting have gained significant interest. However, current methods often overlook the multi-scale nature of time series, which is essential for accurate forecasting. To address this, we propose HiMTM, a hierarchical multi-scale masked time series modeling with self-distillation for long-term forecasting. HiMTM integrates four key components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales; (2) decoupled encoder-decoder (DED) that directs the encoder towards feature extraction while the decoder focuses on pretext tasks; (3) hierarchical self-distillation (HSD) for multi-stage feature-level supervision signals during pre-training; and (4) cross-scale attention fine-tuning (CSA-FT) to capture dependencies between different scales for downstream tasks. These components collectively enhance multi-scale feature extraction in masked time series modeling, improving forecasting accuracy. Extensive experiments on seven mainstream datasets show that HiMTM surpasses state-of-the-art self-supervised and end-to-end learning methods by a considerable margin of 3.16-68.54%. Additionally, HiMTM outperforms the latest robust self-supervised learning method, PatchTST, in cross-domain forecasting by a significant margin of 2.3%. The effectiveness of HiMTM is further demonstrated through its application in natural gas demand forecasting.

Self-supervised learning (SSL) shows impressive performance in many tasks lacking sufficient labels. In this paper, we study SSL in time series anomaly detection (TSAD) by incorporating the characteristics of time series data. Specifically, we build an anomaly detection algorithm consisting of global pattern learning and local association learning. The global pattern learning module builds encoder and decoder to reconstruct the raw time series data to detect global anomalies. To complement the limitation of the global pattern learning that ignores local associations between anomaly points and their adjacent windows, we design a local association learning module, which leverages contrastive predictive coding (CPC) to transform the identification of anomaly points into positive pairs identification. Motivated by the observation that adjusting the distance between the history window and the time point to be detected directly impacts the detection performance in the CPC framework, we further propose a skip-step CPC scheme in the local association learning module which adjusts the distance for better construction of the positive pairs and detection results. The experimental results show that the proposed algorithm achieves superior performance on SMD and PSM datasets in comparison with 12 state-of-the-art algorithms.

Variance estimation has been one of the key challenges in time series analysis for a long time. Although many ARCHtype algorithms are widely applied in variance estimation, they suffer from sensitivity to outliers and fail to handle complex data such as abrupt trend change and variance periodicity. The time warping of the periodicity makes it further complicated. To deal with these challenges, we propose a robust algorithm called RobustTSVar, based on quantile regression for robust variance estimation. To deal with variance periodicity with time warping, we propose non-local periodic filtering to further refine the variance estimate. An efficient implementation based on ADMM is also proposed to handle large-scale data. We compare our proposed RobustTSVar method with other state-of-the-art methods on both synthetic and real-world datasets, and the numerical results demonstrate the superior performance of our algorithm.

Anomaly detection significantly enhances the robustness of cloud systems. While neural network-based methods have recently demonstrated strong advantages, they encounter practical challenges in cloud environments: the contradiction between the impracticality of maintaining a unique model for each service and the limited ability to deal with diverse normal patterns by a unified model, as well as issues with handling heavy traffic in real time and short-term anomaly detection sensitivity. Thus, we propose MACE, a multi-normal-pattern accommodated and efficient anomaly detection method in the frequency domain for time series anomaly detection. There are three novel characteristics of it: (i) a pattern extraction mechanism excelling at handling diverse normal patterns with a unified model, which enables the model to identify anomalies by examining the correlation between the data sample and its service normal pattern, instead of solely focusing on the data sample itself; (ii) a dualistic convolution mechanism that amplifies short-term anomalies in the time domain and hinders the reconstruction of anomalies in the frequency domain, which enlarges the reconstruction error disparity between anomaly and normality and facilitates anomaly detection; (iii) leveraging the sparsity and parallelism of frequency domain to enhance model efficiency. We theoretically and experimentally prove that using a strategically selected subset of Fourier bases can not only reduce computational overhead but is also profitable to distinguish anomalies, compared to using the complete spectrum. Moreover, extensive experiments demonstrate MACE's effectiveness in handling diverse normal patterns with a unified model and it achieves state-of-the-art performance with high efficiency.

Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks, models for time series forecasting are often specialized, necessitating distinct designs for different tasks and applications. While pre-trained foundation models have made impressive strides in NLP and CV, their development in time series domains has been constrained by data sparsity. Recent studies have revealed that large language models (LLMs) possess robust pattern recognition and reasoning abilities over complex sequences of tokens. However, the challenge remains in effectively aligning the modalities of time series data and natural language to leverage these capabilities. In this work, we present Time-LLM, a reprogramming framework to repurpose LLMs for general time series forecasting with the backbone language models kept intact. We begin by reprogramming the input time series with text prototypes before feeding it into the frozen LLM to align the two modalities. To augment the LLM's ability to reason with time series data, we propose Prompt-as-Prefix (PaP), which enriches the input context and directs the transformation of reprogrammed input patches. The transformed time series patches from the LLM are finally projected to obtain the forecasts. Our comprehensive evaluations demonstrate that \method is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models. Moreover, Time-LLM excels in both few-shot and zero-shot learning scenarios. The code is made available at https://github.com/KimMeen/Time-LLM.

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.

Time series forecasting is an important and forefront task whose techniques have been applied to electricity forecasting, trajectory prediction, labor planning, etc. However, most of time series forecasting techniques assume that the training data is clean without anomalies. This assumption is unrealistic since the collected time series data can be contaminated in practice. The forecasting model will be inferior if it is directly trained by time series with anomalies. Thus it is essential to develop methods to automatically learn a robust forecasting model from the contaminated data. In this paper, we first statistically define three types of anomalies, then theoretically and experimentally analyze the loss robustness and sample robustness when these anomalies exist. Based on our analyses, we propose a simple and efficient algorithm to learn a robust forecasting model. Extensive experiments show that our method is highly robust and outperforms all existing approaches. The code is available at https://github.com/haochenglouis/RobustTSF.

Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbation may not alleviate the distribution shift issue, which is inevitable especially in heterogeneous samples. We present ContraLSP, a locally sparse model that introduces counterfactual samples to build uninformative perturbations but keeps distribution using contrastive learning. Furthermore, we incorporate sample-specific sparse gates to generate more binary-skewed and smooth masks, which easily integrate temporal trends and select the salient features parsimoniously. Empirical studies on both synthetic and real-world datasets show that ContraLSP outperforms state-of-the-art models, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/ContraLSP}.

Recent studies have demonstrated the great power of Transformer models for time series forecasting. One of the key elements that lead to the transformer's success is the channel-independent (CI) strategy to improve the training robustness. However, the ignorance of the correlation among different channels in CI would limit the model's forecasting capacity. In this work, we design a special Transformer, i.e., **C**hannel **A**ligned **R**obust Blen**d** Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals and dynamical dependence among multiple variables over time. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue. This new loss function weights the importance of forecasting over a finite horizon based on prediction uncertainties. Our evaluation of multiple long-term and short-term forecasting datasets demonstrates that CARD significantly outperforms state-of-the-art time series forecasting methods. The code is available at the following repository: https://github.com/wxie9/CARD.

Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts. The code and data are available at \url{https://github.com/ant-research/EasyTemporalPointProcess}.

Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution shifts, conventional model evaluation encounters limitations in calculating performance metrics (e.g., test error) and measuring graph data-level discrepancies, particularly when the training graph used for developing GNNs remains unobserved during test time. In this paper, we study a new research problem, online GNN evaluation, which aims to provide valuable insights into the well-trained GNNs's ability to effectively generalize to real-world unlabeled graphs under the test-time graph distribution shifts. Concretely, we develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models. Through a novel GNN re-training strategy with a parameter-free optimality criterion, the proposed LeBeD comprehensively integrates learning behavior discrepancies from both node prediction and structure reconstruction perspectives. This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation. Extensive experiments on real-world test graphs under diverse graph distribution shifts could verify the effectiveness of the proposed method, revealing its strong correlation with ground-truth test errors on various well-trained GNN models.

Time series analysis is essential for comprehending the complexities inherent in various real-world systems and applications. Although large language models (LLMs) have recently made significant strides, the development of artificial general intelligence (AGI) equipped with time series analysis capabilities remains in its nascent phase. Most existing time series models heavily rely on domain knowledge and extensive model tuning, predominantly focusing on prediction tasks. In this paper, we argue that current LLMs have the potential to revolutionize time series analysis, thereby promoting efficient decision-making and advancing towards a more universal form of time series analytical intelligence. Such advancement could unlock a wide range of possibilities, including time series modality switching and question answering. We encourage researchers and practitioners to recognize the potential of LLMs in advancing time series analysis and emphasize the need for trust in these related efforts. Furthermore, we detail the seamless integration of time series analysis with existing LLM technologies and outline promising avenues for future research.

In real-world scenarios such as traffic and energy management, we frequently encounter large volumes of time-series data characterized by missing values, noise, and irregular sampling patterns. While numerous imputation methods have been proposed, the majority tend to operate within a local horizon, which involves dividing long sequences into batches of fixed-length segments for model training. This local horizon often leads to the overlooking of global trends and periodic patterns. More importantly, most methods assume the observations are sampled at regular timestamps, and fail to handle complex irregular sampled time series in various applications. Additionally, most existing methods are learned in an offline manner. Thus, it is not suitable for applications with rapidly arriving streaming data. To address these challenges, we propose BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decomposition. Our method conceptualizes multivariate time series as the weighted combination of groups of low-rank temporal factors with different patterns. We employ a suite of Gaussian Processes (GPs),each with a unique kernel, as functional priors to model these factors. For computational efficiency, we further convert the GPs into a state-space prior by constructing an equivalent stochastic differential equation (SDE), and developing a scalable algorithm for online inference. The proposed method can not only handle imputation over arbitrary timestamps, but also offer uncertainty quantification and interpretability for the downstream application. We evaluate our method on both synthetic and real-world datasets. We release the code at https://github.com/xuangu-fang/BayOTIDE.

Slow task detection is a critical problem in cloud operation and maintenance since it is highly related to user experience and can bring substantial liquidated damages. Most anomaly detection methods detect it from a single-task aspect. However, considering millions of concurrent tasks in large-scale cloud computing clusters, it becomes impractical and inefficient. Moreover, single-task slowdowns are very common and do not necessarily indicate a malfunction of a cluster due to its violent fluctuation nature in a virtual environment. Thus, we shift our attention to cluster-wide task slowdowns by utilizing the duration time distribution of tasks across a cluster, so that the computation complexity is not relevant to the number of tasks. The task duration time distribution often exhibits compound periodicity and local exceptional fluctuations over time. Though transformer-based methods are one of the most powerful methods to capture these time series normal variation patterns, we empirically find and theoretically explain the flaw of the standard attention mechanism in reconstructing subperiods with low amplitude when dealing with compound periodicity. To tackle these challenges, we propose SORN (i.e., Skimming Off subperiods in descending amplitude order and Reconstructing Non-slowing fluctuation), which consists of a Skimming Attention mechanism to reconstruct the compound periodicity and a Neural Optimal Transport module to distinguish cluster-wide slowdowns from other exceptional fluctuations. Furthermore, since anomalies in the training set are inevitable in a practical scenario, we propose a picky loss function, which adaptively assigns higher weights to reliable time slots in the training set. Extensive experiments demonstrate that SORN outperforms state-of-the-art methods on multiple real-world industrial datasets.

Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. Specifically, our approach implicitly captures spatiotemporal heterogeneity through learning spatial and temporal embeddings, which can be viewed as a clustering process. Then, a novel spatiotemporal meta-parameter learning paradigm is proposed to learn spatiotemporal-specific parameters from meta-parameter pools, which is informed by the captured heterogeneity. Based on these ideas, we develop a Heterogeneity-Informed Spatiotemporal Meta-Network (HimNet) for spatiotemporal time series forecasting. Extensive experiments on five widely-used benchmarks demonstrate our method achieves state-of-the-art performance while exhibiting superior interpretability. Our code is available at https://github.com/XDZhelheim/HimNet.

Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications. Recent advances in Foundation Models (FMs) have fundamentally reshaped the paradigm of model design for time series analysis, boosting various downstream tasks in practice. These innovative approaches often leverage pre-trained or fine-tuned FMs to harness generalized knowledge tailored for time series analysis. This survey aims to furnish a comprehensive and up-to-date overview of FMs for time series analysis. While prior surveys have predominantly focused on either application or pipeline aspects of FMs in time series analysis, they have often lacked an in-depth understanding of the underlying mechanisms that elucidate why and how FMs benefit time series analysis. To address this gap, our survey adopts a methodology-centric classification, delineating various pivotal elements of time-series FMs, including model architectures, pre-training techniques, adaptation methods, and data modalities. Overall, this survey serves to consolidate the latest advancements in FMs pertinent to time series analysis, accentuating their theoretical underpinnings, recent strides in development, and avenues for future exploration.

Time series data has become ubiquitous across various fields such as healthcare, finance, entertainment, and transportation, driven by advancements in sensing technologies that enable continuous monitoring and recording. This growth in data size and complexity presents new challenges for traditional analysis techniques, necessitating the development of advanced, interdisciplinary temporal mining algorithms. The goals of this workshop are to: (1) highlight significant challenges in learning and mining from time series data, such as irregular sampling, spatiotemporal structures, and uncertainty quantification; (2) discuss recent developments in algorithmic, theoretical, statistical, and systems-based approaches for addressing these challenges, including both classical methods and large language models (LLMs); and (3) synergize research efforts by exploring both new and open problems in time series analysis and mining. This workshop will focus on both the theoretical and practical aspects of time series data analysis, providing a platform for researchers and practitioners from academia, government, and industry to discuss potential research directions, critical technical issues, and present solutions for practical applications. Contributions from related fields such as AI, machine learning, data science, and statistics are also included.

Recent advanced AI technologies, especially large language models (LLMs) like GPTs, have significantly advanced the field of data mining and led to the development of various LLM-based applications. AI for education (AI4EDU) is a vibrant multi-disciplinary field of data mining, machine learning, and education, with increasing importance and extraordinary potential. In this field, LLM and adaptive learning-based models can be utilized as interfaces in human-in-the-loop education systems, where the model serves as a mediator among the teacher, students, and machine capabilities, including its own. This perspective has several benefits, including the ability to personalize interactions, allow unprecedented flexibility and adaptivity for human-AI collaboration and improve the user experience. However, several challenges still exist, including the need for more robust and efficient algorithms, designing effective user interfaces, and ensuring ethical considerations are addressed. This workshop aims to bring together researchers and practitioners from academia and industry to explore cutting-edge AI technologies for personalized education, especially the potential of LLMs and adaptive learning technologies.

Logs are ubiquitous digital footprints, playing an indispensable role in system diagnostics, security analysis, and performance optimization. The extraction of actionable insights from logs is critically dependent on the log parsing process, which converts raw logs into structured formats for downstream analysis. Yet, the complexities of contemporary systems and the dynamic nature of logs pose significant challenges to existing automatic parsing techniques. The emergence of Large Language Models (LLM) offers new horizons. With their expansive knowledge and contextual prowess, LLMs have been transformative across diverse applications. Building on this, we introduce LogParser-LLM, a novel log parser integrated with LLM capabilities. This union seamlessly blends semantic insights with statistical nuances, obviating the need for hyper-parameter tuning and labeled training data, while ensuring rapid adaptability through online parsing. Further deepening our exploration, we address the intricate challenge of parsing granularity, proposing a new metric and integrating human interactions to allow users to calibrate granularity to their specific needs. Our method's efficacy is empirically demonstrated through evaluations on the Loghub-2k and the large-scale LogPub benchmark. In evaluations on the LogPub benchmark, involving an average of 3.6 million logs per dataset across 14 datasets, our LogParser-LLM requires only 272.5 LLM invocations on average, achieving a 90.6% F1 score for grouping accuracy and an 81.1% for parsing accuracy. These results demonstrate the method's high efficiency and accuracy, outperforming current state-of-the-art log parsers, including pattern-based, neural network-based, and existing LLM-enhanced approaches.

In long-term time series forecasting (LTSF) tasks, an increasing number of works have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their underlying dynamics. Recognizing the chaotic nature of real-world data, our model, Attraos, incorporates chaos theory into LTSF, perceiving real-world time series as low-dimensional observations from unknown high-dimensional chaotic dynamical systems. Under the concept of attractor invariance, Attraos utilizes non-parametric Phase Space Reconstruction embedding along with a novel multi-resolution dynamic memory unit to memorize historical dynamical structures, and evolves by a frequency-enhanced local evolution strategy. Detailed theoretical analysis and abundant empirical evidence consistently show that Attraos outperforms various LTSF methods on mainstream LTSF datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.

Cultural bias is pervasive in many large language models (LLMs), largely due to the deficiency of data representative of different cultures. Typically, cultural datasets and benchmarks are constructed either by extracting subsets of existing datasets or by aggregating from platforms such as Wikipedia and social media. However, these approaches are highly dependent on real-world data and human annotations, making them costly and difficult to scale. Inspired by cognitive theories on social communication, this paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. CulturePark simulates cross-cultural human communication with LLM-based agents playing roles in different cultures. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. Using CulturePark, we generated 41,000 cultural samples to fine-tune eight culture-specific LLMs. We evaluated these models across three downstream tasks: content moderation, cultural alignment, and cultural education. Results show that for content moderation, our GPT-3.5-based models either match or outperform GPT-4 on $41$ datasets. Regarding cultural alignment, our models surpass GPT-4 on Hofstede's VSM 13 framework. Furthermore, for cultural education of human participants, our models demonstrate superior outcomes in both learning efficacy and user experience compared to GPT-4. CulturePark proves an important step in addressing cultural bias and advancing the democratization of AI, highlighting the critical role of culturally inclusive data in model training. Code is released at https://github.com/Scarelette/CulturePark.

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of language models (LMs) for time series analysis, dedicated parameters for various downstream forecasting tasks need training, which hinders the common knowledge sharing across domains. Moreover, data owners may hesitate to share the access to local data due to privacy concerns and copyright protection, which makes it impossible to simply construct a FM on cross-domain training instances. To address these issues, we propose Time-FFM, a Federated Foundation Model for Time series forecasting by leveraging pretrained LMs. Specifically, we begin by transforming time series into the modality of text tokens. To bootstrap LMs for time series reasoning, we propose a prompt adaption module to determine domain-customized prompts dynamically instead of artificially. Given the data heterogeneity across domains, we design a personalized federated training strategy by learning global encoders and local prediction heads. Our comprehensive experiments indicate that Time-FFM outperforms state-of-the-arts and promises effective few-shot and zero-shot forecaster. The code is available at https://github.com/CityMind-Lab/NeurIPS24-Time-FFM/tree/main.

Time series data are ubiquitous across a wide range of real-world domains. Whilereal-world time series analysis (TSA) requires human experts to integrate numerical series data with multimodal domain-specific knowledge, most existing TSAmodels rely solely on numerical data, overlooking the significance of information beyond numerical series. This oversight is due to the untapped potentialof textual series data and the absence of a comprehensive, high-quality multimodal dataset. To overcome this obstacle, we introduce Time-MMD, the firstmulti-domain, multimodal time series dataset covering 9 primary data domains.Time-MMD ensures fine-grained modality alignment, eliminates data contamination, and provides high usability. Additionally, we develop MM-TSFlib, thefirst-cut multimodal time-series forecasting (TSF) library, seamlessly pipeliningmultimodal TSF evaluations based on Time-MMD for in-depth analyses. Extensiveexperiments conducted on Time-MMD through MM-TSFlib demonstrate significant performance enhancements by extending unimodal TSF to multimodality,evidenced by over 15% mean squared error reduction in general, and up to 40%in domains with rich textual data. More importantly, our datasets and libraryrevolutionize broader applications, impacts, research topics to advance TSA. Thedataset is available at https://github.com/AdityaLab/Time-MMD.

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a fully unlabeled graph. We reveal that having access to the normal nodes, even just a small percentage of normal nodes, helps enhance the detection performance of existing unsupervised GAD methods when they are adapted to the semi-supervised setting. However, their utilization of these normal nodes is limited. In this paper, we propose a novel Generative GAD approach (namely GGAD) for the semi-supervised scenario to better exploit the normal nodes. The key idea is to generate pseudo anomaly nodes, referred to as 'outlier nodes', for providing effective negative node samples in training a discriminative one-class classifier. The main challenge here lies in the lack of ground truth information about real anomaly nodes. To address this challenge, GGAD is designed to leverage two important priors about the anomaly nodes -- asymmetric local affinity and egocentric closeness -- to generate reliable outlier nodes that assimilate anomaly nodes in both graph structure and feature representations. Comprehensive experiments on six real-world GAD datasets are performed to establish a benchmark for semi-supervised GAD and show that GGAD substantially outperforms state-of-the-art unsupervised and semi-supervised GAD methods with varying numbers of training normal nodes.

This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence. Traditional survey paper creation faces challenges due to the vast volume and complexity of information, prompting the need for efficient survey methods. While large language models (LLMs) offer promise in automating this process, challenges such as context window limitations, parametric knowledge constraints, and the lack of evaluation benchmarks remain. AutoSurvey addresses these challenges through a systematic approach that involves initial retrieval and outline generation, subsection drafting by specialized LLMs, integration and refinement, and rigorous evaluation and iteration. Our contributions include a comprehensive solution to the survey problem, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness.

Time series analysis is widely used in many fields such as power energy, economics, and transportation, including different tasks such as forecasting, anomaly detection, classification, etc. Missing values are widely observed in these tasks, and often leading to unpredictable negative effects on existing methods, hindering their further application. In response to this situation, existing time series imputation methods mainly focus on restoring sequences based on their data characteristics, while ignoring the performance of the restored sequences in downstream tasks. Considering different requirements of downstream tasks (e.g., forecasting), this paper proposes an efficient downstream task-oriented time series imputation evaluation approach. By combining time series imputation with neural network models used for downstream tasks, the gain of different imputation strategies on downstream tasks is estimated without retraining, and the most favorable imputation value for downstream tasks is given by combining different imputation strategies according to the estimated gain.

The study of treatment effects is an essential area in causal inference that has received extensive attention in the sciences. When access to counterfactual groups and experimental settings is limited, the synthetic control method (SCM) emerges as a key approach for observational studies. However, conventional SCM techniques mainly concentrate on addressing confounding issues in the pre-treatment period, often overlooking the confounding effects of control groups in the post-treatment period. In this paper, we propose a new approach named Stable-SC, which integrates synthetic control with anomaly detection algorithms to mitigate the influence of confounding factors in both the pre- and post-treatment periods. Our algorithm incorporates an anomaly-detection process that identifies trends and distance anomalies within control groups, significantly impacting SCM estimation results. Subsequently, we employ a re-weighting schema to adjust the significance of these abnormal groups and utilize the Difference-in-Differences estimator to assess causal effects. Through extensive experimentation with multiple simulated and real-world datasets, we demonstrate that our Stable-SC approach yields more robust estimates compared to other existing methods in the literature. Furthermore, we have successfully applied our proposed framework in diverse business scenarios within a prominent retail company, where the need for stable and robust A/B testing is paramount in quantifying causal effects.

Most of current anomaly detection models assume that the normal pattern remains the same all the time. However, the normal patterns of web services can change dramatically and frequently over time. The model trained on old-distribution data becomes outdated and ineffective after such changes. Retraining the whole model whenever the pattern is changed is computationally expensive. Further, at the beginning of normal pattern changes, there is not enough observation data from the new distribution. Retraining a large neural network model with limited data is vulnerable to overfitting. Thus, we propose a Light Anti-overfitting Retraining Approach (LARA) based on deep variational auto-encoders for time series anomaly detection. In LARA we make the following three major contributions: 1) the retraining process is designed as a convex problem such that overfitting is prevented and the retraining process can converge fast; 2) a novel ruminate block is introduced, which can leverage the historical data without the need to store them; 3) we mathematically and experimentally prove that when fine-tuning the latent vector and reconstructed data, the linear formations can achieve the least adjusting errors between the ground truths and the fine-tuned ones. Moreover, we have performed many experiments to verify that retraining LARA with even a limited amount of data from new distribution can achieve competitive performance in comparison with the state-of-the-art anomaly detection models trained with sufficient data. Besides, we verify its light computational overhead.

Urban region profiling from web-sourced data is of utmost importance for urban computing. We are witnessing a blossom of LLMs for various fields, especially in multi-modal data research such as vision-language learning, where text modality serves as a supplement for images. As textual modality has rarely been introduced into modality combinations in urban region profiling, we aim to answer two fundamental questions: i) Can text modality enhance urban region profiling? ii) and if so, in what ways and which aspects? To answer the questions, we leverage the power of Large Language Models (LLMs) and introduce the first-ever LLM-enhanced framework that integrates the knowledge of text modality into urban imagery, named LLM-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining (UrbanCLIP ). Specifically, it first generates a detailed textual description for each satellite image by Image-to-Text LLMs. Then, the model is trained on image-text pairs, seamlessly unifying language supervision for urban visual representation learning, jointly with contrastive loss and language modeling loss. Results on urban indicator prediction in four major metropolises show its superior performance, with an average improvement of 6.1% on R2 compared to the state-of-the-art methods. Our code and dataset are available at https://github.com/StupidBuluchacha/UrbanCLIP.

Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial to unlocking the wealth of information implicit in available data. With the recent advancements in graph neural networks (GNNs), there has been a surge in GNN-based approaches for time series analysis. These approaches can explicitly model inter-temporal and inter-variable relationships, which traditional and other deep neural network-based methods struggle to do. In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation. Our aim is to guide designers and practitioners to understand, build applications, and advance research of GNN4TS. At first, we provide a comprehensive task-oriented taxonomy of GNN4TS. Then, we present and discuss representative research works and introduce mainstream applications of GNN4TS. A comprehensive discussion of potential future research directions completes the survey. This survey, for the first time, brings together a vast array of knowledge on GNN-based time series research, highlighting foundations, practical applications, and opportunities of graph neural networks for time series analysis.

Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we first comprehensively review existing surveys related to SSL and time series, and then provide a new taxonomy of existing time series SSL methods by summarizing them from three perspectives: generative-based, contrastive-based, and adversarial-based. These methods are further divided into ten subcategories with detailed reviews and discussions about their key intuitions, main frameworks, advantages and disadvantages. To facilitate the experiments and validation of time series SSL methods, we also summarize datasets commonly used in time series forecasting, classification, anomaly detection, and clustering tasks. Finally, we present the future directions of SSL for time series analysis.

With the continued migration of storage to cloud database systems, the impact of slow queries in such systems on services and user experience is increasing. Root-cause diagnosis plays an indispensable role in facilitating slow-query detection and revision. This paper proposes a method capable of both identifying possible root cause types for slow queries and ranking these according to their potential for accelerating slow queries. This enables prioritizing root causes with the highest impact, in turn improving slow-query revision effectiveness. To enable more accurate and detailed diagnoses, we propose the multimodal Ranking for the Root Causes of slow queries (RCRank) framework, which formulates root cause analysis as a multimodal machine learning problem and leverages multimodal information from query statements, execution plans, execution logs, and key performance indicators. To obtain expressive embeddings from its heterogeneous multimodal input, RCRank integrates self-supervised pre-training that enhances cross-modal alignment and task relevance. Next, the framework integrates root-cause-adaptive cross Transformers that enable adaptive fusion of multimodal features with varying characteristics. Finally, the framework offers a unified model that features an impact-aware training objective for identifying and ranking root causes. We report on experiments on real and synthetic datasets, finding that RCRank is capable of consistently outperforming the state-of-the-art methods at root cause identification and ranking according to a range of metrics.

Flink clusters often suffer from hotspot issues where the monitored job delay and CPU usage keep rising and remain high. This necessitates the detection of anomalous time series to pinpoint the hotspot machines. However, the state-of-the-art unsupervised time series anomaly detection (UTAD) methods are ineffective in this scenario. We identify two main reasons for this. First, the hotspot scenario requires us to pay particular attention to Flink-specific anomalies, e.g., slow-rising and high-level anomalies, which the existing methods struggle to address. Second, the state-of-the-art anomaly detection methods often assume that training datasets do not contain anomalies, but the data collected from the running Flink clusters contains noise, which causes these methods to learn anomalous patterns as normal patterns. In this paper, we first conduct experiments to analyze why existing methods fail in the Flink scenario. To tackle these challenges, we propose a cross-contrastive approach to learn the context information for each timestamp to enable Flink-specific anomaly detection. Then, to address noisy anomalies, we incorporate prior knowledge to set an anomaly boundary to prevent the model from learning anomalous patterns. Extensive experiments show that our method not only outperforms existing methods in the Flink scenario but also achieves state-of-the-art results on public benchmark datasets.

Unsupervised domain adaptation (UDA) of time series aims to teach models to identify consistent patterns across various temporal scenarios, disregarding domain-specific differences, which can maintain their predictive accuracy and effectively adapt to new domains. However, existing UDA methods struggle to adequately extract and align both global and local features in time series data. To address this issue, we propose theLocal-GlobalRepresentationAlignment framework (LogoRA), which employs a two-branch encoder–comprising a multi-scale convolutional branch and a patching transformer branch. The encoder enables the extraction of both local and global representations from time series. A fusion module is then introduced to integrate these representations, enhancing domain-invariant feature alignment from multi-scale perspectives. To achieve effective alignment, LogoRA employs strategies like invariant feature learning on the source domain, utilizing triplet loss for fine alignment and dynamic time warping-based feature alignment. Additionally, it reduces source-target domain gaps through adversarial training and per-class prototype alignment. Our evaluations on four time-series datasets demonstrate that LogoRA outperforms strong baselines by up to 12.52%, showcasing its superiority in time series UDA tasks.

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries. In this paper, we present a novel Transformer termed AirFormer to predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages: 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in Chinese Mainland. Compared to prior models, AirFormer reduces prediction errors by 5%∼8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

The existing resource allocation policy for application instances in Kubernetes cannot dynamically adjust according to the requirement of business, which would cause an enormous waste of resources during fluctuations. Moreover, the emergence of new cloud services puts higher resource management requirements. This paper discusses horizontal POD resources management in Alibaba Cloud Container Services with a newly deployed AI algorithm framework named AHPA - the adaptive horizontal pod auto-scaling system. Based on a robust decomposition forecasting algorithm and performance training model, AHPA offers an optimal pod number adjustment plan that could reduce POD resources and maintain business stability. Since being deployed in April 2021, this system has expanded to multiple customer scenarios, including logistics, social networks, AI audio and video, e-commerce, etc. Compared with the previous algorithms, AHPA solves the elastic lag problem, increasing CPU usage by 10% and reducing resource cost by more than 20%. In addition, AHPA can automatically perform flexible planning according to the predicted business volume without manual intervention, significantly saving operation and maintenance costs.

Electricity forecasting is crucial in scheduling and planning of future electric load, so as to improve the reliability and safeness of the power grid. Despite recent developments of forecasting algorithms in the machine learning community, there is a lack of general and advanced algorithms specifically considering requirements from the power industry perspective. In this paper, we present eForecaster, a unified AI platform including robust, flexible, and explainable machine learning algorithms for diversified electricity forecasting applications. Since Oct. 2021, multiple commercial bus load, system load, and renewable energy forecasting systems built upon eForecaster have been deployed in seven provinces of China. The deployed systems consistently reduce the average Mean Absolute Error (MAE) by 39.8% to 77.0%, with reduced manual work and explainable guidance. In particular, eForecaster also integrates multiple interpretation methods to uncover the working mechanism of the predictive models, which significantly improves forecasts adoption and user satisfaction.

Spatio-temporal graph neural networks (STGNN) have emerged as the dominant model for spatio-temporal graph (STG) forecasting. Despite their success, they fail to model intrinsic uncertainties within STG data, which cripples their practicality in downstream tasks for decision-making. To this end, this paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex ST dependencies. In this study, we present the first attempt to generalize the popular de-noising diffusion probabilistic models to STGs, leading to a novel non-autoregressive framework called DiffSTG, along with the first denoising network UGnet for STG in the framework. Our approach combines the spatio-temporal learning capabilities of STGNNs with the uncertainty measurements of diffusion models. Extensive experiments validate that DiffSTG reduces the Continuous Ranked Probability Score (CRPS) by 4%-14%, and Root Mean Squared Error (RMSE) by 2%-7% over existing methods on three real-world datasets.

Accurate prediction of electric load is crucial in power grid planning and management. In this paper, we solve the electric load forecasting problem under extreme events such as scorching heats. One challenge for accurate forecasting is the lack of training samples under extreme conditions. Also load usually changes dramatically in these extreme conditions, which calls for interpretable model to make better decisions. In this paper, we propose a novel forecasting framework, named Self-adaptive Decomposed Interpretable framework (SaDI), which ensembles long-term trend, short-term trend, and period modelings to capture temporal characteristics in different components. The external variable triggered loss is proposed for the imbalanced learning under extreme events. Furthermore, Generalized Additive Model (GAM) is employed in the framework for desirable interpretability. The experiments on both Central China electric load and public energy meters from buildings show that the proposed SaDI framework achieves average 22.14% improvement compared with the current state-of- the-art algorithms in forecasting under extreme events in terms of daily mean of normalized RMSE. Code, Public datasets, and Appendix are available at: https://doi.org/10.24433/CO.9696980.v1.

Periodicity detection is an important task in time series analysis, but still a challenging problem due to the diverse characteristics of time series data like abrupt trend change, outlier, noise, and especially block missing data. In this paper, we propose a robust and effective periodicity detection algorithm for time series with block missing data. We first design a robust trend filter to remove the interference of complicated trend patterns under missing data. Then, we propose a robust autocorrelation function (ACF) that can handle missing values and outliers effectively. We rigorously prove that the proposed robust ACF can still work well when the length of the missing block is less than 1/3 of the period length. Last, by combining the time-frequency information, our algorithm can generate the period length accurately. The experimental results demonstrate that our algorithm outperforms existing periodicity detection algorithms on real-world time series datasets.

Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also triggered great interest in the time series community. Among multiple advantages of Transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review Transformer schemes for time series modeling by highlighting their strengths as well as limitations. In particular, we examine the development of time series Transformers in two perspectives. From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis. From the perspective of applications, we categorize time series Transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance.

Time series data has become pervasive across domains such as finance, transportation, retail, entertainment, and healthcare. This shift towards continuous monitoring and recording, fueled by advancements in sensing technologies, necessitates the development of new tools and solutions. Despite extensive study, the importance of time series analysis continues to increase. However, modern time series data present challenges to existing techniques, including irregular sampling and spatiotemporal structures. Time series mining research is both challenging and rewarding as it connects diverse disciplines and requires interdisciplinary solutions. The goals of this workshop are to (1) highlight the significant challenges that underpin learning and mining from time series data (e.g., irregular sampling, spatiotemporal structure, uncertainty quantification), (2) discuss recent algorithmic, theoretical, statistical, or systems-based developments for tackling these problems, and (3) to synergize the research activities and discuss both new and open problems in time series analysis and mining. In summary, our workshop will focus on both the theoretical and practical aspects of time series data analysis and will provide a platform for researchers and practitioners from academia and industry to discuss potential research directions and critical technical issues and present solutions to tackle related issues in practical applications. We will invite researchers and practitioners from the related areas of AI, machine learning, data science, statistics, and many others to contribute to this workshop.

Time series anomaly detection is critical for a wide range of applications. It aims to identify deviant samples from the normal sample distribution in time series. The most fundamental challenge for this task is to learn a representation map that enables effective discrimination of anomalies. Reconstruction-based methods still dominate, but the representation learning with anomalies might hurt the performance with its large abnormal loss. On the other hand, contrastive learning aims to find a representation that can clearly distinguish any instance from the others, which can bring a more natural and promising representation for time series anomaly detection. In this paper, we propose DCdetector, a multi-scale dual attention contrastive representation learning model. DCdetector utilizes a novel dual attention asymmetric design to create the permutated environment and pure contrastive loss to guide the learning process, thus learning a permutation invariant representation with superior discrimination abilities. Extensive experiments show that DCdetector achieves state-of-the-art results on multiple time series anomaly detection benchmark datasets. Code is publicly available at https://github.com/DAMO-DI-ML/KDD2023-DCdetector.

Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing. However, most of the current research tends to view deep AD algorithms as a whole, without dissecting the contributions of individual design choices like loss functions and network architectures. This view tends to diminish the value of preliminary steps like data preprocessing, as more attention is given to newly designed loss functions, network architectures, and learning paradigms. In this paper, we aim to bridge this gap by asking two key questions: (i) Which design choices in deep AD methods are crucial for detecting anomalies? (ii) How can we automatically select the optimal design choices for a given AD dataset, instead of relying on generic, pre-existing solutions? To address these questions, we introduce ADGym, a platform specifically crafted for comprehensive evaluation and automatic selection of AD design elements in deep methods. Our extensive experiments reveal that relying solely on existing leading methods is not sufficient. In contrast, models developed using ADGym significantly surpass current state-of-the-art techniques.

Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms are designed for online time series forecasting, with some exploiting cross-variable dependency while others assume independence among variables. Given every data assumption has its own pros and cons in online time series modeling, we propose **On**line **e**nsembling **Net**work (**OneNet**). It dynamically updates and combines two models, with one focusing on modeling the dependency across the time dimension and the other on cross-variate dependency. Our method incorporates a reinforcement learning-based approach into the traditional online convex programming framework, allowing for the linear combination of the two models with dynamically adjusted weights. OneNet addresses the main shortcoming of classical online learning methods that tend to be slow in adapting to the concept drift. Empirical results show that OneNet reduces online forecasting error by more than $\mathbf{50}\\%$ compared to the State-Of-The-Art (SOTA) method.

An increasing number of distributed energy resources (DERs), such as rooftop photovoltaic (PV), electric vehicles (EVs), and distributed energy storage, are being integrated into the distribution systems. The rise of DERs has come hand-in-hand with large amounts of data generated and explosive growth in data collection, communication, and control devices. In addition, a massive number of consumers are involved in the interaction with the power grid to provide flexibility. Electricity consumers, power networks, and communication networks are three main parts of the distribution systems, which are deeply coupled. In this sense, smart distribution systems can be essentially viewed as cyber–physical–social systems. So far, extensive works have been conducted on the intersection of cyber, physical, and social aspects in distribution systems. These works involve two or three of the cyber, physical, and social aspects. Having a better understanding of how the three aspects are coupled can help to better model, monitor, control, and operate future smart distribution systems. In this regard, this article provides a comprehensive review of the coupling relationships among the cyber, physical, and social aspects of distribution systems. Remarkably, several emerging topics that challenge future cyber–physical–social distribution systems, including applications of 5G communication, the impact of COVID-19, and data privacy issues, are discussed. This article also envisions several future research directions or challenges regarding cyber–physical–social distribution systems.

Robust multivariate time series forecasting is crucial in many cyberphysical and Internet of Things applications. Existing state-of-the-art robust forecasting models decompose time series into independent functions covering trends and periodicities. However, these independent functions fail to capture correlations among multiple time series, thereby reducing prediction accuracy. Moreover, existing robust forecasting models treat certain abrupt but normal changes, e.g., caused by holidays, as outliers because they occur infrequently and have data distributions that resemble those of outliers. This exacerbates model bias and reduces prediction accuracy. This paper aims to capture correlations across multiple time series and abrupt but normal changes, thereby improving prediction accuracy. We employ weak labels to partition the dataset into source and target domains. Then, we propose the Domain Adversarial Robust Forecaster (DARF). This forecasting model is based on adversarial domain adaptation and includes two novel modules: Correlated Robust Forecaster (CORF) and Domain Critic. Specifically, CORF constitutes an encoder-decoder framework proficient at robust multivariate time series forecasting, and Domain Critic works to reduce data bias. Extensive experiments and discussions show that DARF is capable of state-of-the-art forecasting accuracy.

Predictive autoscaling is a key enabler for optimizing cloud resource allocation in Alibaba Cloud's computing platforms, which dynamically adjust the Elastic Compute Service (ECS) instances based on predicted user demands to ensure Quality of Service (QoS). However, user demands in the cloud are often highly complex, with high uncertainty and scale-sensitive temporal dependencies, thus posing great challenges for accurate prediction of future demands. These in turn make autoscaling challenging---autoscaling needs to properly account for demand uncertainty while maintaining a reasonable trade-off between two contradictory factors, i.e., low instance running costs vs. low QoS violation risks. To address the above challenges, we propose a novel predictive autoscaling framework MagicScaler , consisting of a Multi-scale attentive Gaussian process based predictor and an uncertainty-aware scaler. First, the predictor carefully bridges the best of two successful prediction methodologies---multi-scale attention mechanisms, which are good at capturing complex, multi-scale features, and stochastic process regression, which can quantify prediction uncertainty, thus achieving accurate demand prediction with quantified uncertainty. Second, the scaler takes the quantified future demand uncertainty into a judiciously designed loss function with stochastic constraints, enabling flexible trade-off between running costs and QoS violation risks. Extensive experiments on three clusters of Alibaba Cloud in different Chinese cities demonstrate the effectiveness and efficiency of MagicScaler , which outperforms other commonly adopted scalers, thus justifying our design choices.

Anomalies are ubiquitous in real-world time-series data which call for effective and timely detection, especially in an unsupervised setting for labeling cost saving. In this paper, we develop an unsupervised density reconstruction model for multi-dimensional time-series anomaly detection. In particular, it directly handles an important realistic setting that the detection is achieved towards raw time-series contaminated with noise for training, in contrast to most existing anomaly detection works that assume the training data is in general clean i.e. not contaminated with anomaly. It extends recent advancements in deep generative models and state space models to achieve robust anomaly detection. Our approach comprises of a novel state space based generative model, a filtering based inference model, together with a carefully-designated emission model based on robust statistics theory. Extensive experimental results are conducted to show that our approach can adapt to complex patterns even given severely contaminated training data. We also develop visualization techniques to help better understand the behavior of the anomaly detection models. Empirical results show that our method outperforms state-of-the-arts on both synthetic and real-world datasets.

Dynamic time warping (DTW) is an effective dissimilarity measure in many time series applications. Despite its popularity, it is prone to noises and outliers, which leads to singularity problem and bias in the measurement. The time complexity of DTW is quadratic to the length of time series, making it inapplicable in real-time applications. In this paper, we propose a novel time series dissimilarity measure named RobustDTW to reduce the effects of noises and outliers. Specifically, the RobustDTW estimates the trend and optimizes the time warp in an alternating manner by utilizing our designed temporal graph trend filtering. To improve efficiency, we propose a multi-level framework that estimates the trend and the warp function at a lower resolution, and then repeatedly refines them at a higher resolution. Based on the proposed RobustDTW, we further extend it to periodicity detection and outlier time series detection. Experiments on real-world datasets demonstrate the superior performance of RobustDTW compared to DTW variants in both outlier time series detection and periodicity detection.

Time series anomaly detection is a challenging problem due to the complex temporal dependencies and the limited label data. Although some algorithms including both traditional and deep models have been proposed, most of them mainly focus on time-domain modeling, and do not fully utilize the information in the frequency domain of the time series data. In this paper, we propose a Time-Frequency analysis based time series Anomaly Detection model, or TFAD for short, to exploit both time and frequency domains for performance improvement. Besides, we incorporate time series decomposition and data augmentation mechanisms in the designed time-frequency architecture to further boost the abilities of performance and interpretability. Empirical studies on widely used benchmark datasets show that our approach obtains state-of-the-art performance in univariate and multivariate time series anomaly detection tasks.

Localizing the root cause of network faults is crucial to network operation and maintenance. However, due to the complicated network architectures and wireless environments, as well as limited labeled data, accurately localizing the true root cause is challenging. In this paper, we propose a novel algorithm named NetRCA to deal with this problem. Firstly, we extract effective derived features from the original raw data by considering temporal, directional, attribution, and interaction characteristics. Secondly, we adopt multivariate time series similarity and label propagation to generate new training data from both labeled and unlabeled data to overcome the lack of labeled samples. Thirdly, we design an ensemble model which combines XGBoost, rule set learning, attribution model, and graph algorithm, to fully utilize all data information and enhance performance. Finally, experiments and analysis are conducted on the real-world dataset from ICASSP 2022 AIOps Challenge to demonstrate the superiority and effectiveness of our approach.

Autoscaling is a critical component for efficient resource utilization with satisfactory quality of service (QoS) in cloud computing. This paper investigates proactive autoscaling for widely-used scaling-per-query applications where scaling is required for each query, such as container registry and function-as-a-service (FaaS). In these scenarios, the workload often exhibits high uncertainty with complex temporal patterns like periodicity, noises and outliers. Conservative strategies that scale out unnecessarily many instances lead to high resource costs whereas aggressive strategies may result in poor QoS. We present RobustScaler to achieve superior trade-off between cost and QoS. Specifically, we design a novel autoscaling framework based on non-homogeneous Poisson processes (NHPP) modeling and stochastically constrained optimization. Furthermore, we develop a specialized alternating direction method of multipliers (ADMM) to efficiently train the NHPP model, and rigorously prove the QoS guarantees delivered by our optimization-based proactive strategies. Extensive experiments show that RobustScaler out-performs common baseline autoscaling strategies in various real-world traces, with large margins for complex workload patterns.

Long-term time series forecasting is challenging since prediction accuracy tends to decrease dramatically with the increasing horizon. Although Transformer-based methods have significantly improved state-of-the-art results for long-term forecasting, they are not only computationally expensive but more importantly, are unable to capture the global view of time series (e.g. overall trend). To address these problems, we propose to combine Transformer with the seasonal-trend decomposition method, in which the decomposition method captures the global profile of time series while Transformers capture more detailed structures. To further enhance the performance of Transformer for long-term prediction, we exploit the fact that most time series tend to have a sparse representation in a well-known basis such as Fourier transform, and develop a frequency enhanced Transformer. Besides being more effective, the proposed method, termed as Frequency Enhanced Decomposed Transformer (FEDformer), is more efficient than standard Transformer with a linear complexity to the sequence length. Our empirical studies with six benchmark datasets show that compared with state-of-the-art methods, Fedformer can reduce prediction error by 14.8% and 22.6% for multivariate and univariate time series, respectively. Code is publicly available at https://github.com/MAZiqing/FEDformer.

Time series forecasting is a critical and challenging problem in many real applications. Recently, Transformer-based models prevail in time series forecasting due to their advancement in long-range dependencies learning. Besides, some models introduce series decomposition to further unveil reliable yet plain temporal dependencies. Unfortunately, few models could handle complicated periodical patterns, such as multiple periods, variable periods, and phase shifts in real-world datasets. Meanwhile, the notorious quadratic complexity of dot-product attentions hampers long sequence modeling. To address these challenges, we design an innovative framework Quaternion Transformer (Quatformer), along with three major components: 1). learning-to-rotate attention (LRA) based on quaternions which introduces learnable period and phase information to depict intricate periodical patterns. 2). trend normalization to normalize the series representations in hidden layers of the model considering the slowly varying characteristic of trend. 3). decoupling LRA using global memory to achieve linear complexity without losing prediction accuracy. We evaluate our framework on multiple real-world time series datasets and observe an average 8.1% and up to 18.5% MSE improvement over the best state-of-the-art baseline.

Time series analysis is ubiquitous and important in various areas, such as Artificial Intelligence for IT Operations (AIOps) in cloud computing, AI-powered Business Intelligence (BI) in E-commerce, Artificial Intelligence of Things (AIoT), etc. In real-world scenarios, time series data often exhibit complex patterns with trend, seasonality, outlier, and noise. In addition, as more time series data are collected and stored, how to handle the huge amount of data efficiently is crucial in many applications. We note that these significant challenges exist in various tasks like forecasting, anomaly detection, and fault cause localization. Therefore, how to design effective and efficient time series models for different tasks, which are robust to address the aforementioned challenging patterns and noise in real-world scenarios, is of great theoretical and practical interests. In this tutorial, we provide a comprehensive and organized tutorial on the state-of-the-art algorithms of robust time series analysis, ranging from traditional statistical methods to the most recent deep learning based methods. We will not only introduce the principle of time series algorithms, but also provide insights into how to apply them effectively in practical real-world industrial applications. Specifically, we organize the tutorial in a bottom-up framework. We first present preliminaries from different disciplines including robust statistics, signal processing, optimization, and deep learning. Then, we identify and discuss those most-frequently processing blocks in robust time series analysis, including periodicity detection, trend filtering, seasonal-trend decomposition, and time series similarity. Lastly, we discuss recent advances in multiple time series tasks including forecasting, anomaly detection, fault cause localization, and autoscaling, as well as practical lessons of large-scale time series applications from an industrial perspective.

The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event prediction models are trained with sequential data collected at one time and need to generalize to newly arrived sequences in remote future, which requires models to handle temporal distribution shift from training to testing. In this paper, we first take a data-generating perspective to reveal a negative result that existing approaches with maximum likelihood estimation would fail for distribution shift due to the latent context confounder, i.e., the common cause for the historical events and the next event. Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems. On top of that, we propose a framework with hierarchical branching structures for learning context-specific representations. Comprehensive experiments on diverse tasks (e.g., sequential recommendation) demonstrate the effectiveness, applicability and scalability of our method with various off-the-shelf models as backbones.

Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found, however, that there is still great room for improvement in how to preserve historical information in neural networks while avoiding overfitting to noise present in the history. Addressing this allows better utilization of the capabilities of deep learning models. To this end, we design a Frequency improved Legendre Memory model, or FiLM: it applies Legendre polynomial projections to approximate historical information, uses Fourier projection to remove noise, and adds a low-rank approximation to speed up computation. Our empirical studies show that the proposed FiLM significantly improves the accuracy of state-of-the-art models in multivariate and univariate long-term forecasting by (19.2%, 22.6%), respectively. We also demonstrate that the representation module developed in this work can be used as a general plugin to improve the long-term prediction performance of other deep learning modules. Code is available at https://github.com/tianzhou2011/FiLM/.

As business of Alibaba expands across the world among various industries, higher standards are imposed on the service quality and reliability of big data cloud computing platforms which constitute the infrastructure of Alibaba Cloud. However, root cause analysis in these platforms is non-trivial due to the complicated system architecture. In this paper, we propose a root cause analysis framework called CloudRCA which makes use of heterogeneous multi-source data including Key Performance Indicators (KPIs), logs, as well as topology, and extracts important features via state-of-the-art anomaly detection and log analysis techniques. The engineered features are then utilized in a Knowledge-informed Hierarchical Bayesian Network (KHBN) model to infer root causes with high accuracy and efficiency. Ablation study and comprehensive experimental comparisons demonstrate that, compared to existing frameworks, CloudRCA 1) consistently outperforms existing approaches in f1-score across different cloud systems; 2) can handle novel types of root causes thanks to the hierarchical structure of KHBN; 3) performs more robustly with respect to algorithmic configurations; and 4) scales more favorably in the data and feature sizes. Experiments also show that a cross-platform transfer learning mechanism can be adopted to further improve the accuracy by more than 10%. CloudRCA has been integrated into the diagnosis system of Alibaba Cloud and employed in three typical cloud computing platforms including MaxCompute, Realtime Compute and Hologres. It saves Site Reliability Engineers (SREs) more than 20% in the time spent on resolving failures in the past twelve months and improves service reliability significantly.

Seasonal time series Forecasting remains a challenging problem due to the long-term dependency from seasonality. In this paper, we propose a two-stage framework to forecast univariate seasonal time series. The first stage explicitly learns the long-range time series structure in a time window beyond the forecast horizon. By incorporating the learned long-range structure, the second stage can enhance the prediction accuracy in the forecast horizon. In both stages, we integrate the auto-regressive model with neural networks to capture both linear and non-linear characteristics in time series. Our framework achieves state-of-the-art performance on M4 Competition Hourly datasets. In particular, we show that incorporating the intermediate results generated in the first stage to existing forecast models can effectively enhance their prediction performance.

Many real-world time series exhibit multiple seasonality with different lengths. The removal of seasonal components is crucial in numerous applications of time series, including forecasting and anomaly detection. However, many seasonal-trend decomposition algorithms suffer from high computational cost and require a large amount of data when multiple seasonal components exist, especially when the periodic length is long. In this paper, we propose a general and efficient multi-scale seasonal-trend decomposition algorithm for time series with multiple seasonality. We first down-sample the original time series onto a lower resolution, and then convert it to a time series with single seasonality. Thus, existing seasonal-trend decomposition algorithms can be applied directly to obtain the rough estimates of trend and the seasonal component corresponding to the longer periodic length. By considering the relationship between different resolutions, we formulate the recovery of different components on the high resolution as an optimization problem, which is solved efficiently by our alternative direction multiplier method (ADMM) based algorithm. Our experimental results demonstrate the accurate decomposition results with significantly improved efficiency.

Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many real-world time series applications may be limited such as classification in medical time series and anomaly detection in AIOps. As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data. In this paper, we systematically review different data augmentation methods for time series. We propose a taxonomy for the reviewed methods, and then provide a structured review for these methods by highlighting their strengths and limitations. We also empirically compare different data augmentation methods for different tasks including time series classification, anomaly detection, and forecasting. Finally, we discuss and highlight five future directions to provide useful research guidance.

Periodicity detection is a crucial step in time series tasks, including monitoring and forecasting of metrics in many areas, such as IoT applications and self-driving database management system. In many of these applications, multiple periodic components exist and are often interlaced with each other. Such dynamic and complicated periodic patterns make the accurate periodicity detection difficult. In addition, other components in the time series, such as trend, outliers and noises, also pose additional challenges for accurate periodicity detection. In this paper, we propose a robust and general framework for multiple periodicity detection. Our algorithm applies maximal overlap discrete wavelet transform to transform the time series into multiple temporal-frequency scales such that different periodic components can be isolated. We rank them by wavelet variance, and then at each scale detect single periodicity by our proposed Huber-periodogram and Huber-ACF robustly. We rigorously prove the theoretical properties of Huber-periodogram and justify the use of Fisher's test on Huber-periodogram for periodicity detection. To further refine the detected periods, we compute unbiased autocorrelation function based on Wiener-Khinchin theorem from Huber-periodogram for improved robustness and efficiency. Experiments on synthetic and real-world datasets show that our algorithm outperforms other popular ones for both single and multiple periodicity detection.

This paper studies the variance filtering and change of variance (CoV) detection under multiple change points in time series signal. In real world scenarios, CoV detection can be challenging since the time series signal may contain not only outliers but also abrupt trend changes. To deal with these challenges, we propose a robust CoV detection algorithm based on robust statistics and sparse regularizations. Specifically, we adopt Huber loss to suppress outliers both in trend removal and variance filtering, utilize sparse regu-larizations to capture trend and variance changes, and obtain accurate change points locations by using breakpoint detection for centered cumulative sum of the estimated variance. We compare our proposed robust CoV algorithm with other state-of-the-art CoV detection algorithms on both synthetic and public datasets. The experiments demonstrate that our algorithm outperforms existing methods.

Many real-world time series data exhibit complex patterns with trend, seasonality, outlier and noise. Robustly and accurately decomposing these components would greatly facilitate time series tasks including anomaly detection, forecasting and classification. RobustSTL is an effective seasonal-trend decomposition for time series data with complicated patterns. However, it cannot handle multiple seasonal components properly. Also it suffers from its high computational complexity, which limits its usage in practice. In this paper, we extend RobustSTL to handle multiple seasonality. To speed up the computation, we propose a special generalized ADMM algorithm to perform the decomposition efficiently. We rigorously prove that the proposed algorithm converges approximately as standard ADMM while reducing the complexity from O(N2) to O(N log N) for each iteration. We empirically study our proposed algorithm with other state-of-the-art seasonal-trend decomposition methods, including MSTL, STR, TBATS, on both synthetic and real-world datasets with single and multiple seasonality. The experimental results demonstrate the superior performance of our decomposition algorithm in terms of both effectiveness and efficiency.

Decomposing complex time series into trend, seasonality, and remainder components is an important task to facilitate time series anomaly detection and forecasting. Although numerous methods have been proposed, there are still many time series characteristics exhibiting in real-world data which are not addressed properly, including 1) ability to handle seasonality fluctuation and shift, and abrupt change in trend and reminder; 2) robustness on data with anomalies; 3) applicability on time series with long seasonality period. In the paper, we propose a novel and generic time series decomposition algorithm to address these challenges. Specifically, we extract the trend component robustly by solving a regression problem using the least absolute deviations loss with sparse regularization. Based on the extracted trend, we apply the the non-local seasonal filtering to extract the seasonality component. This process is repeated until accurate decomposition is obtained. Experiments on different synthetic and real-world time series datasets demonstrate that our method outperforms existing solutions.

Extracting the underlying trend signal is a crucial step to facilitate time series analysis like forecasting and anomaly detection. Besides noise signal, time series can contain not only outliers but also abrupt trend changes in real-world scenarios. To deal with these challenges, we propose a robust trend filtering algorithm based on robust statistics and sparse learning. Specifically, we adopt the Huber loss to suppress outliers, and utilize a combination of the first order and second order difference on the trend component as regularization to capture both slow and abrupt trend changes. Furthermore, an efficient method is designed to solve the proposed robust trend filtering based on majorization minimization (MM) and alternative direction method of multipliers (ADMM). We compared our proposed robust trend filter with other nine state-of-the-art trend filtering algorithms on both synthetic and real-world datasets. The experiments demonstrate that our algorithm outperforms existing methods.

Effective Lenstra-Lenstra-Lovász (ELLL) algorithm is a common low-complexity lattice reduction (LR) technique adopted in LR-aided successive interference cancellation (SIC) multiple-input multiple-output (MIMO) detectors. However, the original ELLL algorithm is undesirable for hardware implementation since the number and the sequence of ELLL iterations are not deterministic. To address these issues, some fixed-complexity ELLL (fcELLL) algorithms have recently been proposed. In this paper, we propose two new fcELLL algorithms to further improve the efficiency of existing fcELLL algorithms by eliminating unnecessary iterations, such that the fcEL-LL algorithm exhibits faster convergence and lower computational complexity. Compared to the existing fcELLL algorithms, simulations show that the proposed fcELLL algorithms can save up to 39%-48% complexity for 8 × 8 MIMO systems without performance loss.

Lenstra-Lenstra-Lovász (LLL) algorithm is a common technique for lattice reduction (LR) aided multiple-input multiple-output (MIMO) detectors. This paper presents the first VLSI implementation of a recently published Incremental fixed-complexity LLL algorithm (Incremental fcLLL) with fewer iterations than other existing fcLLL algorithms. We propose a modified Incremental fcLLL algorithm with simplified size reduction and Siegel condition as well as the designed two-angle complex Givens rotation for column swap, which eliminates all computationally intensive operations. By exploiting the proposed modified algorithm in a pipelined architecture, the implementation on a Xilinx Virtex-5 FPGA demonstrates a throughput of 26 cycles per matrix and near 8 M matrices per second, significantly outperforming the existing FPGA solutions.

The Lenstra-Lenstra-Lovász (LLL) algorithm has been adopted as a lattice reduction (LR) technique for multiple-input multiple-output (MIMO) communications to improve performance with low complexity. However, implementing the LLL algorithm is still challenging due to slow convergence especially for large channel matrices. One of the main reasons is that the column swap may not happen in some LLL iterations, which leads to more iterations. To address it, some greedy LLL algorithms have recently been proposed, which only perform the iterations with column swaps. In this paper, we propose two efficient greedy LLL algorithms for various LR-aided MIMO detectors. First, both algorithms use a relaxed Lovász condition to search the candidate set of LLL iterations. Then, to select an LLL iteration in the candidate set each time, one is based on a relaxed decrescence of LLL potential, and the other takes the error performance of the LR-aided MIMO detectors into consideration. The proposed two algorithms are proved to collect full receive diversity in both LR-aided linear and successive-interference-cancellation detectors. Furthermore, compared to existing greedy LLL algorithms, simulations show that the proposed two algorithms not only converge faster but also exhibit much lower complexity while maintaining comparable error performance in LR-aided MIMO detectors.

Lenstra-Lenstra-Lovász (LLL) lattice reduction technique has been applied to multiple-input multiple-output (MIMO) detectors to collect full diversity while enjoying low complexity. However, the original LLL algorithm has variable complexity, which is not desirable in hardware implementation. To solve this problem, some fixed-complexity LLL (fcLLL) algorithms have recently been proposed by using the fixed-column traverse strategy with limited number of LLL iterations. The existing fcLLL algorithms are designed to process each column with equal priority, which is not optimized in terms of error performance and complexity. In this paper, we propose an enhanced fcLLL algorithm with a novel column traverse strategy by allocating priorities to columns based on the characteristics of LLL and MIMO detection. In addition, we propose an improved termination criterion without sacrificing the error performance in the proposed fcLLL algorithm. Simulations show that our proposed fcLLL algorithm converges faster than LLL and existing fcLLL algorithms, and yields better error performance than the LLL and existing fcLLL algorithms when the maximum number of LLL iterations is fixed. Furthermore, in large MIMO systems, our proposed fcLLL algorithm exhibits significant complexity advantage, saving about 90% LLL iterations in average compared to the existing fcLLL algorithms for a 128× 128 MIMO system with 64-QAM.

Multiple-input multiple-output (MIMO) techniques provide high data rates but the optimal maximum likelihood (ML) detector exhibits high complexity. Recently lattice reduction (LR) aided detectors have been proposed to achieve near-ML performance with low complexity. In this paper, we develop a LR-aided complex K-best algorithm which reduces the complexity of the existing sphere decoding based K-best algorithm. Then we provide the fixed-point design of the LR-aided K-best MIMO receiver for both coded and uncoded systems. The architecture selection of each sub-module is developed and a simulation-based wordlength optimization procedure is proposed. Simulations show that the fixed-point results can keep bit error rate degradation within 0.2dB under 8 × 8 256-QAM MIMO systems.

Partial transmit sequence (PTS) is an attractive distortless peak-to-average power ratio (PAPR) reduction technique for orthogonal frequency division multiplexing (OFDM) system. However, the complexity of PTS increases exponentially with the number of sub-blocks as it requires an exhaustive searching over all phase factor combinations. In this paper, we explored the correlation among the multiple candidate signals of PTS and proposed a modified scheme with lower complexity. The main idea is based on selecting a subset from the whole set of candidate signals by analyzing the correlation of candidate signals. Simulation results show that the performance of the modified scheme is close to the theoretical lower bound and outperforms selected mapping (SLM) scheme with the same computational complexity.

The high peak-to-average power ratio (PAPR) is one of the main drawbacks of multicarrier code division multiple access (MC-CDMA) system. To alleviate this problem, in this paper, we propose a novel user grouping scheme for PAPR reduction in the downlink of MC-CDMA. The basic principle is to partition the users into subgroups, and generate multiple alternatives to achieve considerable PAPR reduction. The proposed scheme can be regarded as a modified version of partial transmit sequence (PTS), but with improved performance. And simulation results show that the user grouping scheme is more effective than the conventional PTS in MC-CDMA system.

This letter presents a class of low complexity partial transmit sequence (LC-PTS) techniques for reducing the peak-to- average power ratio (PAPR) in orthogonal frequency division multiplexing (OFDM) systems. The basic principle is to analyze and utilize the correlation among the candidate signals generated in PTS, so as to simplify the computational complexity. Furthermore, the proposed technique focuses on simplifying the computation for each candidate signal, instead of reducing the total number of candidate signals such as in (Jayalath and Tellambura, 2000). Thus, it can be easily combined with other simplified techniques. Simulation results show that the new technique can effectively reduce the complexity compared with the conventional PTS scheme.