# Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Rates

arXiv: https://arxiv.org/abs/2506.12459 · HTML: https://mlsanity.com/paper/2506.12459/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 68 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2012.09641/) (2020)
- [SAITS: Self-Attention-based Imputation for Time Series](https://mlsanity.com/paper/2202.08516/) (2022)
- [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2208.05233/) (2022)
- [N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting](https://mlsanity.com/paper/2201.12886/) (2022)
- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective](https://mlsanity.com/paper/2311.06190/) (2023)
- [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2206.09112/) (2022)
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022)
- [Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2206.09113/) (2022)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations](https://mlsanity.com/paper/2205.13479/) (2022)
- [Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://mlsanity.com/paper/2301.08871/) (2023)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction](https://mlsanity.com/paper/2308.03274/) (2023)
- [Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction](https://mlsanity.com/paper/2303.16005/) (2023)
- [Mutual Contrastive Learning for Visual Representation Learning](https://mlsanity.com/paper/2104.12565/) (2021)
- [XtremeDistil: Multi-stage Distillation for Massive Multilingual Models](https://mlsanity.com/paper/2004.05686/) (2020)
- [Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values](https://mlsanity.com/paper/1911.10273/) (2019)
- [Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition](https://mlsanity.com/paper/2207.11518/) (2022)
- [GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation](https://mlsanity.com/paper/2311.14332/) (2023)
- [INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging](https://mlsanity.com/paper/2302.02738/) (2023)
- [A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting](https://mlsanity.com/paper/2109.01657/) (2021)
- [GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing](https://mlsanity.com/paper/2405.11333/) (2024)

## Built on by (most cited first, 20 of 20)

- [TAB: Unified Benchmarking of Time Series Anomaly Detection Methods](https://mlsanity.com/paper/2506.18046/) (2025)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2603.08032/) (2026)
- [ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting](https://mlsanity.com/paper/2509.23313/) (2025)
- [Selective Learning for Deep Time Series Forecasting](https://mlsanity.com/paper/2510.25207/) (2025)
- [FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting](https://mlsanity.com/paper/2512.14253/) (2025)
- [Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis](https://mlsanity.com/paper/2607.01918/) (2026)
- [WPBench: A Comprehensive Benchmark for Wind Power Forecasting](https://mlsanity.com/paper/2609.24444/) (2026)
- [SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement](https://mlsanity.com/paper/2602.00589/) (2026)
- [GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization](https://mlsanity.com/paper/2605.12431/) (2026)
- [GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values](https://mlsanity.com/paper/2508.14083/) (2025)
- [Parameterized Prompt for Incremental Object Detection](https://mlsanity.com/paper/2510.27316/) (2025)
- [TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling](https://mlsanity.com/paper/2607.13101/) (2026)
- [UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations](https://mlsanity.com/paper/2609.22217/) (2026)
- [MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2609.24441/) (2026)
- [Aurora-X: Built for Extreme Time Series Forecasting](https://mlsanity.com/paper/2609.31038/) (2026)
- [WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting](https://mlsanity.com/paper/2609.31162/) (2026)
- [XMatch: Enhancing Covariate-Aware Time Series Forecasting through Tree-Structured Exogenous Matching](https://mlsanity.com/paper/2609.34939/) (2026)
- [QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting](https://mlsanity.com/paper/2610.06936/) (2026)

## Abstract (arXiv)

Multivariate Time Series Forecasting (MTSF) involves predicting future values of multiple interrelated time series. Recently, deep learning-based MTSF models have gained significant attention for their promising ability to mine semantics (global and local information) within MTS data. However, these models are pervasively susceptible to missing values caused by malfunctioning data collectors. These missing values not only disrupt the semantics of MTS, but their distribution also changes over time. Nevertheless, existing models lack robustness to such issues, leading to suboptimal forecasting performance. To this end, in this paper, we propose Multi-View Representation Learning (Merlin), which can help existing models achieve semantic alignment between incomplete observations with different missing rates and complete observations in MTS. Specifically, Merlin consists of two key modules: offline knowledge distillation and multi-view contrastive learning. The former utilizes a teacher model to guide a student model in mining semantics from incomplete observations, similar to those obtainable from complete observations. The latter improves the student model's robustness by learning from positive/negative data pairs constructed from incomplete observations with different missing rates, ensuring semantic alignment across different missing rates. Therefore, Merlin is capable of effectively enhancing the robustness of existing models against unfixed missing rates while preserving forecasting accuracy. Experiments on four real-world datasets demonstrate the superiority of Merlin.