Multivariate Time Series Forecasting

Follow this topic Ask about this topic

Momentum

46 papers in the last four weeks, up 39% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 223

All topics

An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
Jun 3, 2026Ossi LehtinenMultivariate Time Series Forecasting Time Series Transformers
Ocon Oy
REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning
Jun 3, 2026Weijia Li, Shun Hu, Yanfei KangMultivariate Time Series Forecasting Time Series Forecasting
School of Mathematical Sciences, Beihang University, Beijing, China · School of Economics and Management, Beihang University, Beijing, China
TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching
Jun 2, 2026Zhe Li, Jindong Tian, Hao Miao +3Irregular Time-Series Modeling Multivariate Time Series Forecasting
East China Normal University Shanghai, China · Hong Kong Polytechnic University Hong Kong, China · Aalborg University Aalborg, Denmark
Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
Jun 1, 2026Waleed Esmail, Stuart Russell, Jana Klinge +2Multivariate Time Series Forecasting Time Series Forecasting
Institut für Kernphysik, Universität Münster, Wilhelm-Klemm-Straße 9, 48149, Münster · Institut für Geophysik, Universität Münster, Corrensstraße 24, 48149, Münster · James Cook University, 1 James Cook Drive, Douglas, Queensland, 4814, Australia +1
RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
Jun 1, 2026Jainam Dhruva, Yousaf Raza, A. B. Siddique +1Multivariate Time Series Forecasting Synthetic-to-Real Domain Adaptation
Department of Computer Science University of Kentucky Lexington, KY 40506
VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
Jun 1, 2026Xudong Zhang, Jierui Lei, Jiacheng Li +3Multivariate Time Series Forecasting Latent Variable Models
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China. · Center for Machine Learning Research, Peking University, Beijing, China. · Amap, Alibaba Group, China. +2
FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting
May 31, 2026Peng He, Yao Liu, Yanglei Gan +3Multivariate Time Series Forecasting Frequency-Domain Feature Learning
University of Electronic Science and Technology of China · Chengdu, Sichuan, China
Airport Terminal Passenger Queue Forecasting for Departure Gates and Security Checkpoints
May 30, 2026Juhwan Lee, Seokbin Yoon, Keumjin Lee +2Multivariate Time Series Forecasting
Department of Air Transport, Transportation, and Logistics, Korea Aerospace University, Goyang, South Korea · Airport Industry Technology Research Institute, Incheon International Airport Corporation, Incheon, South Korea
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
May 29, 2026Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1Multivariate Time Series Forecasting Joint-Embedding Predictive Architecture
C3 AI, Redwood City, CA, USA
KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
May 28, 2026Kun Feng, Ziwei Shan, Yuchen Fang +6Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting
ShanghaiTech University · Ant Group
Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
May 28, 2026Haoxin Liu, Yichen Zhou, Rajat Sen +2Multivariate Time Series Forecasting LLM Post-Training
Georgia Institute of Technology · Google Research
Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration
May 27, 2026Haonan Wen, Hanyang Chen, Songhe FengIrregular Time-Series Modeling Multivariate Time Series Forecasting
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · Tangshan Research Institute, Beijing Jiaotong University Tangshan, China
Inpainting-Style Conditional Diffusion for Multivariable Time Series Forecasting
May 27, 2026Kourosh Kiani, S. M. MuyeenMultivariate Time Series Forecasting Time Series Forecasting
1Electrical and Computer Engineering, Semnan University, Semnan, Iran · Electrical Engineering Department, Qatar University, Doha, Qatar
QuITE: Query-Based Irregular Time Series Embedding
May 27, 2026Junghoon LimIrregular Time-Series Modeling Multivariate Time Series Forecasting
SK Shieldus, Seongnam, Republic of Korea
Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
May 26, 2026Yiding Liu, Yifan Hu, Hongjie Xia +5Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting
Transfer Learning using 66 Diseases for Disease Forecasting Applications
May 26, 2026Lauren J Beesley, Alexander C Murph, Dave Osthus +1Multivariate Time Series Forecasting Epidemic Forecasting
Statistics, Los Alamos National Laboratory · Computational Intelligence & Modeling, Los Alamos National Laboratory
BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
May 26, 2026Ruifeng Tan, Jintao Dong, Weixiang Hong +3Multivariate Time Series Forecasting RUL Estimation
School of Computer Science and Engineering, Central South University · Material Genome Institute, Shanghai University
Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling
May 26, 2026Haochen Yuan, Yichen Song, Yunbo Wang +1Multivariate Time Series Forecasting Time-Series Foundation Models
MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science Shanghai Jiao Tong University
Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting
May 26, 2026Shuang Liang, Chaochuan Hou, Xu Yao +4Multivariate Time Series Forecasting Forecasting Benchmarks
Shanghai University of Finance and Economics Shanghai, China · Ant Group Shanghai, China · Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai, China
STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms
May 25, 2026Ahmed Abdulaal, Maruf Aytekin, Thilaga kumaran Srinivasan +1Multivariate Time Series Forecasting Cloud Computing
Walmart Global Tech Sunnyvale, California, USA
Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations
May 25, 2026Eduardo Luiz Alba, Gilson Adamczuk Oliveira, Matheus Henrique Dal Molin Ribeiro +1Multivariate Time Series Forecasting Long-Term Time Series Forecasting
Industrial & Systems Engineering Graduate Program (PPGEPS), Federal University of Technology-Parana (UTFPR), Via do Conhecimento, KM 0l—Fraron, Pato Branco 85503-390, PR, Brazil
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
May 22, 2026Jinglin Li, Jun Tan, QI Fang +1Multivariate Time Series Forecasting Non-Stationary Time Series Forecasting
School of Computer Science and Engineering, Central South University, Changsha, China.
Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
May 21, 2026Marco Gregnanin, Johannes De Smedt, Giorgio Gnecco +1Multivariate Time Series Forecasting Graph Structure Learning
IMT School for Advanced Studies Lucca · KU Leuven · University of Chieti-Pescara
SURGE: An Event-Centric Social Media Sentiment Time Series Benchmark with Interaction Structure
May 20, 2026Chen Su, Pengsen Cheng, Yuanhe Tian +1Social Media Analysis Multivariate Time Series Forecasting
University of Science and Technology of China · Sichuan University · Zhongguancun Academy
Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics
May 20, 2026Adeline Hillier, Jennifer Sleeman, Jay Brett +3Neural Surrogate Modeling Multivariate Time Series Forecasting
Johns Hopkins Applied Physics Laboratory Hopkins University · Johns
Latent Laplace Diffusion for Irregular Multivariate Time Series
May 19, 2026Zinuo You, Jin Zheng, John CartlidgeIrregular Time-Series Modeling Multivariate Time Series Forecasting
School of Computer Science, University of Bristol · School of Engineering Mathematics and Technology, University of Bristol
Probabilistic Multivariate Time Series Forecasting with Diffusion Copulas
May 19, 2026David Huk, Dongshan Wang, Miha BresarMultivariate Time Series Forecasting Copula Models
Department of Statistics The University of Warwick · School of Data Science The Chinese University of Hong Kong, Shenzhen
Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks
May 19, 2026Rylan WadeMultivariate Time Series Forecasting Graph Neural Networks
University of Southern California
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
May 18, 2026Paul Quinlan, Jeremy Levasseur, Qingguo Li +1Cross-Modal Learning Multivariate Time Series Forecasting
1InertialAI · Department of Electrical and Computer Engineering, Queen’s University · Department of Mechanical and Materials Engineering, Queen’s University
Learning Long-Term Temporal Dependencies in Photovoltaic Power Output Prediction Through Multi-Horizon Forecasting
May 18, 2026Sumit Laha, Ankit Sharma, Hassan ForooshMultivariate Time Series Forecasting Time Series Forecasting
Department of Computer Science University of Central Florida Orlando, Florida, United States.

Jun 3, 2026, cs.LGJ/K move · Enter open · S save

An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers

Ossi Lehtinen

Ocon Oy

Multivariate Time Series Forecasting Time Series Transformers

Open paper AskPDF arXiv

Transformers consuming multi-channel scalar signals must embed

C

simultaneous values into one

d_{\text{model}}

-dimensional vector per time step. We audit eight input encoders -- a shared-scalar baseline, per-channel linear projections, an orthogonality regulariser, a nonlinear MLP, block-partitioned concatenation, channel-independent and channel-as-token architectures, and a projected positional encoding -- on a synthetic benchmark where channel identity is informative and on ETTh1, scored by next-step negative log-likelihood. The headline is practical near-equivalence within a wide "top tier": the standard per-channel linear projection matches every alternative up to small, statistically real but practically modest differences. A direct geometric probe attributes this to a spontaneous orthogonalisation of the per-channel projections: they end up near-orthogonal with no explicit regulariser, letting the standard linear recover channel identity from the summed embedding. Two encoders lose decisively: the shared-scalar baseline collapses for information-theoretic reasons we make explicit, and the channel-independent PatchTST-spirit baseline overfits universally on the synthetic benchmark and underperforms on both. Paired tests resolve two small gaps: projecting the sinusoidal positional encoding through a learned linear layer edges the rest at small

C

by extending this orthogonality to the positional subspace; a nonlinear MLP stem edges them at the largest

C

, with the gap shrinking under more training data. The practical recommendation: use the standard per-channel linear projection by default; reach for something more elaborate only when the task calls for it.

Momentum

Related topics

Latest papers 223