Pith. sign in

REVIEW 16 cited by

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.19072 v4 pith:R2HM75JQ submitted 2024-02-29 cs.LG cs.AI

Yuxuan Wang , Haixu Wu , Jiaxiang Dong , Guo Qin , Haoran Zhang , Yong Liu , Yunzhong Qiu , Jianmin Wang
show 1 more author
Mingsheng Long
This is my paper · ORCID
classification cs.LGcs.AI
keywords variablesforecastingendogenousexogenousinformationtimexerseriestime
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep models have demonstrated remarkable performance in time series forecasting. However, due to the partially-observed nature of real-world applications, solely focusing on the target of interest, so-called endogenous variables, is usually insufficient to guarantee accurate forecasting. Notably, a system is often recorded into multiple variables, where the exogenous variables can provide valuable external information for endogenous variables. Thus, unlike well-established multivariate or univariate forecasting paradigms that either treat all the variables equally or ignore exogenous information, this paper focuses on a more practical setting: time series forecasting with exogenous variables. We propose a novel approach, TimeXer, to ingest external information to enhance the forecasting of endogenous variables. With deftly designed embedding layers, TimeXer empowers the canonical Transformer with the ability to reconcile endogenous and exogenous information, where patch-wise self-attention and variate-wise cross-attention are used simultaneously. Moreover, global endogenous tokens are learned to effectively bridge the causal information underlying exogenous series into endogenous temporal patches. Experimentally, TimeXer achieves consistent state-of-the-art performance on twelve real-world forecasting benchmarks and exhibits notable generality and scalability. Code is available at this repository: https://github.com/thuml/TimeXer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 49 citations worldwide. Full citation record

  1. MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A diffusion model trained on C-GASF images of mobile usage generates synthetic user traces that match real trace statistics far better than prior time-series generative baselines.

  2. The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Bidirectional joint-attention, complete forecasting aggregation, and direct mapping form the most effective Transformer design for long-term time series forecasting.

  3. Leveraging External Factors in Household-Level Electrical Consumption Forecasting using Hypernetworks

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A hypernetwork that generates per-household linear forecast weights is the only global model in the test that improves its error when weather, holiday, and football-event data are added, beating other global models on...

  4. Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs

    cs.LG 2025-06 unverdicted novelty 6.0 of 10

    Time-R1 trains LLMs via supervised fine-tuning followed by reinforcement learning with a time-series-specific reward and non-uniform GRIP sampling to enable multi-step reasoning that improves forecasting accuracy.

  5. A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    DST-SGNN uses a Stiefel-manifold-constrained graph Fourier transform and a dynamic graph optimizer to achieve efficient and accurate spatio-temporal forecasting.

  6. Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting

    stat.ML 2026-07 reject novelty 5.0 of 10

    A two-stage forecaster (SPA trend extraction + LoRA-fine-tuned residual Transformer) that the paper claims beats prior models by 6.56% MASE, though the claim is not robust to its own extended baseline tables.

  7. Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Exogenous dropout, a model-agnostic whole-channel training mask, restores corruption robustness better than a deliberately bounded gated-FiLM architecture across three forecasting domains.

  8. BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting

    cs.AI 2025-08 conditional novelty 5.0 of 10

    BALM-TSF combines a statistical-prompt text branch with a patch-based time series branch, using scaling plus contrastive alignment to balance the two modalities, improving long-term and few-shot forecasting on five of...

  9. Inferring Effects of Major Events through Discontinuity Forecasting of Population Anxiety

    cs.LG 2025-08 conditional novelty 5.0 of 10

    Discontinuity forecasting predicts a county's anxiety jump and slope change after a major event from pre-event trends, reaching out-of-sample correlations of about .76 and .87.

  10. Camel: Energy-Aware LLM Inference on Resource-Constrained Devices

    cs.NI 2025-08 reject novelty 5.0 of 10

    The paper's stated abstract (Camel, energy-aware LLM inference) is unsupported by a full text that instead presents PatchECG, an ECG arrhythmia detection model, making the submission internally incoherent.

  11. Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives

    cs.LG 2025-06 reject novelty 5.0 of 10

    TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...

  12. Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    DRAGON maps discretized multivariate time series onto a de Bruijn graph with cross-dimension connections and uses graph attention to add global pattern memory to a CNN-based forecaster, improving short-context forecas...

  13. Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model

    cs.CL 2025-05 conditional novelty 5.0 of 10

    IOHFuseLM combines patient attributes and MAP waveforms through token-level alignment and diffusion-augmented pretraining, improving IOH event detection on two datasets over six baselines.

  14. PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A physics-informed positional encoding that embeds timestamps and latitude/longitude into a vision language model improves typhoon intensity and track forecasting on the Digital Typhoon dataset.

  15. Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A learnable fusor that reads meta-features of an input time series and weights 13 pre-trained forecasters per sample outperforms each individual model on most benchmark samples, including zero-shot settings.

  16. TS-RAG: Retrieval Augmented Generation for Time Series Forecasting

    cs.AI 2026-08 conditional novelty 4.0 of 10

    A retrieval-augmented transformer with learned reference tokens shows marginal average MSE improvement over strong baselines on six time series benchmarks.

Pith tools