SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies

• URL: http://arxiv.org/abs/2605.14551v1
• Date: Thu, 14 May 2026 08:29:52 GMT
• Title: SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies
• Abstract summary: SeesawNet is a unified architecture that balances common and instance-specific dependency modeling in both temporal and channel dimensions.<n>At its core is Adaptive Stationary-Nonstationary Attention (ASNA), which captures common dependencies from normalized sequences and specific dependencies from raw sequences.<n>Built upon ASNA, SeesawNet alternates dedicated temporal and channel relationship modeling to jointly capture long-range and cross-variable dependencies.
• Score: 27.260310284240248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common patterns across samples. However, IN can over-smooth instance-specific structural information that is essential for modeling temporal and cross-channel heterogeneity. While prior methods further suppress distribution discrepancies or attempt to recover temporal specific dependencies, they often ignore a central tension: how to adaptively model common and instance-specific dependency based on each instance's non-stationary structures. To address this dilemma, we propose SeesawNet, a unified architecture that dynamically balances common and instance-specific dependency modeling in both temporal and channel dimensions. At its core is Adaptive Stationary-Nonstationary Attention (ASNA), which captures common dependencies from normalized sequences and specific dependencies from raw sequences, and adaptively fuses them according to instance-level non-stationarity. Built upon ASNA, SeesawNet alternates dedicated temporal and channel relationship modeling to jointly capture long-range and cross-variable dependencies. Extensive experiments on multiple real-world benchmarks demonstrate that SeesawNet consistently outperforms state-of-the-art methods.

Related papers

• TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching [15.279995924017458]
  TiWeaver is a unified framework designed to handle temporal dynamics and fine-grained inter-channel dependencies adaptively.<n>We evaluate TiWeaver on 12 real-world time series datasets, where it achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-06-02T04:06:12Z)
• XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis [10.642410240494238]
  We introduce XCTFormer, a transformer-based channel-dependent (CD) model that captures cross-temporal and cross-channel dependencies.<n>XCTFormer achieves strong results compared to widely recognized baselines.<n>It attains state-of-the-art performance on the imputation task, outperforming the second-best method by an average of 20.8% in MSE and 15.3% in MAE.
  arXiv  Detail & Related papers  (2026-05-18T15:18:22Z)
• TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting [67.91113180885601]
  TimeAPN explicitly models and predicts non-stationary factors from both the time and frequency domains.<n>TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons.<n>It outperforms state-of-the-art reversible normalization methods.
  arXiv  Detail & Related papers  (2026-03-18T07:21:24Z)
• Beyond Marginals: Learning Joint Spatio-Temporal Patterns for Multivariate Anomaly Detection [2.893006778402251]
  In time series data, an anomaly may be indicated by the simultaneous deviation of interrelated time series.<n>Our approach addresses this by modeling joint dependencies in the latent space.
  arXiv  Detail & Related papers  (2025-09-18T14:57:55Z)
• DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training [39.30046923897652]
  We propose a Dependency Controlled Pre-training framework that explicitly models dynamic, multi-scale dependencies by simulating evolving inter-patch dependencies.<n>DeCoP achieves state-of-the-art results on ten datasets with lower computing resources, improving MSE by 3% on ETTh1 over PatchTST using only 37% of the FLOPs.
  arXiv  Detail & Related papers  (2025-09-18T05:44:06Z)
• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting [51.94256702463408]
  Time series predictability is derived from periodic characteristics at different frequencies.<n>We propose a novel time series forecasting method based on multi-frequency reference series correlation analysis.<n> Experiments on major open and synthetic datasets show state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-11T11:40:14Z)
• DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting [43.071713191702486]
  DisenTS is a tailored framework for modeling disentangled channel evolving patterns in general time series forecasting. We introduce a novel Forecaster Aware Gate (FAG) module that generates the routing signals adaptively according to both the forecasters' states and input series' characteristics.
  arXiv  Detail & Related papers  (2024-10-30T12:46:14Z)
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting [98.12558945781693]
  We propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our experiments on several datasets for time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T14:39:28Z)
• Causal Temporal Regime Structure Learning [49.77103348208835]
  We present CASTOR, a novel method that concurrently learns the Directed Acyclic Graph (DAG) for each regime.<n>We establish the identifiability of the regimes and DAGs within our framework.<n>Experiments show that CASTOR consistently outperforms existing causal discovery models.
  arXiv  Detail & Related papers  (2023-11-02T17:26:49Z)
• Probabilistic Learning of Multivariate Time Series with Temporal Irregularity [21.361823581838355]
  Real-world time series often suffer from temporal irregularities, including nonuniform intervals and misaligned variables.<n>We propose an end-to-end framework that models temporal irregularities while capturing the joint distribution of variables at arbitrary continuous-time points.
  arXiv  Detail & Related papers  (2023-06-15T14:08:48Z)
• Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models [61.10851158749843]
  Key insights can be obtained by discovering lead-lag relationships inherent in the data. We develop a clustering-driven methodology for robust detection of lead-lag relationships in lagged multi-factor models.
  arXiv  Detail & Related papers  (2023-05-11T10:30:35Z)
• Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition [7.9603223299524535]
  This paper revisits conventional sequential modeling approaches, aiming to address the problem of capturing time-varying temporal dependency patterns. We propose a different formulation of HMMs, whereby the dependence on past frames is dynamically inferred from the data. We derive a tractable inference algorithm based on the forward-backward algorithm.
  arXiv  Detail & Related papers  (2020-02-13T23:18:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.