iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

2023/10/10 by Yong Liu, Liu, Yong, Tengge Hu +11 · 1 voice · 371 citations
Computer Science · Decision Sciences · Engineering · #Computer science #Electrical engineering #Engineering #Geology #Neural Networks and Applications #Series (stratigraphy) #Stock Market Forecasting Methods #Time Series Analysis and Forecasting #Transformer #Voltage

paper · pdf · doi:10.48550/arxiv.2310.06625

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2023/10/10 · openalex created_date 2023/10/12 · openalex updated_date 2026/08/01

Abstract

The recent boom of linear forecasting models questions the ongoing passion for architectural modifications of Transformer-based forecasters. These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series, with each token formed by multiple variates of the same timestamp. However, Transformers are challenged in forecasting series with larger lookback windows due to performance degradation and computation explosion. Besides, the embedding for each temporal token fuses multiple variates that represent potential delayed events and distinct physical measurements, which may fail in learning variate-centric representations and result in meaningless attention maps. In this work, we reflect on the competent duties of Transformer components and repurpose the Transformer architecture without any modification to the basic components. We propose iTransformer that simply applies the attention and feed-forward network on the inverted dimensions. Specifically, the time points of individual series are embedded into variate tokens which are utilized by the attention mechanism to capture multivariate correlations; meanwhile, the feed-forward network is applied for each variate token to learn nonlinear representations. The iTransformer model achieves state-of-the-art on challenging real-world datasets, which further empowers the Transformer family with promoted performance, generalization ability across different variates, and better utilization of arbitrary lookback windows, making it a nice alternative as the fundamental backbone of time series forecasting. Code is available at this repository: https://github.com/thuml/iTransformer.

Cited by

• Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
• PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing
• CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting
• From Vector Autoregressions to AI-based Time Series Forecasting: A Review
• PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling
• HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
• Post-Training in Time Series Foundation Models: A Unifying Framework
• Regime-Aware Physics-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Using Thermo-Mechanical Signals
• Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting
• ClouDens: Operational Context-Aware Anomaly Detection for Large-scale Cloud System Monitoring
• LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
• A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-Fidelity Trade-offs and Limitations
• SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction
• Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting
• Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting
• Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification
• Fourier-mixed window attention for efficient and robust long sequence time-series forecasting
• Time Series Foundation Models for Process Model Forecasting
• Empirical Investigation of the Impact of Phase Information on Fault Diagnosis of Rotating Machinery
• What Matters in Deep Learning for Time Series Forecasting?
• TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
• Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
• DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling
• Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics
• Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
• Transformer-Based Modeling of User Interaction Sequences for Dwell Time Prediction in Human-Computer Interfaces
• DecoKAN: Interpretable Decomposition for Forecasting Cryptocurrency Market Dynamics
• LoFT-LLM: Low-Frequency Time-Series Forecasting with Large Language Models
• FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
• TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting
• BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
• Contrastive Time Series Forecasting with Anomalies
• Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
• DB2-TransF: All You Need Is Learnable Daubechies Wavelets for Time Series Forecasting
• Adaptive Information Routing for Multimodal Time Series Forecasting
• NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization
• Probabilistic Multi-Agent Aircraft Landing Time Prediction
• FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting
• STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
• DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting
• FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting
• Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
• TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
• RED-F: Reconstruction-Elimination based Dual-stream Contrastive Forecasting for Multivariate Time Series Anomaly Prediction
• MSTN: Fast and Efficient Multivariate Time Series Prediction Model
• Interpretable Air Pollution Forecasting by Physics-Guided Spatiotemporal Decoupling
• Partial multivariate transformer as a tool for cryptocurrencies time series prediction
• VitalBench: A Rigorous Multi-Center Benchmark for Long-Term Vital Sign Prediction in Intraoperative Care
• AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting
• TransactionGPT
• The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models
• Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment
• FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
• FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction
• Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Traffic
• Emission-Forecasting-Based Spatial-Temporal Carbon Response: A Multi-Agent Attention-Enhanced Deep Learning Framework
• An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
• LLM-TSFD: An industrial time series human-in-the-loop fault diagnosis method based on a large language model
• FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
• Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
• Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
• DBLoss: Decomposition-based Loss Function for Time Series Forecasting
• NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series
• SEMPO: Lightweight Foundation Models for Time Series Forecasting
• Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
• Foundation Model Forecasts: Form and Function
• An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Version
• Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
• Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective
• A Physics Prior-Guided Dual-Stream Attention Network for Motion Prediction of Elastic Bragg Breakwaters
• On Evaluating Loss Functions for Stock Ranking: An Empirical Analysis With Transformer Model
• CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
• Vision-LLMs for Spatiotemporal Traffic Forecasting
• LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting
• CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
• Inner-Instance Normalization for Time Series Forecasting
• MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis
• MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
• HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting
• TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting
• Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising
• Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN
• Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
• Benchmarking M-LTSF: Frequency and Noise-Based Evaluation of Multivariate Long Time Series Forecasting Models
• PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting
• Signature-Informed Transformer for Asset Allocation
• Cross-Modal Reconstruction Pretraining for Ramp Flow Prediction at Highway Interchanges
• TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
• FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
• EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting
• ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
• Kairos: Towards Adaptive and Generalizable Time Series Foundation Models
• TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
• Fidel-TS: A High-Fidelity Benchmark for Multimodal Time Series Forecasting
• ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection
• MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
• Mapping burdens and inequalities of polycystic ovary syndrome in young females across 953 locations 1990–2040 with deep learning forecasts
• Echo Flow Networks
• IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting
• Multi-Scale Spatial-Temporal Hypergraph Network with Lead-Lag Structures for Stock Time Series Forecasting
• How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting
• Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
• TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
• ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
• RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
• Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
• From Noise to Laws: Regularized Time-Series Forecasting via Denoised Dynamic Graphs
• Revisiting Multivariate Time Series Forecasting with Missing Values
• Learning Temporal Saliency for Time Series Forecasting with Cross-Scale Attention
• Aurora: Towards Universal Generative Multimodal Time Series Forecasting
• Unlocking the Power of Mixture-of-Experts for Task-Aware Time Series Analytics
• SciTS: Scientific Time Series Understanding and Generation with LLMs
• ChaosNexus: A Foundation Model for Universal Chaotic System Forecasting with Multi-scale Representations
• Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
• Lossless Compression: A New Benchmark for Time Series Model Evaluation
• VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion
• CoSupFormer : A Contrastive Supervised learning approach for EEG signal Classification
• From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting
• Transformer Modeling for Both Scalability and Performance in Multivariate Time Series
• MOMEMTO: Patch-based Memory Gate Model in Time Series Foundation Model
• TS-P²CL: Plug-and-Play Dual Contrastive Learning for Vision-Guided Medical Time Series Classification
• Conv-like Scale-Fusion Time Series Transformer: A Multi-Scale Representation for Variable-Length Long Time Series
• TSGym: Design Choices for Deep Multivariate Time-Series Forecasting
• GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts
• DPANet: Dual Pyramid Attention Network for Multivariate Time Series Forecasting
• IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorders
• Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
• Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework
• AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Use
• FTSCommDetector: Discovering Behavioral Communities through Temporal Synchronization
• Self Identity Mapping
• Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
• Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting
• Dynamic Relational Priming Improves Transformer in Multivariate Time Series
• A Time-Series Foundation Model by Universal Delay Embedding
• Detecting Multilevel Manipulation from Limit Order Book via Cascaded Contrastive Representation Learning
• Dynamic Adaptive Parsing of Temporal and Cross-Variable Patterns for Network State Classification
• AquaCast: Urban Water Dynamics Forecasting with Precipitation-Informed Multi-Input Transformer
• S²Transformer: Scalable Structured Transformers for Global Station Weather Forecasting
• FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model
• Towards Scalable and Structured Spatiotemporal Forecasting
• AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
• Synthetic Data Generation with Lorenzetti for Time Series Anomaly Detection in High-Energy Physics Calorimeters
• WindFM: An Open-Source Foundation Model for Zero-Shot Wind Power Forecasting
• Online time series prediction using feature adjustment
• One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
• StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecasting
• Speech Foundation Models Generalize to Time Series Tasks from Wearable Sensor Data
• Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models
• Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filtering
• Using normal to find abnormal: AI-based anomaly detection in gravitational wave data
• STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
• PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbations
• EventTSF: Event-Aware Non-Stationary Time Series Forecasting
• Uncovering Spontaneous Physics Representations in In-Context Learning
• CC-Time: Cross-Model and Cross-Modality Time Series Forecasting
• Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification
• Wavelet Mixture of Experts for Time Series Forecasting
• Semantic-Enhanced Time-Series Forecasting via Large Language Models
• FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
• PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting
• PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers
• PA-RNet: Perturbation-Aware Reasoning Network for Multimodal Time Series Forecasting
• JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis
• KANMixer: Can KAN Serve as a New Modeling Core for Long-term Time Series Forecasting?
• Semantically-Guided Inference for Conditional Diffusion Models: Enhancing Covariate Consistency in Time Series Forecasting
• CLIPTime: Time-Aware Multimodal Representation Learning from Images and Text
• Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion
• Time Series Forecasting Through the Lens of Dynamics
• State of Health Estimation of Batteries Using a Time-Informed Dynamic Sequence-Inverted Transformer
• U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecasting
• TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
• Diffusion Models for Time Series Forecasting: A Survey
• SDSC:A Structure-Aware Metric for Semantic Signal Representation Learning
• ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies
• Efficient Temporal Tokenization for Mobility Prediction with Large Language Models
• The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting
• FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series Prediction
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter
• Tailored Architectures for Time Series Forecasting: Evaluating Deep Learning Models on Gaussian Process-Generated Data
• Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
• KARMA: A Multilevel Decomposition Hybrid Mamba Framework for Multivariate Long-Term Time Series Forecasting
• Data Augmentation in Time Series Forecasting through Inverted Framework
• StellarF: A Physics-Informed LoRA Framework for Stellar Flare Forecasting with Historical & Statistical Data
• TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
• TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting
• NeuTSFlow: Modeling Continuous Functions Behind Time Series Forecasting
• TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion
• Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching
• Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection
• DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting
• Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems
• Extreme Value Theory-based Distributed Interference Prediction for 6G Industrial Sub-networks
• Temporal Window Smoothing of Exogenous Variables for Improved Time Series Prediction
• SCAWaveNet: A Spatial-Channel Attention-based Network for Global Significant Wave Height Retrieval
• When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
• Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives
• Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
• SPI-BoTER: Error Compensation for Industrial Robots via Sparse Attention Masking and Hybrid Loss with Spatial-Physical Information
• UniCA: Unified Covariate Adaptation for Time Series Foundation Model
• ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction
• SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
• Echo State Transformer: Attention Over Finite Memories
• Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series
• ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
• FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
• When Does Multimodality Lead to Better Time Series Forecasting?
• AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction
• Biaxialformer: Leveraging Channel Independence and Inter-Channel Correlations in EEG Signal Decoding for Predicting Neurological Outcomes
• SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
• Review of Machine Learning for Real-Time Analysis at the Large Hadron Collider experiments ALICE, ATLAS, CMS and LHCb
• Leveraging External Factors in Household-Level Electrical Consumption Forecasting using Hypernetworks
• A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction
• CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values
• TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
• A Review of the Long Horizon Forecasting Problem in Time Series Analysis
• MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolution
• Delayformer: spatiotemporal transformation for predicting high-dimensional dynamics
• Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
• LightGTS: A Lightweight General Time Series Forecasting Model
• LETS Forecast: Learning Embedology for Time Series Forecasting
• TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
• FaCTR: Factorized Channel-Temporal Representation Transformers for Efficient Time Series Forecasting
• Uncovering Insights of Compound Flooding with Data-Driven AI
• Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
• XicorAttention: Time Series Transformer Using Attention with Nonlinear Correlation
• Temporal Variational Implicit Neural Representations
• Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
• A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting
• Channel Normalization for Time Series Channel Identification
• Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification
• Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
• K²VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
• Non-collective Calibrating Strategy for Time Series Forecasting
• Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting
• Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model
• UDuo: Universal Dual Optimization Framework for Online Matching
• Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting
• TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
• PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series
• AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
• Are Data Embeddings effective in time series forecasting?
• SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
• A Unified Foundation Model for Wireless Technology Recognition and Localization
• Beyond Fixed Patches: Enhancing GPTs for Financial Prediction with Adaptive Segmentation and Learnable Wavelets
• Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
• Representation Learning of Limit Order Book: A Comprehensive Study and Benchmarking
• CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
• Latent-Regime Bias Auditing for Volatility Forecasting
• Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
• CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection
• TimeCF: A TimeMixer-Based Model with adaptive Convolution and Sharpness-Aware Minimization Frequency Domain Loss for long-term time seris forecasting
• HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
• Ellipsoidal Time Series Forecasting
• GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation
• FreshRetailNet-50K: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
• Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
• Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands
• Human in the Loop Adaptive Optimization for Improved Time Series Forecasting
• Time Tracker: Mixture-of-Experts-Enhanced Foundation Time Series Forecasting Model with Decoupled Training Pipelines
• R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
• Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting
• CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness
• Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model
• Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions
• This Time is Different: An Observability Perspective on Time Series Foundation Models
• TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
• Enhancing Channel-Independent Time Series Forecasting via Cross-Variate Patch Embedding
• Temporal Query Network for Efficient Multivariate Time Series Forecasting
• Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
• Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting
• Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting
• ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Data
• A Set-Sequence Model for Time Series
• ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Data
• OrEdge: Efficient Multi-Modal Anomaly Detection in Distributed Software Systems via Orthogonal-Domain Learning
• Feature Fitted Online Conformal Prediction for Deep Time Series Forecasting Model
• DELPHYNE: A Pre-Trained Model for General and Financial Time Series
• Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism
• A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction
• OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain
• Learning Soft Sparse Shapes for Efficient Time-Series Classification
• Accurate and Efficient Multivariate Time Series Forecasting via Offline Clustering
• Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet
• AROpt: An Optimization Method for Autoregressive Time Series Forecasting
• CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting
• How Effective are Large Time Series Models in Hydrology? A Study on Water Level Forecasting in Everglades
• FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection
• Dual-Forecaster: A Multimodal Time Series Model Integrating Descriptive and Predictive Texts
• Pretrained Time-Series Foundation Models for Financial Return Forecasting
• Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting
• Visual Reasoning over Time Series via Multi-Agent System
• Gateformer: Advancing Multivariate Time Series Forecasting through Temporal and Variate-Wise Attention with Gated Representations
• Rethinking Time Encoding via Learnable Transformation Functions
• NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting
• TopoPrimer: The Missing Topological Context in Forecasting Models
• A Market-Rule-Informed Neural Network for Efficient Imbalance Electricity Price Forecasting
• TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
• TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation
• CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
• Smart Predict--then--Optimize Paradigm for Portfolio Optimization in Real Markets
• CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationarity
• Goal-Oriented Time-Series Forecasting: Foundation Framework Design
• Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patients
• Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning
• DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection
• MMformer with Adaptive Transferable Attention: Advancing Multivariate Time Series Forecasting for Environmental Applications
• Multivariate Time Series Forecasting needs Cross Variable Loss
• Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support
• FISformer: Replacing Self-Attention with a Fuzzy Inference System in Transformer Models for Time Series Forecasting
• Fast-Powerformer: A Memory-Efficient Transformer for Accurate Mid-Term Wind Power Forecasting
• Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network
• Predictive AI with External Knowledge Infusion: Datasets and Benchmarks for Stock Markets
• Leveraging Large Self-Supervised Time-Series Models for Transferable Diagnosis in Cross-Aircraft Type Bleed Air System
• ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
• DP-LET: An Efficient Spatio-Temporal Network Traffic Prediction Framework

Discussions

• Inverted Transformers Are Effective for Time Series Forecasting [hn, 206 points, 38 comments]

Related

• Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers
• EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting
• LATST: Are Transformers Necessarily Complex for Time-Series Forecasting
• Are Transformers Effective for Time Series Forecasting?
• Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting